\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Tim P. BRUNDLE, ON BEHALF OF the CONSTELLIS EMPLOYEE STOCK OWNERSHIP PLAN, Plaintiff - Appellee, and Andrew Halldorson, on Behalf of the Constellis Employee Stock Ownership Plan, and on Behalf of a Class of All Other Persons Similarly Situated, Plaintiff, v. WILMINGTON TRUST, N.A., as Successor to Wilmington Trust Retirement and Institutional Services Company, Defendant - Appellant. American Society of Appraisers, Amicus Supporting Appellant, Secretary of the United States Department of Labor, Amicus Supporting Appellee. Tim P. Brundle, on Behalf of the Constellis Employee Stock Ownership Plan, Plaintiff - Appellant, and Andrew Halldorson, on Behalf of the Constellis Employee Stock Ownership Plan, and on Behalf of a Class of All Other Persons Similarly Situated, Plaintiff, v. Wilmington Trust, N.A., as Successor to Wilmington Trust Retirement and Institutional Services Company, Defendant - Appellee. Secretary of the United States Department of Labor, Amicus Supporting Appellant, American Society of Appraisers, Amicus Supporting Appellee. Tim P. Brundle, on Behalf of the Constellis Employee Stock Ownership Plan, Plaintiff - Appellee, and Andrew Halldorson, on Behalf of the Constellis Employee Stock Ownership Plan, and on Behalf of a Class of All Other Persons Similarly Situated, Plaintiff, Constellis Group, Inc., Party-In-Interest, v. Wilmington Trust, N.A., as Successor to Wilmington Trust Retirement and Institutional Services Company, Defendant - Appellant. American Society of Appraisers, Amicus Supporting Appellant, Secretary of the United States Department of Labor, Amicus Supporting Appellee. Tim P. Brundle, on Behalf of the Constellis Employee Stock Ownership Plan, Plaintiff - Appellee, and Andrew Halldorson, on Behalf of the Constellis Employee Stock Ownership Plan, and on Behalf of a Class of All Other Persons Similarly Situated, Plaintiff, v. Constellis Group, Inc., Party-In-Interest - Appellant, and Wilmington Trust, N.A., as Successor to Wilmington Trust Retirement and Institutional Services Company, Defendant. Tim P. Brundle, on Behalf of the Constellis Employee Stock Ownership Plan, Plaintiff - Appellant, and Andrew Halldorson, on Behalf of the Constellis Employee Stock Ownership Plan, and on Behalf of a Class of All Other Persons Similarly Situated, Plaintiff, v. Wilmington Trust, N.A., as Successor to Wilmington Trust Retirement and Institutional Services Company, Defendant - Appellee, Constellis Group, Inc., Party-In-Interest.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-03-21\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 17-1873\n\n\nTIM P. BRUNDLE, on behalf of the Constellis Employee Stock Ownership Plan,\n\n Plaintiff - Appellee,\n\n and\n\nANDREW HALLDORSON, on behalf of the Constellis Employee Stock\nOwnership Plan, and on behalf of a class of all other persons similarly situated,\n\n Plaintiff,\n\n v.\n\nWILMINGTON TRUST, N.A., as successor to Wilmington Trust Retirement and\nInstitutional Services Company,\n\n Defendant - Appellant.\n\n-------------------------------------------\n\nAMERICAN SOCIETY OF APPRAISERS,\n\n Amicus Supporting Appellant,\n\nSECRETARY OF THE UNITED STATES DEPARTMENT OF LABOR,\n\n Amicus Supporting Appellee.\n\n\n No. 17-2224\n\n\nTIM P. BRUNDLE, on behalf of the Constellis Employee Stock Ownership Plan,\n\f Plaintiff - Appellant,\n\n and\n\nANDREW HALLDORSON, on behalf of the Constellis Employee Stock\nOwnership Plan, and on behalf of a class of all other persons similarly situated,\n\n Plaintiff,\n\n v.\n\nWILMINGTON TRUST, N.A., as successor to Wilmington Trust Retirement and\nInstitutional Services Company,\n\n Defendant - Appellee.\n\n-------------------------------------------\n\nSECRETARY OF THE UNITED STATES DEPARTMENT OF LABOR,\n\n Amicus Supporting Appellant,\n\nAMERICAN SOCIETY OF APPRAISERS,\n\n Amicus Supporting Appellee.\n\n\n No. 17-2323\n\n\nTIM P. BRUNDLE, on behalf of the Constellis Employee Stock Ownership Plan,\n\n Plaintiff - Appellee,\n\n and\n\nANDREW HALLDORSON, on behalf of the Constellis Employee Stock\nOwnership Plan, and on behalf of a class of all other persons similarly situated,\n\n Plaintiff,\n\nCONSTELLIS GROUP, INC.,\n\n\n 2\n\f Party-in-Interest,\n\n v.\n\nWILMINGTON TRUST, N.A., as successor to Wilmington Trust Retirement and\nInstitutional Services Company,\n\n Defendant - Appellant.\n\n-------------------------------------------\n\nAMERICAN SOCIETY OF APPRAISERS,\n\n Amicus Supporting Appellant,\n\nSECRETARY OF THE UNITED STATES DEPARTMENT OF LABOR,\n\n Amicus Supporting Appellee.\n\n\n No. 17-2324\n\n\nTIM P. BRUNDLE, on behalf of the Constellis Employee Stock Ownership Plan,\n\n Plaintiff - Appellee,\n\n and\n\nANDREW HALLDORSON, on behalf of the Constellis Employee Stock\nOwnership Plan, and on behalf of a class of all other persons similarly situated,\n\n Plaintiff,\n\n v.\n\nCONSTELLIS GROUP, INC.,\n\n Party-in-Interest - Appellant,\n\n and\n\n\n\n 3\n\fWILMINGTON TRUST, N.A., as successor to Wilmington Trust Retirement and\nInstitutional Services Company,\n\n Defendant.\n\n\n No. 18-1029\n\n\nTIM P. BRUNDLE, on behalf of the Constellis Employee Stock Ownership Plan,\n\n Plaintiff - Appellant,\n\n and\n\nANDREW HALLDORSON, on behalf of the Constellis Employee Stock\nOwnership Plan, and on behalf of a class of all other persons similarly situated,\n\n Plaintiff,\n\n v.\n\nWILMINGTON TRUST, N.A., as successor to Wilmington Trust Retirement and\nInstitutional Services Company,\n\n Defendant - Appellee,\n\nCONSTELLIS GROUP, INC.,\n\n Party-in-Interest.\n\n\nAppeals from the United States District Court for the Eastern District of Virginia, at\nAlexandria. Leonie M. Brinkema, District Judge. (1:15-cv-01494-LMB-IDD)\n\n\nArgued: December 11, 2018 Decided: March 21, 2019\n\n\nBefore GREGORY, Chief Judge, and MOTZ and FLOYD, Circuit Judges.\n\n\n\n\n 4\n\fAffirmed by published opinion. Judge Motz wrote the opinion, in which Chief Judge\nGregory and Judge Floyd joined.\n\n\nARGUED: Carter Glasgow Phillips, SIDLEY AUSTIN LLP, Washington, D.C., for\nAppellant/Cross-Appellee Wilmington Trust, N.A. Gregory Y. Porter, BAILEY &\nGLASSER LLP, Washington, D.C., for Appellee/Cross-Appellant. Robin Springberg\nParry, UNITED STATES DEPARTMENT OF LABOR, Washington, D.C., for Amicus\nSecretary of Labor. ON BRIEF: James P. McElligott, Jr., Summer L. Speight,\nRichmond, Virginia, Stephen W. Robinson, MCGUIRE WOODS LLP, Tysons, Virginia;\nJacqueline G. Cooper, Kurt A. Johnson, SIDLEY AUSTIN LLP, Washington, D.C., for\nAppellant/Cross-Appellee Wilmington Trust, N.A. Edward Lee Isler, Micah E. Ticatch,\nISLER DARE, P.C., Vienna, Virginia, for Appellant Constellis Group, Inc. Tillman J.\nBreckenridge, Ryan T. Jenny, BAILEY & GLASSER LLP, Washington, D.C., for\nAppellee/Cross-Appellant. J. Christian Nemeth, Chicago, Illinois, Sophia A. Luby,\nWashington, D.C.; Eliot T. Burriss, Erin Turley, Calli Turner, MCDERMOTT WILL &\nEMERY LLP, Dallas, Texas, for Amicus American Society of Appraisers. Kate S.\nO’Scannlain, Solicitor of Labor, G. William Scott, Associate Solicitor for Plan Benefits\nSecurity, Thomas Tso, Counsel for Appellate and Special Litigation, UNITED STATES\nDEPARTMENT OF LABOR, Washington, D.C., for Amicus Secretary of Labor.\n\n\n\n\n 5\n\fDIANA GRIBBON MOTZ, Circuit Judge:\n\n After owners of a closely held corporation sold the company to its Employee\n\nStock Ownership Plan (“ESOP”), a participant in the ESOP brought this action. The\n\nparticipant contended that the trustee chosen for the ESOP by the corporation breached\n\nits fiduciary duties to the ESOP and overpaid for the stock — improperly enriching the\n\ncorporation’s owners at the expense of its employees.\n\n Following a multi-day bench trial, the district court issued detailed findings of fact\n\nconcluding that the trustee had indeed breached its fiduciary duties, causing the ESOP to\n\noverpay for the corporation’s stock by $29,773,250. The court entered judgment for the\n\nESOP in that amount and awarded attorneys’ fees to the participant’s counsel. These\n\nappeals and cross-appeals followed. As explained within, we affirm the careful findings\n\nof the district court.\n\n\n\n I.\n\n To facilitate understanding of the issues here, we begin with the governing legal\n\nprinciples and background facts that gave rise to this suit. The parties do not challenge\n\nthese principles or facts. All are more fully set forth in the comprehensive district court\n\nopinions, upon which we rely throughout. See Brundle v. Wilmington Tr. N.A., 241\n\nF. Supp. 3d 610 (E.D. Va. 2017) (“Brundle I”); Brundle v. Wilmington Tr. N.A., 258\n\nF. Supp. 3d 647 (E.D. Va. 2017) (“Brundle II”).\n\n\n\n\n 6\n\f A.\n\n The Employee Retirement Income Security Act of 1974 (ERISA) allows an\n\nemployer to create an ESOP, an employee pension plan that invests primarily in the\n\nemployer’s stock. The employer makes contributions to the plan that are used to\n\npurchase stock in the employer’s company. Because — and only because — an ESOP\n\ncontribution qualifies as employee compensation, an employer can deduct the total value\n\nof its ESOP contribution from its income tax liability as an ordinary business expense.\n\n26 U.S.C. § 404; 26 C.F.R. § 1.404(a)–1(b). 1 In this way, an ESOP benefits both\n\nemployees and employers by providing deferred compensation to the former and a\n\nvaluable tax deduction to the latter.\n\n ERISA imposes duties and obligations on all pension plan fiduciaries, including\n\nthose of ESOPs. These duties “ensure that employees will not be left empty-handed once\n\nemployers have guaranteed them certain benefits.” Lockheed Corp. v. Spink, 517 U.S.\n\n882, 887 (1996). One such provision prohibits the fiduciary of any ERISA plan from\n\ncausing a “sale or exchange . . . of any property between the plan and a party in interest.”\n\n29 U.S.C. § 1106(a)(1)(A). Absent a statutory exception, this provision would ban\n\nESOPs because their creation necessarily requires the ESOP to purchase stock from its\n\nsponsoring employer, which is a party in interest. Congress, however, has carved out an\n\n\n\n 1\n An employer’s contributions to an ESOP thus constitute a valuable form of\ndeferred compensation, rather than a gift to employees. See, e.g., Reich v. Hall Holding\nCo., 990 F. Supp. 955, 961 (N.D. Ohio 1998), aff’d sub nom. Chao v. Hall Holding Co.,\n285 F.3d 415 (6th Cir. 2002). Wilmington wisely does not suggest otherwise.\n\n 7\n\fexception to this prohibition to permit the creation of an ESOP if the stock purchase\n\nmeets certain conditions. See 29 U.S.C. § 1108(e).\n\n To protect employees from losing the value of their earned retirement savings, the\n\nexception to the ERISA ban on party-in-interest transactions requires that an ESOP pay\n\nno more than “adequate consideration” for the employer’s stock. Id. § 1108(e)(1). If an\n\nemployer’s “stock was not worth what the ESOP paid for it,” then the ESOP paid more\n\nthan adequate consideration and “the ESOP and its participants suffered a loss under\n\nERISA.” See Reich, 990 F. Supp. at 961.\n\n ERISA does not define what constitutes “adequate consideration” under the\n\n§ 1108(e) exception; the Department of Labor (DOL) has proposed, but never enacted,\n\nregulations doing so. 2 Although courts look to these regulations for guidance, the focus\n\nof the adequate-consideration inquiry rests on the conduct of a fiduciary, as judged by\n\nERISA’s “prudent man” standard of care. See Perez v. Bruister, 823 F.3d 250, 263 (5th\n\nCir. 2016); Henry III, 445 F.3d at 619; Chao, 285 F.3d at 437; Howard v. Shay, 100 F.3d\n\n1484, 1489 (9th Cir. 1996).\n\n Under this standard, “ESOP fiduciaries are subject to the duty of prudence just as\n\nother ERISA fiduciaries are.” Fifth Third Bancorp v. Dudenhoeffer, 134 S. Ct. 2459,\n\n 2\n These proposed regulations, to which courts look for guidance, provide that\n“adequate” consideration must (1) reflect the stock’s “fair market value,” and (2) be “the\nproduct of a determination made by the fiduciary in good faith.” Proposed Regulation\nRelating to the Definition of Adequate Consideration, 53 Fed. Reg. 17,632, 17,633\n(proposed May 17, 1988) (to be codified at 29 C.F.R. pt. 2510). “[I]n practice, the ‘fair\nmarket value’ inquiry overlaps considerably with the ‘good faith’ inquiry.’” Henry v.\nChamplain Enters., Inc., 445 F.3d 610, 618–19 (2d Cir. 2006) (Sotomayor, J.) (“Henry\nIII”) (collecting cases).\n\n 8\n\f2467 (2014). Thus an ESOP fiduciary, like any other ERISA fiduciary, must “discharge\n\nhis duties . . . with the care, skill, prudence, and diligence under the circumstances then\n\nprevailing that a prudent man acting in a like capacity and familiar with such matters\n\nwould use in the conduct of an enterprise of a like character and with like aims.” 29\n\nU.S.C. § 1104(a)(1)(B).\n\n Although these fiduciary duties “draw much of their content from the common law\n\nof trusts . . . ERISA’s standards and procedural protections partly reflect a congressional\n\ndetermination that the common law of trusts did not offer completely satisfactory\n\nprotection.” Tatum v. RJR Pension Inv. Comm., 761 F.3d 346, 357 (4th Cir. 2014)\n\n(internal quotation marks omitted). Courts apply the “prudent man rule . . . bearing in\n\nmind the special nature and purpose of employee benefit plans.” Id. (internal quotation\n\nmarks and alterations omitted). For this reason, “[t]he fiduciary obligations of the\n\ntrustees to the participants and beneficiaries [of an ERISA] plan are . . . the highest\n\nknown to the law.” Id. at 356 (alterations in original) (quoting Donovan v. Bierwith, 680\n\nF.2d 263, 272 n.8 (2d Cir. 1982)).\n\n Because an ESOP fiduciary that raises an affirmative defense under the § 1108(e)\n\nexception seeks to avoid ERISA liability for an otherwise prohibited transaction, the\n\nfiduciary bears the burden of proving by a preponderance of the evidence that the sale\n\nwas for adequate consideration. See Elmore v. Cone Mills Corp., 23 F.3d 855, 864 (4th\n\nCir. 1994) (en banc). “This burden is a heavy one.” Shay, 100 F.3d at 1488.\n\n B.\n\n With these principles in mind, we turn to the facts of this case.\n\n 9\n\f Since its inception, Constellis Group, Inc., the closely held parent company of a\n\ngroup of private security subsidiaries, has offered some form of deferred compensation to\n\nits employees, who are primarily retired members of the U.S. Armed Forces. Brundle I,\n\n241 F. Supp. 3d at 614. After initially offering a stock option program, Constellis\n\nreplaced that program with a profit-sharing plan in 2010. Id. In mid-2013, looking for an\n\n“exit strategy” after having twice tried and failed to effectuate a sale of the company, the\n\nowners of Constellis (hereinafter “the Sellers”) 3 began exploring the possibility of\n\ncreating an ESOP to purchase Constellis. Id. at 615.\n\n To that end, Constellis retained CSG International, an investment banking firm.\n\nCSG reported that sale of Constellis to an ESOP would not only enable the Sellers to\n\nliquidate their shares but would save them 23.8% in federal capital gains taxes. Id.\n\nAlthough noting that an ESOP would also benefit employees, CSG emphasized that\n\nselling Constellis to an ESOP provided the best option to optimize the Sellers’ after-tax\n\ncash return. See, e.g., id. at 616 (noting that CSG reported to the Sellers that, having\n\n“looked at every possible scenario,” it had not seen “any possible alternative that\n\nproduce[d] more after tax cash” than the proposed ESOP (internal quotation marks\n\nomitted)).\n\n CSG suggested that Constellis create what several trial witnesses characterized as\n\na “unique” ESOP structure to effectuate the sale. This unique structure would permit the\n\nSellers to retain de facto control of Constellis, even after the ESOP purchased all of the\n\n 3\n Four individuals owned 77% of Constellis stock at the time of the sale at issue\nhere. See Brundle I, 241 F. Supp. 3d at 615.\n\n 10\n\fcompany stock. Rather than sell 100% of their ownership interest to the ESOP, as is the\n\nusual practice, the Sellers would sell 90% of their shares to the ESOP and then exchange\n\nthe remaining 10% for “equity-like” warrants. These warrants would entitle the Sellers to\n\nbuy back equity in Constellis from the ESOP at a designated price and guarantee the\n\nSellers a majority on the board of directors. Id. at 626.\n\n To fund the ESOP’s purchase, Constellis would contribute 24% of the purchase\n\nprice and the ESOP would borrow the remainder from Constellis and the Sellers\n\nthemselves. Id. at 625. In late September 2013, Constellis decided to move forward with\n\nCSG’s proposal to create this unique ESOP. Id. To maximize the Sellers’ tax savings,\n\nConstellis had to complete the sale by the end of the calendar year. Id. at 622.\n\n On the recommendation of CSG, Constellis engaged Wilmington Trust, N.A., to\n\nserve as trustee for the ESOP. Id. at 616. In its role as trustee, Wilmington hired Stout\n\nRisius Ross (SRR) to be the financial advisor on the ESOP’s purchase of Constellis. Id.\n\nat 617. CSG, Wilmington, and SRR maintained significant long-term business\n\nrelationships, having worked together on more than twenty ESOP deals. Id. at 643\n\n(calling “the ESOP world . . . a very incestuous community”) (internal quotation marks\n\nomitted); id. at 617.\n\n On November 12, 2013, SRR submitted a draft valuation of Constellis stock to\n\nWilmington (the “SRR Report”). The SRR Report concluded that the fair market value\n\nfor a single share of Constellis stock lay between $3,865 and $4,600 — resulting in a\n\nrounded median price per share of $4,235. This placed the company’s worth, or its\n\n“enterprise value,” within a range of $275 to $330 million. Id. at 620–21. On November\n\n 11\n\f14, Wilmington met with analysts from SRR to discuss its report and valuation. At the\n\nmeeting’s conclusion, Wilmington set out to negotiate the ESOP’s purchase of Constellis\n\nwith authorization to offer a share price of $3,900 to $4,235. Id. at 622.\n\n The next day, Wilmington submitted an opening bid on behalf of the ESOP for\n\n$3,900 per share. Id. at 642. CSG, on behalf of Constellis, countered with $4,350 and\n\nsuggested to Wilmington that the ESOP and Constellis agree on a price first and then\n\nadjust the terms of the agreement at a later date. Wilmington agreed and raised its own\n\nbid to $4,100. CSG then countered with $4,250. By the end of the day, Wilmington and\n\nCSG had settled on a share price of $4,235 — the very top of Wilmington’s authorized\n\nnegotiation range. The negotiations lasted little more than five hours.\n\n The ESOP issued a tender offer for the shares on November 18 with a closing date\n\nof December 20. The parties finalized the term sheet on November 22. Between the\n\nconclusion of negotiations and the closing date for the transaction, SRR revised its\n\nvaluation of the draft enterprise range downward from $275–$330 million to $275–$325\n\nmillion, but the per share purchase price remained $4,235. On December 19, after\n\nmeeting with SRR for half an hour to discuss SRR’s valuation, Wilmington approved the\n\npurchase. Id. at 624. On December 20, the ESOP’s purchase of Constellis closed for a\n\nper share price of $4,235. Id. at 625.\n\n Subsequently, Tim P. Brundle, a former Constellis employee and ESOP\n\nparticipant, brought this action contending that Wilmington caused the ESOP to enter\n\n\n\n\n 12\n\finto a transaction prohibited under ERISA § 1106. 4 Brundle alleged that the $4,235 per\n\nshare paid by the ESOP for Constellis was too high and resulted in the ESOP overpaying\n\nthe Sellers for the stock. The district court initially held that the 2013 purchase of\n\nConstellis by the ESOP constituted a prohibited transaction under § 1106(a)(1). Brundle\n\nv. Wilmington Tr., N.A., 2016 WL 6542718, at *12 (E.D. Va. Nov. 3, 2016). Wilmington\n\nconceded as much before the district court but raised the adequate-consideration\n\naffirmative defense available under § 1108(e)(1). Id.\n\n Following a bench trial, the district court issued meticulous factual findings and\n\nconcluded on the basis of those findings that Wilmington had not established the\n\n§ 1108(e) affirmative defense. Rather, the court found that Wilmington had violated its\n\nfiduciary duty to the ESOP. The district court concluded that Wilmington’s fiduciary\n\nfailures resulted in the ESOP overpaying for the Constellis stock by $29,773,250, and so\n\nawarded that amount to the ESOP as damages. Brundle I, 241 F. Supp. 3d at 613.\n\n Brundle then moved for attorneys’ fees. The court first ordered Wilmington to\n\npay attorneys’ fees pursuant to ERISA’s fee-shifting provision, 29 U.S.C. § 1132(g)(1),\n\nin the amount of $1,819,631.11. Brundle II, 258 F. Supp. 3d at 663–69. It subsequently\n\nawarded an additional $1.5 million in fees from the damages award.\n\n 4\n Andrew Halldorson, another former Constellis employee and an ESOP\nparticipant, filed the initial complaint against Wilmington. Halldorson later amended his\ncomplaint to add Brundle as a named plaintiff. Both Halldorson and Brundle moved for\nclass certification, which the district court denied. Following a motion for summary\njudgment by Wilmington, the district court dismissed Halldorson because of a release he\nsigned barring his suit against Wilmington. Halldorson appealed both his dismissal and\nthe denial of class certification but later withdrew his appeal of the class certification\nissue. Brundle did not timely appeal the denial of class certification.\n\n 13\n\f On appeal, Wilmington challenges the court’s liability and damages\n\ndeterminations and its award of $1.5 million in non-statutory attorneys’ fees. Brundle\n\ncross-appeals, challenging as inadequate the same portion of the attorneys’ fees award.\n\n\n\n II.\n\n Wilmington initially and principally contends that the district court erred in\n\nconcluding that it violated ERISA. Following a bench trial, we review a district court’s\n\nfactual findings for clear error and its legal conclusions de novo. Nat’l Fed’n of the Blind\n\nv. Lamone, 813 F.3d 494, 502 (4th Cir. 2016).\n\n At the outset of both its principal brief and its oral argument, Wilmington\n\nemphasized that there is no claim in this case that it acted in bad faith. But of course, an\n\nESOP participant seeking recovery from its fiduciary need not prove that the fiduciary\n\nacted in bad faith. Rather, an ESOP fiduciary is liable to the plan participants if it\n\nbreached its fiduciary duties, i.e., failed to act “solely in the interest of the participants,”\n\nwith the care, skill, prudence, and diligence used by a “prudent man acting in a like\n\ncapacity.” 29 U.S.C. § 1104(a) (emphasis added). Thus our focus is not on\n\nWilmington’s motives (good or bad) but on whether it acted “solely in the interest” of the\n\nplan participants, id., and “engaged in a reasoned decisionmaking process, consistent\n\nwith that of a prudent man in like capacity,” DiFelice v. U.S. Airways, Inc., 497 F.3d 410,\n\n420 (4th Cir. 2007) (internal quotation marks omitted); accord Tatum, 761 F.3d at 356.\n\nAs the Fifth Circuit has put it, “a pure heart and an empty head are not enough.”\n\nDonovan v. Cunningham, 716 F.2d 1455, 1467 (5th Cir. 1983).\n\n 14\n\f A.\n\n The district court found that because Wilmington failed to prove by a\n\npreponderance of the evidence that the ESOP’s purchase of Constellis was for adequate\n\nconsideration — and no more than adequate consideration — the transaction failed to\n\nqualify for the § 1108(e) affirmative defense. 5 In challenging this holding, Wilmington\n\nheavily relies on the valuation of Constellis stock submitted by its advisor, SRR.\n\n Expert advice, like an advisor’s independent valuation, can of course serve as\n\nevidence of prudence in the discharge of an ESOP trustee’s duties under § 1108(e). See\n\nBussian v. RJR Nabisco, Inc., 223 F.3d 286, 300–01 (5th Cir. 2000). But such advice “is\n\nnot a magic wand that fiduciaries may simply wave over a transaction to ensure that their\n\nresponsibilities are fulfilled.” Cunningham, 716 F.2d at 1474. Rather, a plan trustee\n\nmust at least show that it (1) “investigate[d] the expert’s qualifications,” (2) “provide[d]\n\nthe expert with complete and accurate information,” and (3) “[made] certain that reliance\n\non the expert’s advice was reasonably justified under the circumstances.” Shay, 100 F.3d\n\nat 1489. Because ERISA demands a high level of scrutiny from fiduciaries, a trustee\n\nmust prove that it considered these factors “and any others relevant under the particular\n\n\n 5\n For this defense to apply, in addition to being for adequate consideration, (1) the\nsale or exchange must be of “qualifying employer securities,” (2) the trustee cannot\ncharge a commission, and (3) the plan must qualify as “an eligible individual account\nplan.” 29 U.S.C. § 1108(e).\n All parties agree that the transaction here was for “qualifying employer securities.”\nThey further agree that Wilmington did not charge a commission, and they do not dispute\nthe district court’s finding that Wilmington’s fees were reasonable. See Brundle I, 241 F.\nSupp. 3d at 617. The parties do contest, however, whether the ESOP qualifies as an\n“eligible plan.” The district court did not reach this issue, nor do we.\n\n 15\n\fcircumstances it faced at the time of the decision,” and took care to avoid any identified\n\nconflicts of interest. See Bruister, 823 F.3d at 263 (internal quotation marks omitted).\n\n The district court properly recognized that the above legal principles guided its\n\ninquiry. The court then issued extensive factual findings in support of its conclusion that\n\nWilmington had “not demonstrated that its reliance on SRR’s [valuation] report was\n\n‘reasonably justified’ in light of all the circumstances because [Wilmington] ha[d] not\n\nshown that it thoroughly probed the gaps and internal inconsistencies in that report.”\n\nBrundle I, 241 F. Supp. 3d at 634.\n\n The court found Wilmington’s decision-making process inadequate in four major\n\nrespects. Id. It explained that “[a]lthough these failings independently” might not be\n\ndispositive, cumulatively they demonstrated that “Wilmington failed to meet its duty”\n\nunder ERISA, id., which, of course, includes the obligation to act “solely in the interest”\n\nof plan participants, 29 U.S.C. § 1104(a). Wilmington challenges the district court’s\n\nexhaustive findings of fact and conclusions of law as to each of the four designated\n\nfailures.\n\n 1.\n\n First, Wilmington maintains the district court erred in finding fault with\n\nWilmington’s failure to investigate SRR’s omission from its report of another, much\n\nlower, valuation of Constellis stock. That valuation, termed the “McLean Report” by the\n\nparties, had been completed just months earlier by the McLean Group, an investment\n\nbank that had regularly provided annual share valuations for Constellis. Brundle I, 241 F.\n\nSupp. 3d at 619, 634–35.\n\n 16\n\f Wilmington’s trial witnesses contended that consideration of the McLean Report\n\n“would not have been helpful because it was prepared with a different purpose in mind\n\n— the valuation of a single share” for stock options, rather than the valuation of a\n\ncontrolling interest for sale. Id. at 634–35. But the district court, relying on the\n\nuncontradicted testimony of a “highly credible” neutral expert, found that the two reports\n\nused “essentially the same methodology” despite being prepared for different purposes.\n\nId. at 635. Using that same methodology, the 2013 McLean Report estimated the per\n\nshare value of Constellis stock as $1,838.11, while SRR estimated its median per share\n\nvalue as $4,235. Id. at 619.\n\n Yet the SRR Report, which guided Wilmington as it evaluated the ESOP\n\ntransaction, did not even mention the McLean Report. And, although trial testimony\n\nestablished that at least one Wilmington official knew of the McLean Report, no one\n\nfrom Wilmington ever asked about it or questioned the vast discrepancy between two\n\nvaluations of the same company performed mere months apart. Id. at 634–35. The\n\ndistrict court concluded that a prudent fiduciary in Wilmington’s position would have\n\ninquired as to SRR’s omission. This was particularly so given that Constellis officers\n\ntestified that the company’s business prospects had not dramatically changed in the\n\nperiod between the two reports, and the SRR Report had referenced a different\n\n“valuation” older than McLean’s. 6\n\n\n 6\n Specifically, the SRR Report noted that in 2012 — a year before the McLean\nReport’s publication — a private equity firm offered to buy Constellis for between $340\nand $350 million. But rather than explain that the private equity firm then lowered its\n(Continued)\n 17\n\f Relying on trial evidence, the district court concluded that even a cursory review\n\nof the McLean Report would have raised questions as to whether the share valuation in\n\nthe SRR Report was too optimistic. The court did not find that the McLean Report\n\nnecessarily offered a more accurate picture of Constellis’s true value, but simply that a\n\nreasonably prudent fiduciary would have asked more questions. The court found that the\n\nanswers to these questions were “precisely the kinds of information that Wilmington, as\n\ntrustee, should have sought and evaluated” when considering the valuation of Constellis\n\nstock. Id. at 636. We see no reason to conclude otherwise.\n\n 2.\n\n The second major fault identified by the district court concerned Wilmington’s\n\nfailure to adequately probe the reliability of financial projections prepared by Constellis\n\nmanagement and used by SRR. Id. at 636–38. The court found that “the record show[ed]\n\nthat there were several red flags indicating that these projections were inflated, which\n\nWilmington either ignored or downplayed.” Id. at 636. Wilmington offers both general\n\nand specific challenges to this finding.\n\n First, Wilmington argues that Constellis management’s financial projections were,\n\nin fact, reliable and so required no probing. In support of this view, Wilmington contends\n\nthat because the McLean Report also utilized management’s financial projections to\n\n\n\n\noffer to $275 million, see Brundle I, 241 F. Supp. 3d at 614–15, the report simply stated\nthat the deal fell through due to the buyer’s “inability to secure sufficient financing.”\n\n 18\n\farrive at its own valuation of Constellis — a valuation the court treated as relevant — the\n\ncourt should have found the projections that the SRR Report used were also reliable.\n\n But although both McLean and SRR relied on financial projections prepared by\n\nConstellis management, they did not rely on the same financial projections. Id. at 638.\n\nThe projections that Constellis provided to SRR forecasted revenue over a much longer\n\ntime period, id. at 637–38, making them less accurate and less reliable. Further,\n\nConstellis management specifically prepared this set of projections for the purposes of\n\nSRR’s valuation in connection with the ESOP sale. This created a risk that Constellis\n\nmanagement might inflate its projections in response to incentives unique to the ESOP\n\nsale. Id. at 636. In light of these distinctions, the district court’s differing assessments of\n\nthe two reports’ comparative reliability were not inherently contradictory.\n\n At a more granular level, Wilmington maintains that each of the red flags that the\n\ndistrict court identified in Constellis’s financial projections are “non-existent.”\n\nWilmington Opening Br. 33–34, 38–39. Wilmington asserts largely factual, and\n\nuniversally unpersuasive, arguments in support of this view.\n\n Wilmington challenges the district court’s conclusion that Wilmington should\n\nhave been more critical of Constellis management’s financial projections because\n\nmanagement had a financial incentive to inflate the purchase price. The court found that\n\nthis initial red flag should have alerted Wilmington to probe the SRR valuation of\n\nConstellis. The district court’s finding on this issue primarily rested on the prospect of\n\nmanagement receiving 5% of the purchase price in cash bonuses — a factual\n\ndetermination well supported by the record. See Brundle I, 241 F. Supp. 3d at 636.\n\n 19\n\f The district court also identified as a red flag an ongoing government investigation\n\ninto accounting and record-keeping errors by Constellis, which the court concluded\n\n“should have raised questions about the reliability of Constellis’[s] . . . projections.” Id.\n\nAgain, contrary to Wilmington’s suggestion, we see no basis for holding this finding\n\nclearly erroneous. A government investigation into errors of this nature surely creates a\n\nquestion as to the reliability of a company’s financial projections, which a reasonably\n\nprudent fiduciary representing the buyers of the company should probe further. Cf.\n\nKeach v. U.S. Tr. Co., 419 F.3d 626, 633–37 (7th Cir. 2005) (finding ESOP trustee met\n\nfiduciary duty when it “analyzed exhaustively [the company’s] financials, had conducted\n\nindependent valuation analyses and had challenged the financial forecasts made by [the\n\ncompany’s] management as too optimistic”).\n\n Still another red flag to which Wilmington, in the district court’s view, did “not\n\nadequately respond was the riskiness of Constellis’[s] contract concentration.” Brundle I,\n\n241 F. Supp. 3d at 637. The district court believed that this risk called for Wilmington to\n\napply further scrutiny to the company’s financial projections. The court found, and\n\nWilmington does not dispute, that at the time of the ESOP sale, about 70% of Constellis’s\n\nrevenue depended on just two government contracts. Id. at 637. Yet Wilmington\n\nadopted a valuation that assumed Constellis stock posed significantly less risk than the\n\nstock market as a whole. Again relying on the trial testimony of a “neutral” and “highly\n\ncredible” third party expert, the court explained its conclusion that Constellis’s industry\n\npeers — namely, government contractors — are certainly “no less risky than the market\n\nas a whole.” Brundle II, 258 F. Supp. 3d at 663. And again, the record offers ample\n\n 20\n\fsupport for this finding. See Brundle I, 241 F. Supp. 3d at 637; Brundle II, 258 F. Supp.\n\n3d at 662–63. 7\n\n Wilmington also maintains that the district court unfairly characterized\n\nConstellis’s “multiple sets of projections” as a red flag. Wilmington claims that the\n\ndistrict court ignored the fact that SRR advised Wilmington that the market and\n\nConstellis had changed throughout 2013. But the court adequately addressed this\n\nargument, see Brundle I, 241 F. Supp. 3d at 635–36, and we defer to its factual finding\n\nthat the changes in the market and Constellis’s business prospects throughout 2013 did\n\nnot justify multiple sets of projections.\n\n Last, Wilmington contends that we should reverse the district court due to its\n\ninitially erroneous understanding of the warranties Wilmington obtained to indemnify the\n\nESOP against the ongoing government investigation. At first, the court incorrectly found\n\n 7\n The court acknowledged that it originally had misunderstood the definition of the\nrisk factor, called “beta,” that SRR used in its report. SRR chose a beta of 0.7, indicating\nthat Constellis stock was less risky than the average stock (set at a beta of 1.0). The court\nhad understood beta to measure the risk of Constellis stock relative to its industry peers,\nbut beta actually measures the risk of a company’s stock — or in the case of a privately\nheld company like Constellis, the risk of a company’s publicly traded industry peers —\nrelative to the stock market as a whole. Brundle II, 258 F. Supp. 3d at 658.\n Upon consideration of Wilmington’s Rule 59 motion, the court stood by its\noriginal conclusion that Wilmington had inappropriately chosen a beta indicating that\nConstellis was less risky than other stocks. The court concluded that a neutral beta of 1.0\nwas more appropriate, noting that “[e]ven if government contracting business [in which\nConstellis participates] does not fluctuate in correlation with the market, that does not\nmean that government contracting is necessarily more stable.” Id. at 663. The court\nnoted that a Wilmington trial witness had acknowledged that “the government contracting\nindustry” is at times “less stable than the market as a whole.” Id. The court further relied\non the “most credible” neutral expert’s testimony that the public companies used by SRR\nto measure beta were “not a good match for Constellis.” Id. We see no clear error in\nthese findings.\n\n 21\n\fthat only Constellis had indemnified the ESOP, thus creating an illusory form of\n\nindemnification. But in denying Wilmington’s Rule 59 motion, the court candidly\n\naddressed that error and acknowledged that, in fact, both Constellis and the Sellers had\n\nindemnified the ESOP. Brundle II, 258 F. Supp. 3d at 656. Nonetheless, the court found\n\nthat its “corrected understanding [did] not alter [its] conclusions about . . . Wilmington’s\n\ninadequate investigation into the soundness of Constellis’[s] financial projections.” Id.\n\nThe court explained that, “[e]ven omitting its erroneous view of the Sellers’ . . .\n\nwarranties,” Wilmington failed to rebut the many red flags discussed above, each of\n\nwhich independently called for more robust due diligence by Wilmington. Id. at 656–57.\n\nFor the reasons we have explained above, we find no clear error in any of these findings\n\nand so reject this final argument from Wilmington as to Constellis management’s\n\nfinancial projections.\n\n 3.\n\n The district court found that Wilmington’s third major failure in ensuring that its\n\nreliance on the SRR valuation was reasonably justified occurred when it “did not\n\ninvestigate the appropriateness of applying a 10% control premium” to Constellis stock\n\nand “fail[ed] to discount the [valuation] for lack of control.” Brundle I, 241 F. Supp. 3d\n\nat 638.\n\n Purchasers will generally pay more for “rights associated with control of the\n\nenterprise.” Estate of Godley v. Comm’r, 286 F.3d 210, 214 (4th Cir. 2002). We have\n\ndefined “control” as “an interest which allows the shareholder to unilaterally direct\n\ncorporate action, select management, decide the amount of distribution, rearrange the\n\n 22\n\fcorporation’s capital structure, and decide whether to liquidate, merge, or sell assets.” Id.\n\nat 215 (internal quotation marks omitted).\n\n The district court recognized that the ESOP had “powers beyond those of an\n\nordinary shareholder.” Brundle I, 241 F. Supp. 3d at 627 n.23. But the court nonetheless\n\nfound that the “ESOP essentially had no power to control Constellis” as a result of the\n\ntransaction’s unique structure. Id. at 638–39. Accordingly, the court concluded that\n\nWilmington erred in failing to investigate the SRR valuation, which not only failed to\n\ndiscount the stock for lack of control, but even added a 10% control premium to the value\n\nof the Constellis stock. The record supports both findings.\n\n The Sellers retained the power to appoint a majority of the Constellis board, a key\n\nindicator of control. See id. at 626. Further, the ESOP governing plan document and the\n\nESOP trust agreement each required Wilmington to vote its shares as the Constellis\n\nboard (not the ESOP) directed. See id. at 626–27. Wilmington maintains that the ESOP\n\ncould independently exercise its voting powers because the plan documents included a\n\nclause nullifying any provision that violated ERISA. But Constellis’s general counsel\n\ntestified at trial that the ESOP could only contravene the plan documents and exercise its\n\nindependent voting authority by filing a lawsuit — the same limited relief available to a\n\nminority shareholder. The district court thus concluded that Wilmington breached its\n\nfiduciary obligation in failing to question SRR’s failure to discount for lack of control.\n\nSee id. at 639. Given the record evidence that the ESOP’s unique ownership structure\n\nwas intentionally designed to maintain the Sellers’ control over Constellis even after\n\nselling their shares, the district court’s conclusion hardly constitutes clear error.\n\n 23\n\f Wilmington next contends that even if the ESOP lacked control, a 10% control\n\npremium was justified by the fact that the ESOP owned 100% of Constellis shares and\n\nobtained “elements of control.” Id. at 647. Wilmington argues that SRR reasonably\n\napplied a “modest” 10% control premium given that market control premiums are often\n\nbetween 35–40%. But in light of the limited rights provided to the ESOP, we cannot\n\nconclude that the district court erred in finding that Wilmington should have done more\n\nto challenge the use of any control premium. The SRR Report “devoted just one sentence\n\nto articulating its decision,” yet Wilmington never asked SRR about its decision to apply\n\na control premium. Id. at 639. For an assumption that carried such weighty\n\nconsequences, we cannot say that the district court clearly erred in finding that a\n\nreasonably prudent fiduciary would have probed the issue further.\n\n 4.\n\n The final major fault that the district court identified in Wilmington’s reliance on\n\nthe SRR Report was Wilmington’s failure to probe why SRR consistently rounded the\n\nvaluation of Constellis stock upwards. This repeatedly increased the price the ESOP had\n\nto pay for the stock. The district court concluded that because an ESOP fiduciary should\n\nbe concerned with achieving the lowest possible price for the ESOP, Wilmington ought\n\nto have asked why SRR consistently engaged in the upward rounding to the ESOP’s\n\ndetriment. Id. at 639–40.\n\n Wilmington devotes only a short footnote in its opening brief to this issue and fails\n\nto address it at all in its reply brief. It thus appears to have forfeited an appellate\n\nchallenge to the court’s findings on this issue. See Wahi v. Charleston Area Med. Ctr.,\n\n 24\n\fInc., 562 F.3d 599, 607 (4th Cir. 2009) (finding argument raised only in a footnote in\n\nappellant’s opening brief forfeited on appeal). Perhaps this is because the district court’s\n\nfinding is self-evidently correct. And, as the district court noted, Brundle I, 241 F. Supp.\n\n3d at 640, this conclusion accords with those of other courts. For example, the Sixth\n\nCircuit described a similar rounding practice as “extremely disconcerting” and noted that\n\nthis conduct, although not dispositive, was illustrative of lackluster due diligence\n\ndisplayed throughout the transaction process. Chao, 285 F.3d at 433–34. So too here.\n\n B.\n\n Apart from Wilmington’s four major failures to scrutinize SRR’s report, the\n\ndistrict court also found that Wilmington’s conduct throughout the transaction provided\n\nfurther evidence that Wilmington failed to act as a prudent fiduciary solely on behalf of\n\nthe ESOP participants. Although the court found that Wilmington’s actions on behalf of\n\nthe ESOP did not amount to bad faith, it recognized that “ERISA demand[ed] more to\n\nexcuse a fiduciary from liability.” Brundle I, 241 F. Supp. 3d at 643.\n\n The district court found that Constellis’s principal motivation for creating the\n\nESOP was to further the Sellers’ interests, not the interests of the ESOP participant\n\nbuyers. Id. at 616. The sale of Constellis to the ESOP enabled the Sellers to cash out\n\ntheir company stock, which they had tried and failed to accomplish several times, and to\n\nreap substantial tax savings. Moreover, the ESOP’s unique structure enabled the Sellers\n\nto avoid the downside risk of holding equity, yet profit from any upside, while also\n\nretaining control over the company. The court found that Wilmington, in its role as the\n\n\n\n 25\n\fESOP’s fiduciary, simply ignored these motivations rather than investigating whether\n\nthey affected the ESOP’s legality under ERISA. Id. at 640–42.\n\n The district court additionally found that making the Sellers’ interests paramount\n\nshortened the transaction timeline and rushed Wilmington’s due diligence process and\n\nprice and terms negotiations. To maximize the after-tax benefits to the Sellers, the ESOP\n\nsale had to conclude before the end of 2013. Accordingly, Wilmington and its agents\n\ncompleted their due diligence, made pricing decisions, conducted negotiations, and\n\nlaunched a tender offer in less than two months. Id. at 621–25. Wilmington employees\n\nmet to discuss the transaction only three times and met with Constellis management just\n\nonce. Id. at 642. All meetings lasted less than 90 minutes and several of Wilmington’s\n\nteam members were absent from each. Id. And the district court found that Wilmington\n\nviolated its own policy by repeatedly taking less than 48 hours between receiving a\n\nvaluation report and meeting to discuss it. Id. at 621, 625. The court concluded that this\n\ntype of conduct fell well short of the diligence expected of a prudent fiduciary. Id. at\n\n643.\n\n Finally, the court noted that “Wilmington’s lack of engagement and willingness to\n\nnegotiate so favorably with CSG may have been motivated by its significant business\n\nrelationship with CSG.” Id. The district court found that Wilmington, CSG, and SRR\n\nmaintained extensive and lucrative business relationships and that SRR was willing to\n\ndiscuss its valuation strategies with CSG while negotiations were ongoing. Id. The\n\nrecord offers ample support for all of these findings.\n\n\n\n 26\n\f C.\n\n Wilmington also maintains that the district court erred in finding that the value of\n\nStock Appreciation Rights (SARs) issued in connection with the ESOP’s purchase of\n\nConstellis should have been deducted from Constellis’s equity value for purposes of\n\nSRR’s valuation. SARs are incentives that Constellis would have owed to management\n\nhad the company’s value reached a certain price by a particular date. Wilmington argues\n\nthe value of the SARs should not have been deducted from Constellis’s estimated value\n\nbecause they were inchoate at the time of the sale. The district court disagreed and found\n\nthat, because Constellis intended for the SARs to be issued, their value should have been\n\ndeducted from Constellis’s equity value. Id. at 648.\n\n Wilmington rehashes the same argument on appeal but fails to identify any\n\nevidence that demonstrates the district court clearly erred in this factual determination.\n\nBecause we discern no such evidence, we reject this claim.\n\n D.\n\n In support of its final attack on the district court’s liability findings, Wilmington\n\nrelies on the ESOP’s subsequent sale of Constellis stock to ACADEMI LLC.\n\n In early February 2014, less than two months after the ESOP transaction,\n\nACADEMI, a major competitor in the private security market, began talks with\n\nConstellis management to acquire the company. Id. at 628. Initially, ACADEMI offered\n\nto purchase Constellis at an enterprise value of $283.3 million, in a transaction that would\n\nresult in $10 million in cash going to the ESOP. Seeking a better offer on the ESOP’s\n\nbehalf, Wilmington entered into negotiations with Constellis, the Sellers, and\n\n 27\n\fACADEMI. Id. at 629. Wilmington’s efforts proved successful: the final transaction,\n\nwhich closed on July 25, 2014, effectuated a sale of all the Constellis stock to ACADEMI\n\nat an implied enterprise value of $288.3 million. Id. at 631. The final transaction paid\n\n$20 million in cash to the ESOP — double the initial $10 million offer — as a result of\n\nthe Sellers’ agreeing to write off $33 million of the ESOP’s debt. Id. at 629.\n\n Wilmington argues that the ACADEMI sale proves that the ESOP did not overpay\n\nfor Constellis seven months earlier. Relying on the first prong of DOL’s proposed\n\nadequate-consideration regulations, Wilmington maintains that the ESOP paid “fair\n\nmarket value” for the Constellis stock because ACADEMI’s purchase of Constellis stock\n\nimplied an enterprise value of $288.3 million, which was within SRR’s estimated range\n\nof $275 to $330 million. Wilmington contends this purchase price is of particular\n\nsignificance because in the intervening time Constellis assertedly suffered several\n\nbusiness setbacks that decreased its enterprise value. 8\n\n This argument is unpersuasive for several reasons. The proposed DOL regulations\n\nupon which Wilmington relies provide that a trustee can prove consideration is\n\n“adequate” if it reflects the stock’s “fair market value” and is “the product of a\n\ndetermination made by the fiduciary in good faith.” Proposed Regulation Relating to the\n\n\n 8\n The district court carefully considered and described these setbacks in detail. See\nBrundle I, 241 F. Supp. 3d at 627–28. Briefly, the State Department made a formal\ndemand for payment of $62.2 million as part of its audit of Constellis’s accounting and\nrecord-keeping practices; Constellis was forced to reduce projected revenue from a\ncontract in Iraq by more than $100 million and push the remaining revenue further into\nthe future; its projected revenue from a contract in Kuwait decreased by tens of millions\nof dollars; and it lost a $338 million contract in Germany it had expected to win. Id.\n\n 28\n\fDefinition of Adequate Consideration, 53 Fed. Reg. at 17,633. Of course, because the\n\nDOL never enacted the proposed regulations, they are not binding. And, as we have\n\nexplained, courts look to the conduct of the trustee and whether it met its fiduciary\n\nobligations, not to whether the trustee arrived at a “fair” value. But even if we were to\n\nadopt the DOL’s proposed regulations, a trustee must satisfy both parts of the test to\n\nbenefit from the adequate consideration exception. See id. Assuming arguendo that the\n\npurchase was for “fair market value,” we find no error in the district court’s findings that\n\nWilmington failed to prove that the share price was also “the product of a determination\n\nmade by the fiduciary in good faith.”\n\n Furthermore, even if proving the ESOP paid “fair market value” sufficed to meet\n\nthe requirements of § 1108(e), the facts of the ACADEMI sale do not prove that the\n\nESOP paid only “fair market value” here. In fact, the district court found that the\n\nopposite was true. The court found that because ACADEMI, a private security company\n\nlike Constellis, would benefit from synergies resulting from its purchase of Constellis, it\n\nwould have been willing to pay significantly more for Constellis than the ESOP. Thus,\n\nthat ACADEMI actually paid less for Constellis stock suggested a significantly lower fair\n\nmarket value for the stock at the time of the ESOP purchase. Of course, Wilmington’s\n\nexperts disagreed with this synergies analysis, but the district court found the testimony\n\nof other experts on this point more persuasive. Brundle I, 241 F. Supp. 3d at 640. The\n\nrecord provides no basis to reject this finding. See Hendricks v. Cent. Reserve Life Ins.\n\nCo., 39 F.3d 507, 513 (4th Cir. 1994) (“An appellate court should be especially reluctant\n\n\n\n 29\n\fto set aside a finding based on the trial court’s evaluation of conflicting expert\n\ntestimony.”).\n\n In sum, the district court found that the ACADEMI sale did not constitute a\n\nmeaningful comparator. Discounting the additional synergy value, the $33 million debt\n\nwrite-off by the Sellers, and an expected tax refund from the sale, the court found the\n\nACADEMI purchase suggested that Constellis’s fair market value was closer to $200\n\nmillion — almost $100 million less than the enterprise value implied by the ESOP\n\ntransaction. Thus, the court found, the ACADEMI sale could not support Wilmington’s\n\nargument that the ESOP paid no more than adequate consideration for Constellis.\n\nBrundle I, 241 F. Supp. 3d at 640. We see no clear error in this conclusion.\n\n Additionally, we note that, despite paying more for Constellis stock, the ESOP did\n\nnot obtain nearly the level of control that ACADEMI acquired. While the ESOP\n\nobtained only some elements of control, ACADEMI acquired absolute and uncontested\n\ncontrol. Had the district court applied the “standard” 35–40% control premium\n\nWilmington’s experts suggested was reasonable, Constellis’s fair market value would fall\n\nsomewhere between $145 million and $150 million, almost half the value of the stock\n\npurchased by the ESOP only months earlier.\n\n\n\n III.\n\n Having rejected all of Wilmington’s challenges to the district court’s findings as to\n\nits liability, we turn to the court’s damages award. The district court concluded that\n\nWilmington’s fiduciary failures inflated the price the ESOP paid for Constellis stock by\n\n 30\n\f$29,773,250. “We review factual findings relating to the calculation of damages for clear\n\nerror.” Simms v. United States, 839 F.3d 364, 368 (4th Cir. 2016).\n\n A.\n\n To calculate the loss to an ESOP and compensate it for a fiduciary’s ERISA\n\nviolation, a court typically subtracts the stock’s fair market value, as determined by the\n\ncourt, from the inflated price paid by the ESOP. See Bruister, 823 F.3d at 265 (collecting\n\ncases). The district court precisely followed this approach. The court used as a baseline\n\nthe comprehensive damages estimate provided by Brundle’s expert — the only expert to\n\noffer one. 9 The court then considered the flaws in this valuation raised by Wilmington\n\nand made “appropriate adjustments based on the evidence adduced at trial and the\n\nrelative credibility of the experts.” Brundle I, 241 F. Supp. 3d at 645.\n\n Brundle’s expert estimated Wilmington’s lack of due diligence had caused the\n\nESOP to overpay for the Constellis stock by almost $103,862,000. But the district court\n\ndid not accept this figure. Instead, it independently analyzed each of Wilmington’s\n\npurported failings, considered the relevant trial testimony, and then awarded $29,773,250\n\n— or less than a third of the expert’s estimation — as damages. Id. at 645–49. The\n\nfollowing chart summarizes the district court’s damages findings:\n\n Error Difference between fair market value and\n inflated price paid by ESOP (Damages)\n Reliance on Management’s $4,325,000\n Growth Projections\n Use of .07 Beta $2,936,000\n\n 9\n The Fifth Circuit held, in another ESOP case involving this same expert, that a\ntrial court “was entitled to credit” his valuation methodology. Bruister, 823 F.3d at 267.\n\n 31\n\f Inclusion of Control Premium $8,186,000\n Failure to Include Lack of $9,715,250\n Control Discount\n Stock Appreciation Rights $1,611,000\n Rounding $3,000,000\n Total Damages $29,773,250\n\n Wilmington did not provide the district court with an alternative damages\n\ncalculation or offer any evidence that the court could use to devise its own. At oral\n\nargument before us, Wilmington conceded as much. Accordingly, it has forfeited its\n\nchallenge to the methodology used by the district court when calculating the damages\n\naward. See Exxon Shipping Co. v. Baker, 554 U.S. 471, 487 n.6 (2008) (“[W]aiver and\n\nforfeiture rules . . . ensure that parties can determine when an issue is out of the case, and\n\nthat litigation remains, to the extent possible, an orderly progression.”).\n\n Moreover, Wilmington’s principal basis for urging reversal of the damages award\n\nconsists of a repetition of its challenge to the district court’s liability findings. Given our\n\naffirmance of all the district court’s liability findings — that Wilmington failed to\n\nadequately investigate and probe SRR as to the omission of the McLean Report, the use\n\nof Constellis management’s growth projections, the 0.7 beta, the 10% control premium,\n\nimproper rounding up, and SARs — that challenge fails.\n\n B.\n\n Wilmington additionally contends that the district court erred in declining to offset\n\nits damages calculation by the $20 million in cash that the ESOP received as a result of\n\nthe ACADEMI sale. According to Wilmington, “the district court’s failure to” do so\n\n“resulted in a clear windfall for the ESOP.” Wilmington Opening Br. at 53. As the\n\n 32\n\fdistrict court ably explained, see Brundle II, 258 F. Supp. 3d at 660–62, this claim is\n\nmeritless.\n\n ERISA expressly requires a fiduciary to “make good to [an ESOP] any losses”\n\nresulting from a given breach of duty. 29 U.S.C. § 1109(a); cf. Restatement (Second) of\n\nTrusts § 205 cmt. e (“If the trustee is authorized to purchase property for the trust, but in\n\nbreach of trust he pays more than he should pay, he is chargeable with the amount he paid\n\nin excess of its value.”). Thus, in cases involving overpayment for ESOP assets, courts\n\ngenerally compute restitution damages exactly as the district court did here: by deducting\n\nthe fair market value of the stock from the amount the ESOP actually paid.\n\n Wilmington insists that the ESOP’s subsequent and unrelated sale of the stock to\n\nACADEMI requires a different result. This misapprehends the nature of the breach. If\n\nWilmington had breached its duty by purchasing Constellis stock at all, then a damages\n\naward consisting of the purchase payments offset by any subsequent profits would indeed\n\nreturn the participants to the pre-purchase status quo.\n\n But Wilmington breached here by overpaying for the Constellis stock. Principles\n\nof restitution therefore entitle the ESOP and its participants to compensation for the loss\n\nfrom the overpayment. Any subsequent gains involving the stock, which the ESOP\n\nwould have obtained regardless of the overpayment, have no bearing on that loss. For\n\nthis very reason, courts have uniformly rejected analogous offsets to damage awards in\n\noverpayment cases. See, e.g., Bruister, 823 F.3d at 270–71 (rejecting offset to account\n\nfor unpaid or forgiven ESOP debt and noting that “[e]very court to consider this\n\nquestion” agreed); Henry v. U.S. Trust Co. of Cal., N.A., 569 F.3d 96, 98–100 (2d Cir.\n\n 33\n\f2009) (“Henry V”) (“If an investor pays $100 for 20 shares of stock and later sells those\n\nshares back to the original seller for $25, the result is not that the investor paid only $75\n\nfor the shares.”).\n\n Even so, Wilmington asserts that the events in this case resulted in “pure gain” to\n\nthe ESOP, justifying a deviation from this rule. It claims the ESOP “made $20 million\n\nfor the nominal cost of carrying $200 million in non-recourse debt for a few months,”\n\nbecause “[j]ust seven months” after the prohibited transaction, “the ESOP exchanged its\n\ndebt-burdened shares to ACADEMI for $20 million in cash.” Wilmington Opening Br.\n\nat 55–56. We disagree. As a preliminary matter, the burden imposed in additional debt\n\nfrom a $30 million overpayment is far from “nominal,” even for “just” seven months.\n\nSee Henry V, 569 F.3d at 99 n.4 (explaining “the obvious fact that the assumption of\n\nindebtedness has immediate legal and economic consequences even before the borrower\n\nbegins to repay the debt”).\n\n Moreover, if Wilmington seeks to portray the ACADEMI sale as an “exchange” in\n\nwhich the ESOP’s pre-sale debt had no effect on its post-sale assets, this is both illogical\n\nand untrue. Had the ESOP not initially overpaid for the stock by $30 million, it would\n\nhave shouldered tens of millions of dollars less in debt; in turn, it would presumably have\n\nbeen tens of millions of dollars better off after being compensated for the stock in the\n\nACADEMI sale. Put differently, although the ESOP benefited despite the breach, it\n\nwould have benefited at least as much — but ended in a far better position — without the\n\nbreach. In fact, had the ESOP initially paid a fair (lower) value for the Constellis stock\n\n\n\n 34\n\fand therefore carried less debt, it would have entered the ACADEMI negotiations in a\n\nstronger bargaining position and may have profited further still.\n\n Wilmington rejects this conclusion, stressing that the Sellers also agreed to write\n\noff more than $30 million of the ESOP’s debt, which it describes as an “effective[]\n\nreduc[tion]” of the 2013 purchase price. Wilmington Opening Br. at 56. But once again,\n\nthis independent act has no bearing on the ESOP’s loss.\n\n Wilmington unpersuasively contends that Henry III supports its argument. That\n\ncase addressed very different facts. There, the Second Circuit held that — where sellers\n\nfully and voluntarily repaid an ESOP after the IRS found overpayment, but before a court\n\nentered a damages judgment — a duplicative recovery for the same overpayment might\n\n“result in a windfall.” Henry III, 445 F.3d at 624. Wilmington does not even argue that\n\nthe Sellers’ write-off here was meant to remedy the ESOP’s overpayment. Nor could it:\n\nunlike the midstream repayment in Henry, the write-off here occurred more than a year\n\nprior to the initiation of any legal proceedings alleging Wilmington breached its fiduciary\n\nduties. As Wilmington concedes, the write-off was part of a negotiated agreement to\n\nclose the ACADEMI sale, a deal wholly unrelated to the issues raised here. Again, it is\n\nreasonable to assume that the ESOP would have negotiated equally favorable (if not more\n\nfavorable) terms had it paid a fair value in the first instance and thus entered the\n\nACADEMI discussions with substantially less debt.\n\n In sum, we find no error in the district court’s damages award.\n\n\n\n\n 35\n\f IV.\n\n Finally, we examine the district court’s award of attorneys’ fees. The court\n\nawarded Brundle’s counsel $1,819,631.11 in statutory fees and an additional $1.5 million\n\nin fees from the ESOP’s damages judgment. No party has presented a substantive\n\nchallenge regarding the award of attorneys’ fees under the fee shifting statute. 10 Brundle\n\nchallenges the $1.5 million in additional fees (payable from the damages awarded to the\n\nESOP) as too small; Wilmington and Constellis, as fiduciaries for the ESOP, challenge\n\nthe award as legally improper. We review that award for abuse of discretion, mindful\n\nthat our review “is sharply circumscribed, and a fee award must not be overturned unless\n\nit is clearly wrong.” Berry v. Schulman, 807 F.3d 600, 617 (4th Cir. 2015) (internal\n\nquotation marks omitted).\n\n A.\n\n We first consider Brundle’s claim that the district court abused its discretion by\n\nnot awarding his counsel, Bailey & Glass, LLP (B&G), a total of $9.9 million in fees\n\nunder the firm’s one-third contingent fee agreement with Brundle himself. The district\n\ncourt initially suggested that this arrangement was indeed controlling. See Brundle II,\n\n258 F. Supp. 3d at 671–72. But the court held its fee decision in abeyance to consider the\n\n\n 10\n Strangely, although Brundle does not challenge the statutory fee award, he does\nsummarily contend that he is entitled to $643,584.50 in expenses (the amount he\nrequested when seeking statutory fees in the district court). The district court denied his\nrequest for expenses, explaining that it was insufficiently documented. See Brundle II,\n258 F. Supp. 3d at 669. Before us, Brundle provides neither documentation nor\nargument. Accordingly, to the extent he even appeals the denial of expenses, we affirm\nthe district court.\n\n 36\n\fviews of plan participants and ultimately based its award on equity rather than contract.\n\nWe can hardly find an abuse of discretion given that Brundle has no right to have the\n\nESOP fund his own fee agreement with B&G.\n\n Brundle contends that 29 U.S.C. § 1132(a)(2) — which empowers ESOP\n\nparticipants and beneficiaries to bring suit on behalf of an ESOP — additionally\n\nauthorizes him to enter into a legal services contract that binds the ESOP. Brundle\n\nmusters no caselaw to support his interpretation of the statute, and for good reason.\n\nWhile § 1132(a)(2) provides Brundle the right to sue on behalf of the ESOP, neither it\n\nnor any other statute authorizes him to unilaterally bind the ESOP to a contract or fee\n\nagreement. For this very reason, the vast majority of suits on behalf of ERISA plans take\n\nthe form of class actions, in which counsel can seek fees only after a class has been\n\ncertified and class members have been given the opportunity to object or opt out. Though\n\nB&G has a valid contingent fee agreement with Brundle, see Venegas v. Mitchell, 495\n\nU.S. 82 (1990), it does not have a fee agreement with the ESOP.\n\n As a result, only equity provides any possible basis for a fee award in addition to\n\nthe statutory fees awarded.\n\n B.\n\n After the district court received the views of some plan participants, it issued a\n\nfinal judgment awarding B&G $1.5 million in “addition[]” to the $1.8 million in statutory\n\n\n\n\n 37\n\ffees — not as a contractual right, but as “a partial common fund award.” 11 Wilmington\n\nand Constellis assert that a trio of ERISA provisions precluded the court from awarding\n\nany common fund recovery. Unlike most challenges to fee awards, we review de novo\n\nquestions regarding a court’s legal authority. See, e.g., Country Vintner of N.C., LLC v. E\n\n& J. Gallo Winery, Inc., 718 F.3d 249, 254 (4th Cir. 2013).\n\n First, Wilmington and Constellis contend that any common fund award here would\n\nviolate ERISA’s “anti-alienation” and “exclusive benefit” provisions. See 29 U.S.C.\n\n§ 1056(d)(1) (providing that benefits under retirement plans cannot be “assigned or\n\nalienated”); id. § 1103(c)(1) (directing all “assets of a plan” to be “held for the exclusive\n\npurposes of providing benefits to participants in the plan and their beneficiaries and\n\ndefraying reasonable expenses of administering the plan”). But the district court properly\n\nrejected this argument, concluding that because the plan administrator did not yet possess\n\nthe damages award — in other words, the court still had jurisdiction over the funds and\n\nhad not distributed them to the ESOP — it could not be considered a plan asset. Brundle\n\nII, 258 F. Supp. 3d at 670. Of course, if the ESOP had received payment of the award,\n\nthose funds would have been subject to ERISA’s duties and protections. See Wilmington\n\n\n 11\n The district court made clear, and the parties do not dispute, that “[i]n granting\nboth fee-shifting and contingent fee awards, . . . the contingent fee award must be offset\nby the amount awarded under the fee-shifting provision.” Brundle II, 258 F. Supp. 3d at\n672 & n.19. On appeal, Brundle seeks a total of approximately $9.9 million in fees plus\nabout $650,000 in purported expenses, which (when offset by the $1.8 million in\nstatutory fees paid by Wilmington) would entitle B&G to a net of approximately $8.8\nmillion from the common fund. The district court instead awarded Brundle a net of only\n$1.5 million in fees from the common fund, which it noted was in “addition[]” to the $1.8\nmillion statutory fee-shifting award, for a total of $3.3 million in fees.\n\n 38\n\fShipping Co. v. New England Life Ins. Co., 496 F.3d 326, 333 (4th Cir. 2007). But where\n\na fund is still under the jurisdiction of the district court, the court may award fees from\n\nthat fund without running afoul of ERISA’s anti-alienation or exclusive benefit\n\nrequirements. See Kickham Hanley P.C. v. Kodak Ret. Income Plan, 558 F.3d 204, 213\n\n(2d Cir. 2009); Lynn v. CSX Transp., Inc., 84 F.3d 970, 975 (7th Cir. 1996).\n\n Next, Wilmington and Constellis argue that ERISA’s statutory fee-shifting\n\nprovision displaces the common fund doctrine. See 29 U.S.C. § 1132(g)(1) (authorizing\n\nprevailing plaintiffs to recover reasonable attorneys’ fees from defendants). They urge us\n\nto follow the Seventh Circuit in “limiting the common-fund approach to cases outside the\n\nscope of a fee-shifting statute.” Pierce v. Visteon Corp., 791 F.3d 782, 787 (7th Cir.\n\n2015); accord Haggart v. Woodley, 809 F.3d 1336, 1358–59 (Fed. Cir. 2016) (largely\n\nadopting Pierce rule). 12\n\n Several other circuits, however, have disagreed with this approach. See McKeage\n\nv. TMBC, LLC, 847 F.3d 992, 1003 (8th Cir. 2017) (“[T]he presence of a fee-shifting\n\nstatute precludes a common fund award only when that result is required by the statutory\n\nscheme involved.”); In re Bluetooth Headset Prods. Liab. Litig., 654 F.3d 935, 941 (9th\n\nCir. 2011) (“The award of attorneys’ fees in a class action settlement is often justified by\n\n[a] common fund or statutory fee-shifting[,] . . . and sometimes by both.”); Staton v.\n\n\n 12\n Pierce is in some tension with prior Seventh Circuit cases holding, in the\ncontext of settlements, that common fund recoveries are sometimes available even where\na case was brought under a statute with a fee-shifting provision. See Florin v.\nNationsbank of Georgia, N.A., 34 F.3d 560, 563–64 (7th Cir. 1994); Skelton v. Gen.\nMotors Corp., 860 F.2d 250, 252–57 (7th Cir. 1988).\n\n 39\n\fBoeing Co., 327 F.3d 938, 967–69 (9th Cir. 2003) (permitting common fund recovery\n\neven where statutory fees may be available); Cty. of Suffolk v. Long Island Lighting Co.,\n\n907 F.2d 1295, 1327 (2d Cir. 1990) (“In our view, fee-shifting statutes are generally not\n\nintended to circumscribe the operation of the equitable fund doctrine.”).\n\n To determine the proper course here, we consider the roots of the common fund\n\ndoctrine. The common fund principle derives from the equitable doctrines of quantum\n\nmeruit, Central Railroad & Banking Co. v. Pettus, 113 U.S. 116 (1885), and unjust\n\nenrichment, Trustees v. Greenough, 105 U.S. 527, 532 (1881). It allows a court to award\n\n“a reasonable attorney’s fee” to “a litigant or a lawyer who recovers a common fund for\n\nthe benefit of persons other than himself or his client . . . from the fund as a whole.”\n\nBoeing Co. v. Van Gemert, 444 U.S. 472, 478 (1980). The rationale for the doctrine is\n\nthat when one benefits from a lawsuit without contributing to its costs, he has been\n\nunjustly enriched at the successful litigant’s or lawyer’s expense. Mills v. Elec. Auto-Lite\n\nCo., 396 U.S. 375, 392 (1970). Courts remedy this inequity by shifting a proportional\n\nshare of reasonable attorneys’ fees onto these unjustly enriched beneficiaries.\n\n The Supreme Court has applied the “strong and uniform . . . background rule” of\n\nthe common fund doctrine “in a wide range of circumstances as part of [its] inherent\n\nauthority.” US Airways, Inc. v. McCutchen, 569 U.S. 88, 104 (2013) (collecting cases).\n\nWe agree with Brundle that it applies here. Scores of unnamed ESOP participants\n\nbenefited substantially from this lawsuit, while B&G bore the entirety of the costs and\n\nrisks. Equity thus demands that the enriched participants pay a proportional share of\n\nreasonable attorneys’ fees.\n\n 40\n\f To be sure, courts often, but not invariably, award common fund fees when a\n\nprocedural obstacle, such as the terms of a settlement, bars statutory fees that are\n\notherwise available. 13 But it does not follow that all statutory fee provisions necessarily\n\ndisplace the doctrine or render it superfluous. To the contrary: although both the\n\ncommon fund doctrine and fee-shifting statutes facilitate suit by plaintiffs who may\n\notherwise lack the means to hire counsel, they operate in distinct ways and serve distinct\n\npurposes.\n\n A common fund recovery places the plaintiffs’ cost of litigation on the recovering\n\nbeneficiaries of a lawsuit, whereas a fee-shifting statute places this burden on the losing\n\nparty. Cf. Venegas, 495 U.S. at 90 (differentiating between “what the losing defendant\n\nmust pay” to the plaintiff as attorneys’ fees under a fee-shifting statute and “what the\n\nprevailing plaintiff must pay his lawyer”). A fee-shifting statute thus creates an\n\nexception to the “American rule” that “the prevailing litigant is ordinarily not entitled to\n\ncollect a reasonable attorneys’ fee from the loser.” Alyeska Pipeline Serv. Co. v.\n\nWilderness Soc., 421 U.S. 240, 247 (1975). In contrast, the common fund doctrine —\n\nthough often similarly described as an exception — better accords with the American rule\n\n 13\n See, e.g., Skelton, 860 F.2d at 256 (affirming common fund award where “the\nfee-shifting provision [did] not . . . apply to a fee determination in a case settled in a\ncommon fund”); In re Fine Paper Antitrust Litig., 751 F.2d 562, 582–83 (3d Cir. 1984)\n(affirming common fund award where settlement released defendants from statutorily\navailable fees). But see Reyes v. Bakery & Confectionary Union & Indus. Int’l Pension\nFund, 281 F. Supp. 3d 833, 850 (N.D. Cal. 2017) (“[C]lass counsel may be awarded fees\nfrom the common fund in addition to any award under ERISA’s fee-shifting statute.”);\nHumphrey v. United Way of Tex. Gulf Coast, 802 F. Supp. 2d 847, 859 (S.D. Tex. 2011)\n(“The Court . . . has the power and discretion to award reasonable fees under both\n[ERISA] and the common fund doctrine.”).\n\n 41\n\fby holding the beneficiaries of a judgment or settlement responsible for compensating the\n\ncounsel who obtained the judgment or settlement for them. See Staton, 327 F.3d at 967.\n\n Furthermore, the purpose of the common fund doctrine, unlike a fee-shifting\n\nstatute, is to avoid unjust enrichment. Thus, although a statutory fee award against a\n\ndefendant generally may not include a contingency enhancement, see City of Burlington\n\nv. Dague, 505 U.S. 557, 565–67 (1992), courts routinely impose enhanced common fund\n\nawards to compensate counsel for litigation risk at the expense of beneficiaries who did\n\nnot shoulder this risk, see, e.g., In re Wash. Pub. Power Supply Sys. Secs. Litig., 19 F.3d\n\n1291, 1300 (9th Cir. 1994) (“There is nothing unfair about contingency enhancements in\n\ncommon fund cases . . . .”); Florin, 34 F.3d at 564–65 (similarly holding that “the policy\n\nconsiderations . . . that militate for forbidding risk multiples in statutory fee-shifting cases\n\nhave little force in common fund cases”).\n\n From these distinctions, it follows that a “reasonable” fee payable by a defendant\n\nto compensate the prevailing plaintiff’s counsel is not necessarily identical to a\n\n“reasonable” fee owed by a recovering beneficiary to plaintiff’s counsel, particularly\n\nwhere the contingency risk to plaintiff’s counsel is substantial. Cf. Venegas, 495 U.S. at\n\n85, 90 (affirming $406,000 contractual fee, paid by prevailing plaintiff to his counsel, as\n\nnot “unreasonable” even though “reasonable” statutory fee, paid by losing defendants,\n\nwas only $117,000); McKeage, 847 F.3d at 1004 (emphasizing “a distinction between the\n\namount a losing party may be required to pay” under fee-shifting provision in settlement\n\n“and the amount a class member should equitably be required to pay” under common\n\nfund doctrine).\n\n 42\n\f Consequently, we find unpersuasive the Seventh Circuit’s reasoning in Pierce. In\n\nlimiting the common fund doctrine to cases “outside the scope of a fee-shifting statute,”\n\nthe Pierce court reasoned first and foremost that “[c]ommon-law doctrines yield to\n\nstatutes.” 791 F.3d at 787. But the Supreme Court has instructed that courts must\n\n“presum[e] that Congress intended to retain the substance of the common law.”\n\nSamantar v. Yousuf, 560 U.S. 305, 320 n.13 (2010). We recognize, of course, that\n\nlegislative displacement of the common law does not require “the same sort of evidence\n\nof a clear and manifest congressional purpose demanded for preemption of state law.”\n\nAm. Elec. Power Co., Inc. v. Connecticut, 564 U.S. 410, 423 (2011) (alterations and\n\ninternal quotation marks omitted). Even so, a statute that shifts a reasonable fee onto a\n\nlosing defendant does not, without more, “speak[] directly” to congressional intent to\n\ndisplace recovery from a common fund. Id. at 424 (internal quotation marks omitted).\n\n The Pierce court additionally emphasized that “fee-shifting statutes are designed\n\nto ensure that the victims retain full compensation,” 791 F.3d at 787, a concern of\n\nindisputable importance. The common fund doctrine, however, balances this critical\n\ninterest against the concern of unjust enrichment, which ERISA’s fee-shifting provision\n\ndoes not purport to address.\n\n Finally, echoing the Pierce court, Wilmington and Constellis stress that B&G was\n\nentitled to, and received, a “reasonable” attorneys’ fee under statute. However, as we\n\nhave explained, what is “reasonable” as a fee from a losing defendant may well differ\n\nfrom what is “reasonable” as a fee from an individual directly benefited by counsel’s\n\nefforts. We particularly note that a “reasonable” fee under ERISA’s attorneys’ fee\n\n 43\n\fprovision (unlike a common fund award) precludes any compensation for contingency\n\nrisk. See Dague, 505 U.S. at 565–67. But, we have previously underscored, contingent\n\nfees serve an important function in providing under-resourced litigants access to counsel\n\nand the courts. In re Abrams & Abrams, P.A., 605 F.3d 238, 245–47 (4th Cir. 2010).\n\nConflating statutory attorneys’ fees with common fund recoveries would squarely\n\ncontravene this policy.\n\n We therefore agree with the Second, Eighth, and Ninth Circuits that a statutory\n\nfee-shifting provision (or an award of fees under such a provision) does not, as a matter\n\nof law, automatically preclude an award under the common fund doctrine. Accordingly,\n\nthe district court retained discretion to award supplemental attorneys’ fees from the\n\ncommon fund.\n\n C.\n\n Having established the district court’s authority to award supplemental fees, we\n\nturn to Brundle’s contention that the court abused its discretion in awarding its counsel\n\ntoo little from the common fund.\n\n Before setting the amount of its common fund award, the district court fashioned\n\nan ad hoc process analogous to class settlement procedures under Rule 23. Brundle II,\n\n258 F. Supp. 3d at 671–72. The court ordered Brundle’s counsel, B&G, to engage in a\n\ngood faith effort to notify the approximately 1,800 former ESOP participants of its\n\nproposed contingency fee award. After B&G did so, the court received 59 letters\n\nobjecting to a one-third contingency award. As a result of the objections, the court\n\ndecided to award B&G only $1.5 million as a supplemental fee payable from the\n\n 44\n\fdamages award, rather than granting counsel a full one-third ($9.9 million) of the ESOP’s\n\ntotal damages recovery.\n\n In reviewing the district court’s award, we note that Brundle had available a\n\nprocedural mechanism designed to carefully balance the interests of counsel, plaintiffs,\n\nand other similarly situated beneficiaries from the start — namely, class certification\n\npursuant to Rule 23. To be fair, Brundle and another plaintiff, Halldorson, did initially\n\nseek class certification, which the district court denied. But Brundle opted not to timely\n\nappeal this denial. And although Halldorson initially sought our review, he later\n\nwithdrew his appeal. See supra n.4.\n\n Had Brundle pursued class certification and prevailed, B&G could have secured\n\nattorneys’ fees from the class as a whole. Although a properly certified class might not\n\nhave agreed to the same one-third contingency fee that Brundle did, the district court\n\nmight well have awarded a fee significantly higher than the firm’s ultimate recovery\n\nhere. 14\n\n Brundle, represented by B&G, instead opted to forego Rule 23’s procedural\n\nstrictures — thus avoiding “the standards set for the protection of absent class members.”\n\nAmchem Prods., Inc. v. Windsor, 521 U.S. 591, 621 (1997). In light of this choice, the\n\ndistrict court’s decision to limit the common fund award was not inequitable, as\n\nillustrated by the objections from some of the ESOP’s participants. Nearly 60 of the\n\n 14\n See, e.g., Savani v. URS Prof’l Sols. LLC, 121 F. Supp. 3d 564, 574–75 (D.S.C.\n2015) (approving fee award of 39.57% from common fund award in ERISA settlement\nand collecting cases); In re Marsh ERISA Litig., 265 F.R.D. 128, 149 (S.D.N.Y. 2010)\n(approving fee award of 33.33% from common fund award).\n\n 45\n\f1,800 participants objected to the proposed common fund award, explaining that they had\n\nnever been informed of the case status, never agreed to B&G’s representation, and never\n\nauthorized the fund to pay a one-third fee. These process concerns would have been\n\navoided upfront had Brundle persisted in his pursuit of class certification. But because he\n\nand his counsel abandoned Rule 23’s class-protective procedures, equity cuts against\n\nawarding B&G the full one-third contingency fee.\n\n The district court properly weighed B&G’s efforts on behalf of the ESOP —\n\nincluding contingency risk — against the objections from ESOP participants to determine\n\na proper common fund award. Because we cannot say this balancing was clearly wrong,\n\nsee Berry, 807 F.3d at 617, we affirm the court’s fee award in full.\n\n\n\n V.\n\n For the foregoing reasons, the judgment of the district court is in all respects\n\n AFFIRMED.\n\n\n\n\n 46\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Tim P. BRUNDLE, ON BEHALF OF the CONSTELLIS EMPLOYEE STOCK OWNERSHIP PLAN, Plaintiff - Appellee, and Andrew Halldorson, on Behalf of the Constellis Employee Stock Ownership Plan, and on Behalf of a Class of All Other Persons Similarly Situated, Plaintiff, v. WILMINGTON TRUST, N.A., as Successor to Wilmington Trust Retirement and Institutional Services Company, Defendant - Appellant. American Society of Appraisers, Amicus Supporting Appellant, Secretary of the United States Department of Labor, Amicus Supporting Appellee. Tim P. Brundle, on Behalf of the Constellis Employee Stock Ownership Plan, Plaintiff - Appellant, and Andrew Halldorson, on Behalf of the Constellis Employee Stock Ownership Plan, and on Behalf of a Class of All Other Persons Similarly Situated, Plaintiff, v. Wilmington Trust, N.A., as Successor to Wilmington Trust Retirement and Institutional Services Company, Defendant - Appellee. Secretary of the United States Department of Labor, Amicus Supporting Appellant, American Society of Appraisers, Amicus Supporting Appellee. Tim P. Brundle, on Behalf of the Constellis Employee Stock Ownership Plan, Plaintiff - Appellee, and Andrew Halldorson, on Behalf of the Constellis Employee Stock Ownership Plan, and on Behalf of a Class of All Other Persons Similarly Situated, Plaintiff, Constellis Group, Inc., Party-In-Interest, v. Wilmington Trust, N.A., as Successor to Wilmington Trust Retirement and Institutional Services Company, Defendant - Appellant. American Society of Appraisers, Amicus Supporting Appellant, Secretary of the United States Department of Labor, Amicus Supporting Appellee. Tim P. Brundle, on Behalf of the Constellis Employee Stock Ownership Plan, Plaintiff - Appellee, and Andrew Halldorson, on Behalf of the Constellis Employee Stock Ownership Plan, and on Behalf of a Class of All Other Persons Similarly Situated, Plaintiff, v. Constellis Group, Inc., Party-In-Interest - Appellant, and Wilmington Trust, N.A., as Successor to Wilmington Trust Retirement and Institutional Services Company, Defendant. Tim P. Brundle, on Behalf of the Constellis Employee Stock Ownership Plan, Plaintiff - Appellant, and Andrew Halldorson, on Behalf of the Constellis Employee Stock Ownership Plan, and on Behalf of a Class of All Other Persons Similarly Situated, Plaintiff, v. Wilmington Trust, N.A., as Successor to Wilmington Trust Retirement and Institutional Services Company, Defendant - Appellee, Constellis Group, Inc., Party-In-Interest.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-03-21\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 17-1873\\n\\n\\nTIM P. BRUNDLE, on behalf of the Constellis Employee Stock Ownership Plan,\\n\\n Plaintiff - Appellee,\\n\\n and\\n\\nANDREW HALLDORSON, on behalf of the Constellis Employee Stock\\nOwnership Plan, and on behalf of a class of all other persons similarly situated,\\n\\n Plaintiff,\\n\\n v.\\n\\nWILMINGTON TRUST, N.A., as successor to Wilmington Trust Retirement and\\nInstitutional Services Company,\\n\\n Defendant - Appellant.\\n\\n-------------------------------------------\\n\\nAMERICAN SOCIETY OF APPRAISERS,\\n\\n Amicus Supporting Appellant,\\n\\nSECRETARY OF THE UNITED STATES DEPARTMENT OF LABOR,\\n\\n Amicus Supporting Appellee.\\n\\n\\n No. 17-2224\\n\\n\\nTIM P. BRUNDLE, on behalf of the Constellis Employee Stock Ownership Plan,\\n\\f Plaintiff - Appellant,\\n\\n and\\n\\nANDREW HALLDORSON, on behalf of the Constellis Employee Stock\\nOwnership Plan, and on behalf of a class of all other persons similarly situated,\\n\\n Plaintiff,\\n\\n v.\\n\\nWILMINGTON TRUST, N.A., as successor to Wilmington Trust Retirement and\\nInstitutional Services Company,\\n\\n Defendant - Appellee.\\n\\n-------------------------------------------\\n\\nSECRETARY OF THE UNITED STATES DEPARTMENT OF LABOR,\\n\\n Amicus Supporting Appellant,\\n\\nAMERICAN SOCIETY OF APPRAISERS,\\n\\n Amicus Supporting Appellee.\\n\\n\\n No. 17-2323\\n\\n\\nTIM P. BRUNDLE, on behalf of the Constellis Employee Stock Ownership Plan,\\n\\n Plaintiff - Appellee,\\n\\n and\\n\\nANDREW HALLDORSON, on behalf of the Constellis Employee Stock\\nOwnership Plan, and on behalf of a class of all other persons similarly situated,\\n\\n Plaintiff,\\n\\nCONSTELLIS GROUP, INC.,\\n\\n\\n 2\\n\\f Party-in-Interest,\\n\\n v.\\n\\nWILMINGTON TRUST, N.A., as successor to Wilmington Trust Retirement and\\nInstitutional Services Company,\\n\\n Defendant - Appellant.\\n\\n-------------------------------------------\\n\\nAMERICAN SOCIETY OF APPRAISERS,\\n\\n Amicus Supporting Appellant,\\n\\nSECRETARY OF THE UNITED STATES DEPARTMENT OF LABOR,\\n\\n Amicus Supporting Appellee.\\n\\n\\n No. 17-2324\\n\\n\\nTIM P. BRUNDLE, on behalf of the Constellis Employee Stock Ownership Plan,\\n\\n Plaintiff - Appellee,\\n\\n and\\n\\nANDREW HALLDORSON, on behalf of the Constellis Employee Stock\\nOwnership Plan, and on behalf of a class of all other persons similarly situated,\\n\\n Plaintiff,\\n\\n v.\\n\\nCONSTELLIS GROUP, INC.,\\n\\n Party-in-Interest - Appellant,\\n\\n and\\n\\n\\n\\n 3\\n\\fWILMINGTON TRUST, N.A., as successor to Wilmington Trust Retirement and\\nInstitutional Services Company,\\n\\n Defendant.\\n\\n\\n No. 18-1029\\n\\n\\nTIM P. BRUNDLE, on behalf of the Constellis Employee Stock Ownership Plan,\\n\\n Plaintiff - Appellant,\\n\\n and\\n\\nANDREW HALLDORSON, on behalf of the Constellis Employee Stock\\nOwnership Plan, and on behalf of a class of all other persons similarly situated,\\n\\n Plaintiff,\\n\\n v.\\n\\nWILMINGTON TRUST, N.A., as successor to Wilmington Trust Retirement and\\nInstitutional Services Company,\\n\\n Defendant - Appellee,\\n\\nCONSTELLIS GROUP, INC.,\\n\\n Party-in-Interest.\\n\\n\\nAppeals from the United States District Court for the Eastern District of Virginia, at\\nAlexandria. Leonie M. Brinkema, District Judge. (1:15-cv-01494-LMB-IDD)\\n\\n\\nArgued: December 11, 2018 Decided: March 21, 2019\\n\\n\\nBefore GREGORY, Chief Judge, and MOTZ and FLOYD, Circuit Judges.\\n\\n\\n\\n\\n 4\\n\\fAffirmed by published opinion. Judge Motz wrote the opinion, in which Chief Judge\\nGregory and Judge Floyd joined.\\n\\n\\nARGUED: Carter Glasgow Phillips, SIDLEY AUSTIN LLP, Washington, D.C., for\\nAppellant/Cross-Appellee Wilmington Trust, N.A. Gregory Y. Porter, BAILEY &\\nGLASSER LLP, Washington, D.C., for Appellee/Cross-Appellant. Robin Springberg\\nParry, UNITED STATES DEPARTMENT OF LABOR, Washington, D.C., for Amicus\\nSecretary of Labor. ON BRIEF: James P. McElligott, Jr., Summer L. Speight,\\nRichmond, Virginia, Stephen W. Robinson, MCGUIRE WOODS LLP, Tysons, Virginia;\\nJacqueline G. Cooper, Kurt A. Johnson, SIDLEY AUSTIN LLP, Washington, D.C., for\\nAppellant/Cross-Appellee Wilmington Trust, N.A. Edward Lee Isler, Micah E. Ticatch,\\nISLER DARE, P.C., Vienna, Virginia, for Appellant Constellis Group, Inc. Tillman J.\\nBreckenridge, Ryan T. Jenny, BAILEY & GLASSER LLP, Washington, D.C., for\\nAppellee/Cross-Appellant. J. Christian Nemeth, Chicago, Illinois, Sophia A. Luby,\\nWashington, D.C.; Eliot T. Burriss, Erin Turley, Calli Turner, MCDERMOTT WILL &\\nEMERY LLP, Dallas, Texas, for Amicus American Society of Appraisers. Kate S.\\nO’Scannlain, Solicitor of Labor, G. William Scott, Associate Solicitor for Plan Benefits\\nSecurity, Thomas Tso, Counsel for Appellate and Special Litigation, UNITED STATES\\nDEPARTMENT OF LABOR, Washington, D.C., for Amicus Secretary of Labor.\\n\\n\\n\\n\\n 5\\n\\fDIANA GRIBBON MOTZ, Circuit Judge:\\n\\n After owners of a closely held corporation sold the company to its Employee\\n\\nStock Ownership Plan (“ESOP”), a participant in the ESOP brought this action. The\\n\\nparticipant contended that the trustee chosen for the ESOP by the corporation breached\\n\\nits fiduciary duties to the ESOP and overpaid for the stock — improperly enriching the\\n\\ncorporation’s owners at the expense of its employees.\\n\\n Following a multi-day bench trial, the district court issued detailed findings of fact\\n\\nconcluding that the trustee had indeed breached its fiduciary duties, causing the ESOP to\\n\\noverpay for the corporation’s stock by $29,773,250. The court entered judgment for the\\n\\nESOP in that amount and awarded attorneys’ fees to the participant’s counsel. These\\n\\nappeals and cross-appeals followed. As explained within, we affirm the careful findings\\n\\nof the district court.\\n\\n\\n\\n I.\\n\\n To facilitate understanding of the issues here, we begin with the governing legal\\n\\nprinciples and background facts that gave rise to this suit. The parties do not challenge\\n\\nthese principles or facts. All are more fully set forth in the comprehensive district court\\n\\nopinions, upon which we rely throughout. See Brundle v. Wilmington Tr. N.A., 241\\n\\nF. Supp. 3d 610 (E.D. Va. 2017) (“Brundle I”); Brundle v. Wilmington Tr. N.A., 258\\n\\nF. Supp. 3d 647 (E.D. Va. 2017) (“Brundle II”).\\n\\n\\n\\n\\n 6\\n\\f A.\\n\\n The Employee Retirement Income Security Act of 1974 (ERISA) allows an\\n\\nemployer to create an ESOP, an employee pension plan that invests primarily in the\\n\\nemployer’s stock. The employer makes contributions to the plan that are used to\\n\\npurchase stock in the employer’s company. Because — and only because — an ESOP\\n\\ncontribution qualifies as employee compensation, an employer can deduct the total value\\n\\nof its ESOP contribution from its income tax liability as an ordinary business expense.\\n\\n26 U.S.C. § 404; 26 C.F.R. § 1.404(a)–1(b). 1 In this way, an ESOP benefits both\\n\\nemployees and employers by providing deferred compensation to the former and a\\n\\nvaluable tax deduction to the latter.\\n\\n ERISA imposes duties and obligations on all pension plan fiduciaries, including\\n\\nthose of ESOPs. These duties “ensure that employees will not be left empty-handed once\\n\\nemployers have guaranteed them certain benefits.” Lockheed Corp. v. Spink, 517 U.S.\\n\\n882, 887 (1996). One such provision prohibits the fiduciary of any ERISA plan from\\n\\ncausing a “sale or exchange . . . of any property between the plan and a party in interest.”\\n\\n29 U.S.C. § 1106(a)(1)(A). Absent a statutory exception, this provision would ban\\n\\nESOPs because their creation necessarily requires the ESOP to purchase stock from its\\n\\nsponsoring employer, which is a party in interest. Congress, however, has carved out an\\n\\n\\n\\n 1\\n An employer’s contributions to an ESOP thus constitute a valuable form of\\ndeferred compensation, rather than a gift to employees. See, e.g., Reich v. Hall Holding\\nCo., 990 F. Supp. 955, 961 (N.D. Ohio 1998), aff’d sub nom. Chao v. Hall Holding Co.,\\n285 F.3d 415 (6th Cir. 2002). Wilmington wisely does not suggest otherwise.\\n\\n 7\\n\\fexception to this prohibition to permit the creation of an ESOP if the stock purchase\\n\\nmeets certain conditions. See 29 U.S.C. § 1108(e).\\n\\n To protect employees from losing the value of their earned retirement savings, the\\n\\nexception to the ERISA ban on party-in-interest transactions requires that an ESOP pay\\n\\nno more than “adequate consideration” for the employer’s stock. Id. § 1108(e)(1). If an\\n\\nemployer’s “stock was not worth what the ESOP paid for it,” then the ESOP paid more\\n\\nthan adequate consideration and “the ESOP and its participants suffered a loss under\\n\\nERISA.” See Reich, 990 F. Supp. at 961.\\n\\n ERISA does not define what constitutes “adequate consideration” under the\\n\\n§ 1108(e) exception; the Department of Labor (DOL) has proposed, but never enacted,\\n\\nregulations doing so. 2 Although courts look to these regulations for guidance, the focus\\n\\nof the adequate-consideration inquiry rests on the conduct of a fiduciary, as judged by\\n\\nERISA’s “prudent man” standard of care. See Perez v. Bruister, 823 F.3d 250, 263 (5th\\n\\nCir. 2016); Henry III, 445 F.3d at 619; Chao, 285 F.3d at 437; Howard v. Shay, 100 F.3d\\n\\n1484, 1489 (9th Cir. 1996).\\n\\n Under this standard, “ESOP fiduciaries are subject to the duty of prudence just as\\n\\nother ERISA fiduciaries are.” Fifth Third Bancorp v. Dudenhoeffer, 134 S. Ct. 2459,\\n\\n 2\\n These proposed regulations, to which courts look for guidance, provide that\\n“adequate” consideration must (1) reflect the stock’s “fair market value,” and (2) be “the\\nproduct of a determination made by the fiduciary in good faith.” Proposed Regulation\\nRelating to the Definition of Adequate Consideration, 53 Fed. Reg. 17,632, 17,633\\n(proposed May 17, 1988) (to be codified at 29 C.F.R. pt. 2510). “[I]n practice, the ‘fair\\nmarket value’ inquiry overlaps considerably with the ‘good faith’ inquiry.’” Henry v.\\nChamplain Enters., Inc., 445 F.3d 610, 618–19 (2d Cir. 2006) (Sotomayor, J.) (“Henry\\nIII”) (collecting cases).\\n\\n 8\\n\\f2467 (2014). Thus an ESOP fiduciary, like any other ERISA fiduciary, must “discharge\\n\\nhis duties . . . with the care, skill, prudence, and diligence under the circumstances then\\n\\nprevailing that a prudent man acting in a like capacity and familiar with such matters\\n\\nwould use in the conduct of an enterprise of a like character and with like aims.” 29\\n\\nU.S.C. § 1104(a)(1)(B).\\n\\n Although these fiduciary duties “draw much of their content from the common law\\n\\nof trusts . . . ERISA’s standards and procedural protections partly reflect a congressional\\n\\ndetermination that the common law of trusts did not offer completely satisfactory\\n\\nprotection.” Tatum v. RJR Pension Inv. Comm., 761 F.3d 346, 357 (4th Cir. 2014)\\n\\n(internal quotation marks omitted). Courts apply the “prudent man rule . . . bearing in\\n\\nmind the special nature and purpose of employee benefit plans.” Id. (internal quotation\\n\\nmarks and alterations omitted). For this reason, “[t]he fiduciary obligations of the\\n\\ntrustees to the participants and beneficiaries [of an ERISA] plan are . . . the highest\\n\\nknown to the law.” Id. at 356 (alterations in original) (quoting Donovan v. Bierwith, 680\\n\\nF.2d 263, 272 n.8 (2d Cir. 1982)).\\n\\n Because an ESOP fiduciary that raises an affirmative defense under the § 1108(e)\\n\\nexception seeks to avoid ERISA liability for an otherwise prohibited transaction, the\\n\\nfiduciary bears the burden of proving by a preponderance of the evidence that the sale\\n\\nwas for adequate consideration. See Elmore v. Cone Mills Corp., 23 F.3d 855, 864 (4th\\n\\nCir. 1994) (en banc). “This burden is a heavy one.” Shay, 100 F.3d at 1488.\\n\\n B.\\n\\n With these principles in mind, we turn to the facts of this case.\\n\\n 9\\n\\f Since its inception, Constellis Group, Inc., the closely held parent company of a\\n\\ngroup of private security subsidiaries, has offered some form of deferred compensation to\\n\\nits employees, who are primarily retired members of the U.S. Armed Forces. Brundle I,\\n\\n241 F. Supp. 3d at 614. After initially offering a stock option program, Constellis\\n\\nreplaced that program with a profit-sharing plan in 2010. Id. In mid-2013, looking for an\\n\\n“exit strategy” after having twice tried and failed to effectuate a sale of the company, the\\n\\nowners of Constellis (hereinafter “the Sellers”) 3 began exploring the possibility of\\n\\ncreating an ESOP to purchase Constellis. Id. at 615.\\n\\n To that end, Constellis retained CSG International, an investment banking firm.\\n\\nCSG reported that sale of Constellis to an ESOP would not only enable the Sellers to\\n\\nliquidate their shares but would save them 23.8% in federal capital gains taxes. Id.\\n\\nAlthough noting that an ESOP would also benefit employees, CSG emphasized that\\n\\nselling Constellis to an ESOP provided the best option to optimize the Sellers’ after-tax\\n\\ncash return. See, e.g., id. at 616 (noting that CSG reported to the Sellers that, having\\n\\n“looked at every possible scenario,” it had not seen “any possible alternative that\\n\\nproduce[d] more after tax cash” than the proposed ESOP (internal quotation marks\\n\\nomitted)).\\n\\n CSG suggested that Constellis create what several trial witnesses characterized as\\n\\na “unique” ESOP structure to effectuate the sale. This unique structure would permit the\\n\\nSellers to retain de facto control of Constellis, even after the ESOP purchased all of the\\n\\n 3\\n Four individuals owned 77% of Constellis stock at the time of the sale at issue\\nhere. See Brundle I, 241 F. Supp. 3d at 615.\\n\\n 10\\n\\fcompany stock. Rather than sell 100% of their ownership interest to the ESOP, as is the\\n\\nusual practice, the Sellers would sell 90% of their shares to the ESOP and then exchange\\n\\nthe remaining 10% for “equity-like” warrants. These warrants would entitle the Sellers to\\n\\nbuy back equity in Constellis from the ESOP at a designated price and guarantee the\\n\\nSellers a majority on the board of directors. Id. at 626.\\n\\n To fund the ESOP’s purchase, Constellis would contribute 24% of the purchase\\n\\nprice and the ESOP would borrow the remainder from Constellis and the Sellers\\n\\nthemselves. Id. at 625. In late September 2013, Constellis decided to move forward with\\n\\nCSG’s proposal to create this unique ESOP. Id. To maximize the Sellers’ tax savings,\\n\\nConstellis had to complete the sale by the end of the calendar year. Id. at 622.\\n\\n On the recommendation of CSG, Constellis engaged Wilmington Trust, N.A., to\\n\\nserve as trustee for the ESOP. Id. at 616. In its role as trustee, Wilmington hired Stout\\n\\nRisius Ross (SRR) to be the financial advisor on the ESOP’s purchase of Constellis. Id.\\n\\nat 617. CSG, Wilmington, and SRR maintained significant long-term business\\n\\nrelationships, having worked together on more than twenty ESOP deals. Id. at 643\\n\\n(calling “the ESOP world . . . a very incestuous community”) (internal quotation marks\\n\\nomitted); id. at 617.\\n\\n On November 12, 2013, SRR submitted a draft valuation of Constellis stock to\\n\\nWilmington (the “SRR Report”). The SRR Report concluded that the fair market value\\n\\nfor a single share of Constellis stock lay between $3,865 and $4,600 — resulting in a\\n\\nrounded median price per share of $4,235. This placed the company’s worth, or its\\n\\n“enterprise value,” within a range of $275 to $330 million. Id. at 620–21. On November\\n\\n 11\\n\\f14, Wilmington met with analysts from SRR to discuss its report and valuation. At the\\n\\nmeeting’s conclusion, Wilmington set out to negotiate the ESOP’s purchase of Constellis\\n\\nwith authorization to offer a share price of $3,900 to $4,235. Id. at 622.\\n\\n The next day, Wilmington submitted an opening bid on behalf of the ESOP for\\n\\n$3,900 per share. Id. at 642. CSG, on behalf of Constellis, countered with $4,350 and\\n\\nsuggested to Wilmington that the ESOP and Constellis agree on a price first and then\\n\\nadjust the terms of the agreement at a later date. Wilmington agreed and raised its own\\n\\nbid to $4,100. CSG then countered with $4,250. By the end of the day, Wilmington and\\n\\nCSG had settled on a share price of $4,235 — the very top of Wilmington’s authorized\\n\\nnegotiation range. The negotiations lasted little more than five hours.\\n\\n The ESOP issued a tender offer for the shares on November 18 with a closing date\\n\\nof December 20. The parties finalized the term sheet on November 22. Between the\\n\\nconclusion of negotiations and the closing date for the transaction, SRR revised its\\n\\nvaluation of the draft enterprise range downward from $275–$330 million to $275–$325\\n\\nmillion, but the per share purchase price remained $4,235. On December 19, after\\n\\nmeeting with SRR for half an hour to discuss SRR’s valuation, Wilmington approved the\\n\\npurchase. Id. at 624. On December 20, the ESOP’s purchase of Constellis closed for a\\n\\nper share price of $4,235. Id. at 625.\\n\\n Subsequently, Tim P. Brundle, a former Constellis employee and ESOP\\n\\nparticipant, brought this action contending that Wilmington caused the ESOP to enter\\n\\n\\n\\n\\n 12\\n\\finto a transaction prohibited under ERISA § 1106. 4 Brundle alleged that the $4,235 per\\n\\nshare paid by the ESOP for Constellis was too high and resulted in the ESOP overpaying\\n\\nthe Sellers for the stock. The district court initially held that the 2013 purchase of\\n\\nConstellis by the ESOP constituted a prohibited transaction under § 1106(a)(1). Brundle\\n\\nv. Wilmington Tr., N.A., 2016 WL 6542718, at *12 (E.D. Va. Nov. 3, 2016). Wilmington\\n\\nconceded as much before the district court but raised the adequate-consideration\\n\\naffirmative defense available under § 1108(e)(1). Id.\\n\\n Following a bench trial, the district court issued meticulous factual findings and\\n\\nconcluded on the basis of those findings that Wilmington had not established the\\n\\n§ 1108(e) affirmative defense. Rather, the court found that Wilmington had violated its\\n\\nfiduciary duty to the ESOP. The district court concluded that Wilmington’s fiduciary\\n\\nfailures resulted in the ESOP overpaying for the Constellis stock by $29,773,250, and so\\n\\nawarded that amount to the ESOP as damages. Brundle I, 241 F. Supp. 3d at 613.\\n\\n Brundle then moved for attorneys’ fees. The court first ordered Wilmington to\\n\\npay attorneys’ fees pursuant to ERISA’s fee-shifting provision, 29 U.S.C. § 1132(g)(1),\\n\\nin the amount of $1,819,631.11. Brundle II, 258 F. Supp. 3d at 663–69. It subsequently\\n\\nawarded an additional $1.5 million in fees from the damages award.\\n\\n 4\\n Andrew Halldorson, another former Constellis employee and an ESOP\\nparticipant, filed the initial complaint against Wilmington. Halldorson later amended his\\ncomplaint to add Brundle as a named plaintiff. Both Halldorson and Brundle moved for\\nclass certification, which the district court denied. Following a motion for summary\\njudgment by Wilmington, the district court dismissed Halldorson because of a release he\\nsigned barring his suit against Wilmington. Halldorson appealed both his dismissal and\\nthe denial of class certification but later withdrew his appeal of the class certification\\nissue. Brundle did not timely appeal the denial of class certification.\\n\\n 13\\n\\f On appeal, Wilmington challenges the court’s liability and damages\\n\\ndeterminations and its award of $1.5 million in non-statutory attorneys’ fees. Brundle\\n\\ncross-appeals, challenging as inadequate the same portion of the attorneys’ fees award.\\n\\n\\n\\n II.\\n\\n Wilmington initially and principally contends that the district court erred in\\n\\nconcluding that it violated ERISA. Following a bench trial, we review a district court’s\\n\\nfactual findings for clear error and its legal conclusions de novo. Nat’l Fed’n of the Blind\\n\\nv. Lamone, 813 F.3d 494, 502 (4th Cir. 2016).\\n\\n At the outset of both its principal brief and its oral argument, Wilmington\\n\\nemphasized that there is no claim in this case that it acted in bad faith. But of course, an\\n\\nESOP participant seeking recovery from its fiduciary need not prove that the fiduciary\\n\\nacted in bad faith. Rather, an ESOP fiduciary is liable to the plan participants if it\\n\\nbreached its fiduciary duties, i.e., failed to act “solely in the interest of the participants,”\\n\\nwith the care, skill, prudence, and diligence used by a “prudent man acting in a like\\n\\ncapacity.” 29 U.S.C. § 1104(a) (emphasis added). Thus our focus is not on\\n\\nWilmington’s motives (good or bad) but on whether it acted “solely in the interest” of the\\n\\nplan participants, id., and “engaged in a reasoned decisionmaking process, consistent\\n\\nwith that of a prudent man in like capacity,” DiFelice v. U.S. Airways, Inc., 497 F.3d 410,\\n\\n420 (4th Cir. 2007) (internal quotation marks omitted); accord Tatum, 761 F.3d at 356.\\n\\nAs the Fifth Circuit has put it, “a pure heart and an empty head are not enough.”\\n\\nDonovan v. Cunningham, 716 F.2d 1455, 1467 (5th Cir. 1983).\\n\\n 14\\n\\f A.\\n\\n The district court found that because Wilmington failed to prove by a\\n\\npreponderance of the evidence that the ESOP’s purchase of Constellis was for adequate\\n\\nconsideration — and no more than adequate consideration — the transaction failed to\\n\\nqualify for the § 1108(e) affirmative defense. 5 In challenging this holding, Wilmington\\n\\nheavily relies on the valuation of Constellis stock submitted by its advisor, SRR.\\n\\n Expert advice, like an advisor’s independent valuation, can of course serve as\\n\\nevidence of prudence in the discharge of an ESOP trustee’s duties under § 1108(e). See\\n\\nBussian v. RJR Nabisco, Inc., 223 F.3d 286, 300–01 (5th Cir. 2000). But such advice “is\\n\\nnot a magic wand that fiduciaries may simply wave over a transaction to ensure that their\\n\\nresponsibilities are fulfilled.” Cunningham, 716 F.2d at 1474. Rather, a plan trustee\\n\\nmust at least show that it (1) “investigate[d] the expert’s qualifications,” (2) “provide[d]\\n\\nthe expert with complete and accurate information,” and (3) “[made] certain that reliance\\n\\non the expert’s advice was reasonably justified under the circumstances.” Shay, 100 F.3d\\n\\nat 1489. Because ERISA demands a high level of scrutiny from fiduciaries, a trustee\\n\\nmust prove that it considered these factors “and any others relevant under the particular\\n\\n\\n 5\\n For this defense to apply, in addition to being for adequate consideration, (1) the\\nsale or exchange must be of “qualifying employer securities,” (2) the trustee cannot\\ncharge a commission, and (3) the plan must qualify as “an eligible individual account\\nplan.” 29 U.S.C. § 1108(e).\\n All parties agree that the transaction here was for “qualifying employer securities.”\\nThey further agree that Wilmington did not charge a commission, and they do not dispute\\nthe district court’s finding that Wilmington’s fees were reasonable. See Brundle I, 241 F.\\nSupp. 3d at 617. The parties do contest, however, whether the ESOP qualifies as an\\n“eligible plan.” The district court did not reach this issue, nor do we.\\n\\n 15\\n\\fcircumstances it faced at the time of the decision,” and took care to avoid any identified\\n\\nconflicts of interest. See Bruister, 823 F.3d at 263 (internal quotation marks omitted).\\n\\n The district court properly recognized that the above legal principles guided its\\n\\ninquiry. The court then issued extensive factual findings in support of its conclusion that\\n\\nWilmington had “not demonstrated that its reliance on SRR’s [valuation] report was\\n\\n‘reasonably justified’ in light of all the circumstances because [Wilmington] ha[d] not\\n\\nshown that it thoroughly probed the gaps and internal inconsistencies in that report.”\\n\\nBrundle I, 241 F. Supp. 3d at 634.\\n\\n The court found Wilmington’s decision-making process inadequate in four major\\n\\nrespects. Id. It explained that “[a]lthough these failings independently” might not be\\n\\ndispositive, cumulatively they demonstrated that “Wilmington failed to meet its duty”\\n\\nunder ERISA, id., which, of course, includes the obligation to act “solely in the interest”\\n\\nof plan participants, 29 U.S.C. § 1104(a). Wilmington challenges the district court’s\\n\\nexhaustive findings of fact and conclusions of law as to each of the four designated\\n\\nfailures.\\n\\n 1.\\n\\n First, Wilmington maintains the district court erred in finding fault with\\n\\nWilmington’s failure to investigate SRR’s omission from its report of another, much\\n\\nlower, valuation of Constellis stock. That valuation, termed the “McLean Report” by the\\n\\nparties, had been completed just months earlier by the McLean Group, an investment\\n\\nbank that had regularly provided annual share valuations for Constellis. Brundle I, 241 F.\\n\\nSupp. 3d at 619, 634–35.\\n\\n 16\\n\\f Wilmington’s trial witnesses contended that consideration of the McLean Report\\n\\n“would not have been helpful because it was prepared with a different purpose in mind\\n\\n— the valuation of a single share” for stock options, rather than the valuation of a\\n\\ncontrolling interest for sale. Id. at 634–35. But the district court, relying on the\\n\\nuncontradicted testimony of a “highly credible” neutral expert, found that the two reports\\n\\nused “essentially the same methodology” despite being prepared for different purposes.\\n\\nId. at 635. Using that same methodology, the 2013 McLean Report estimated the per\\n\\nshare value of Constellis stock as $1,838.11, while SRR estimated its median per share\\n\\nvalue as $4,235. Id. at 619.\\n\\n Yet the SRR Report, which guided Wilmington as it evaluated the ESOP\\n\\ntransaction, did not even mention the McLean Report. And, although trial testimony\\n\\nestablished that at least one Wilmington official knew of the McLean Report, no one\\n\\nfrom Wilmington ever asked about it or questioned the vast discrepancy between two\\n\\nvaluations of the same company performed mere months apart. Id. at 634–35. The\\n\\ndistrict court concluded that a prudent fiduciary in Wilmington’s position would have\\n\\ninquired as to SRR’s omission. This was particularly so given that Constellis officers\\n\\ntestified that the company’s business prospects had not dramatically changed in the\\n\\nperiod between the two reports, and the SRR Report had referenced a different\\n\\n“valuation” older than McLean’s. 6\\n\\n\\n 6\\n Specifically, the SRR Report noted that in 2012 — a year before the McLean\\nReport’s publication — a private equity firm offered to buy Constellis for between $340\\nand $350 million. But rather than explain that the private equity firm then lowered its\\n(Continued)\\n 17\\n\\f Relying on trial evidence, the district court concluded that even a cursory review\\n\\nof the McLean Report would have raised questions as to whether the share valuation in\\n\\nthe SRR Report was too optimistic. The court did not find that the McLean Report\\n\\nnecessarily offered a more accurate picture of Constellis’s true value, but simply that a\\n\\nreasonably prudent fiduciary would have asked more questions. The court found that the\\n\\nanswers to these questions were “precisely the kinds of information that Wilmington, as\\n\\ntrustee, should have sought and evaluated” when considering the valuation of Constellis\\n\\nstock. Id. at 636. We see no reason to conclude otherwise.\\n\\n 2.\\n\\n The second major fault identified by the district court concerned Wilmington’s\\n\\nfailure to adequately probe the reliability of financial projections prepared by Constellis\\n\\nmanagement and used by SRR. Id. at 636–38. The court found that “the record show[ed]\\n\\nthat there were several red flags indicating that these projections were inflated, which\\n\\nWilmington either ignored or downplayed.” Id. at 636. Wilmington offers both general\\n\\nand specific challenges to this finding.\\n\\n First, Wilmington argues that Constellis management’s financial projections were,\\n\\nin fact, reliable and so required no probing. In support of this view, Wilmington contends\\n\\nthat because the McLean Report also utilized management’s financial projections to\\n\\n\\n\\n\\noffer to $275 million, see Brundle I, 241 F. Supp. 3d at 614–15, the report simply stated\\nthat the deal fell through due to the buyer’s “inability to secure sufficient financing.”\\n\\n 18\\n\\farrive at its own valuation of Constellis — a valuation the court treated as relevant — the\\n\\ncourt should have found the projections that the SRR Report used were also reliable.\\n\\n But although both McLean and SRR relied on financial projections prepared by\\n\\nConstellis management, they did not rely on the same financial projections. Id. at 638.\\n\\nThe projections that Constellis provided to SRR forecasted revenue over a much longer\\n\\ntime period, id. at 637–38, making them less accurate and less reliable. Further,\\n\\nConstellis management specifically prepared this set of projections for the purposes of\\n\\nSRR’s valuation in connection with the ESOP sale. This created a risk that Constellis\\n\\nmanagement might inflate its projections in response to incentives unique to the ESOP\\n\\nsale. Id. at 636. In light of these distinctions, the district court’s differing assessments of\\n\\nthe two reports’ comparative reliability were not inherently contradictory.\\n\\n At a more granular level, Wilmington maintains that each of the red flags that the\\n\\ndistrict court identified in Constellis’s financial projections are “non-existent.”\\n\\nWilmington Opening Br. 33–34, 38–39. Wilmington asserts largely factual, and\\n\\nuniversally unpersuasive, arguments in support of this view.\\n\\n Wilmington challenges the district court’s conclusion that Wilmington should\\n\\nhave been more critical of Constellis management’s financial projections because\\n\\nmanagement had a financial incentive to inflate the purchase price. The court found that\\n\\nthis initial red flag should have alerted Wilmington to probe the SRR valuation of\\n\\nConstellis. The district court’s finding on this issue primarily rested on the prospect of\\n\\nmanagement receiving 5% of the purchase price in cash bonuses — a factual\\n\\ndetermination well supported by the record. See Brundle I, 241 F. Supp. 3d at 636.\\n\\n 19\\n\\f The district court also identified as a red flag an ongoing government investigation\\n\\ninto accounting and record-keeping errors by Constellis, which the court concluded\\n\\n“should have raised questions about the reliability of Constellis’[s] . . . projections.” Id.\\n\\nAgain, contrary to Wilmington’s suggestion, we see no basis for holding this finding\\n\\nclearly erroneous. A government investigation into errors of this nature surely creates a\\n\\nquestion as to the reliability of a company’s financial projections, which a reasonably\\n\\nprudent fiduciary representing the buyers of the company should probe further. Cf.\\n\\nKeach v. U.S. Tr. Co., 419 F.3d 626, 633–37 (7th Cir. 2005) (finding ESOP trustee met\\n\\nfiduciary duty when it “analyzed exhaustively [the company’s] financials, had conducted\\n\\nindependent valuation analyses and had challenged the financial forecasts made by [the\\n\\ncompany’s] management as too optimistic”).\\n\\n Still another red flag to which Wilmington, in the district court’s view, did “not\\n\\nadequately respond was the riskiness of Constellis’[s] contract concentration.” Brundle I,\\n\\n241 F. Supp. 3d at 637. The district court believed that this risk called for Wilmington to\\n\\napply further scrutiny to the company’s financial projections. The court found, and\\n\\nWilmington does not dispute, that at the time of the ESOP sale, about 70% of Constellis’s\\n\\nrevenue depended on just two government contracts. Id. at 637. Yet Wilmington\\n\\nadopted a valuation that assumed Constellis stock posed significantly less risk than the\\n\\nstock market as a whole. Again relying on the trial testimony of a “neutral” and “highly\\n\\ncredible” third party expert, the court explained its conclusion that Constellis’s industry\\n\\npeers — namely, government contractors — are certainly “no less risky than the market\\n\\nas a whole.” Brundle II, 258 F. Supp. 3d at 663. And again, the record offers ample\\n\\n 20\\n\\fsupport for this finding. See Brundle I, 241 F. Supp. 3d at 637; Brundle II, 258 F. Supp.\\n\\n3d at 662–63. 7\\n\\n Wilmington also maintains that the district court unfairly characterized\\n\\nConstellis’s “multiple sets of projections” as a red flag. Wilmington claims that the\\n\\ndistrict court ignored the fact that SRR advised Wilmington that the market and\\n\\nConstellis had changed throughout 2013. But the court adequately addressed this\\n\\nargument, see Brundle I, 241 F. Supp. 3d at 635–36, and we defer to its factual finding\\n\\nthat the changes in the market and Constellis’s business prospects throughout 2013 did\\n\\nnot justify multiple sets of projections.\\n\\n Last, Wilmington contends that we should reverse the district court due to its\\n\\ninitially erroneous understanding of the warranties Wilmington obtained to indemnify the\\n\\nESOP against the ongoing government investigation. At first, the court incorrectly found\\n\\n 7\\n The court acknowledged that it originally had misunderstood the definition of the\\nrisk factor, called “beta,” that SRR used in its report. SRR chose a beta of 0.7, indicating\\nthat Constellis stock was less risky than the average stock (set at a beta of 1.0). The court\\nhad understood beta to measure the risk of Constellis stock relative to its industry peers,\\nbut beta actually measures the risk of a company’s stock — or in the case of a privately\\nheld company like Constellis, the risk of a company’s publicly traded industry peers —\\nrelative to the stock market as a whole. Brundle II, 258 F. Supp. 3d at 658.\\n Upon consideration of Wilmington’s Rule 59 motion, the court stood by its\\noriginal conclusion that Wilmington had inappropriately chosen a beta indicating that\\nConstellis was less risky than other stocks. The court concluded that a neutral beta of 1.0\\nwas more appropriate, noting that “[e]ven if government contracting business [in which\\nConstellis participates] does not fluctuate in correlation with the market, that does not\\nmean that government contracting is necessarily more stable.” Id. at 663. The court\\nnoted that a Wilmington trial witness had acknowledged that “the government contracting\\nindustry” is at times “less stable than the market as a whole.” Id. The court further relied\\non the “most credible” neutral expert’s testimony that the public companies used by SRR\\nto measure beta were “not a good match for Constellis.” Id. We see no clear error in\\nthese findings.\\n\\n 21\\n\\fthat only Constellis had indemnified the ESOP, thus creating an illusory form of\\n\\nindemnification. But in denying Wilmington’s Rule 59 motion, the court candidly\\n\\naddressed that error and acknowledged that, in fact, both Constellis and the Sellers had\\n\\nindemnified the ESOP. Brundle II, 258 F. Supp. 3d at 656. Nonetheless, the court found\\n\\nthat its “corrected understanding [did] not alter [its] conclusions about . . . Wilmington’s\\n\\ninadequate investigation into the soundness of Constellis’[s] financial projections.” Id.\\n\\nThe court explained that, “[e]ven omitting its erroneous view of the Sellers’ . . .\\n\\nwarranties,” Wilmington failed to rebut the many red flags discussed above, each of\\n\\nwhich independently called for more robust due diligence by Wilmington. Id. at 656–57.\\n\\nFor the reasons we have explained above, we find no clear error in any of these findings\\n\\nand so reject this final argument from Wilmington as to Constellis management’s\\n\\nfinancial projections.\\n\\n 3.\\n\\n The district court found that Wilmington’s third major failure in ensuring that its\\n\\nreliance on the SRR valuation was reasonably justified occurred when it “did not\\n\\ninvestigate the appropriateness of applying a 10% control premium” to Constellis stock\\n\\nand “fail[ed] to discount the [valuation] for lack of control.” Brundle I, 241 F. Supp. 3d\\n\\nat 638.\\n\\n Purchasers will generally pay more for “rights associated with control of the\\n\\nenterprise.” Estate of Godley v. Comm’r, 286 F.3d 210, 214 (4th Cir. 2002). We have\\n\\ndefined “control” as “an interest which allows the shareholder to unilaterally direct\\n\\ncorporate action, select management, decide the amount of distribution, rearrange the\\n\\n 22\\n\\fcorporation’s capital structure, and decide whether to liquidate, merge, or sell assets.” Id.\\n\\nat 215 (internal quotation marks omitted).\\n\\n The district court recognized that the ESOP had “powers beyond those of an\\n\\nordinary shareholder.” Brundle I, 241 F. Supp. 3d at 627 n.23. But the court nonetheless\\n\\nfound that the “ESOP essentially had no power to control Constellis” as a result of the\\n\\ntransaction’s unique structure. Id. at 638–39. Accordingly, the court concluded that\\n\\nWilmington erred in failing to investigate the SRR valuation, which not only failed to\\n\\ndiscount the stock for lack of control, but even added a 10% control premium to the value\\n\\nof the Constellis stock. The record supports both findings.\\n\\n The Sellers retained the power to appoint a majority of the Constellis board, a key\\n\\nindicator of control. See id. at 626. Further, the ESOP governing plan document and the\\n\\nESOP trust agreement each required Wilmington to vote its shares as the Constellis\\n\\nboard (not the ESOP) directed. See id. at 626–27. Wilmington maintains that the ESOP\\n\\ncould independently exercise its voting powers because the plan documents included a\\n\\nclause nullifying any provision that violated ERISA. But Constellis’s general counsel\\n\\ntestified at trial that the ESOP could only contravene the plan documents and exercise its\\n\\nindependent voting authority by filing a lawsuit — the same limited relief available to a\\n\\nminority shareholder. The district court thus concluded that Wilmington breached its\\n\\nfiduciary obligation in failing to question SRR’s failure to discount for lack of control.\\n\\nSee id. at 639. Given the record evidence that the ESOP’s unique ownership structure\\n\\nwas intentionally designed to maintain the Sellers’ control over Constellis even after\\n\\nselling their shares, the district court’s conclusion hardly constitutes clear error.\\n\\n 23\\n\\f Wilmington next contends that even if the ESOP lacked control, a 10% control\\n\\npremium was justified by the fact that the ESOP owned 100% of Constellis shares and\\n\\nobtained “elements of control.” Id. at 647. Wilmington argues that SRR reasonably\\n\\napplied a “modest” 10% control premium given that market control premiums are often\\n\\nbetween 35–40%. But in light of the limited rights provided to the ESOP, we cannot\\n\\nconclude that the district court erred in finding that Wilmington should have done more\\n\\nto challenge the use of any control premium. The SRR Report “devoted just one sentence\\n\\nto articulating its decision,” yet Wilmington never asked SRR about its decision to apply\\n\\na control premium. Id. at 639. For an assumption that carried such weighty\\n\\nconsequences, we cannot say that the district court clearly erred in finding that a\\n\\nreasonably prudent fiduciary would have probed the issue further.\\n\\n 4.\\n\\n The final major fault that the district court identified in Wilmington’s reliance on\\n\\nthe SRR Report was Wilmington’s failure to probe why SRR consistently rounded the\\n\\nvaluation of Constellis stock upwards. This repeatedly increased the price the ESOP had\\n\\nto pay for the stock. The district court concluded that because an ESOP fiduciary should\\n\\nbe concerned with achieving the lowest possible price for the ESOP, Wilmington ought\\n\\nto have asked why SRR consistently engaged in the upward rounding to the ESOP’s\\n\\ndetriment. Id. at 639–40.\\n\\n Wilmington devotes only a short footnote in its opening brief to this issue and fails\\n\\nto address it at all in its reply brief. It thus appears to have forfeited an appellate\\n\\nchallenge to the court’s findings on this issue. See Wahi v. Charleston Area Med. Ctr.,\\n\\n 24\\n\\fInc., 562 F.3d 599, 607 (4th Cir. 2009) (finding argument raised only in a footnote in\\n\\nappellant’s opening brief forfeited on appeal). Perhaps this is because the district court’s\\n\\nfinding is self-evidently correct. And, as the district court noted, Brundle I, 241 F. Supp.\\n\\n3d at 640, this conclusion accords with those of other courts. For example, the Sixth\\n\\nCircuit described a similar rounding practice as “extremely disconcerting” and noted that\\n\\nthis conduct, although not dispositive, was illustrative of lackluster due diligence\\n\\ndisplayed throughout the transaction process. Chao, 285 F.3d at 433–34. So too here.\\n\\n B.\\n\\n Apart from Wilmington’s four major failures to scrutinize SRR’s report, the\\n\\ndistrict court also found that Wilmington’s conduct throughout the transaction provided\\n\\nfurther evidence that Wilmington failed to act as a prudent fiduciary solely on behalf of\\n\\nthe ESOP participants. Although the court found that Wilmington’s actions on behalf of\\n\\nthe ESOP did not amount to bad faith, it recognized that “ERISA demand[ed] more to\\n\\nexcuse a fiduciary from liability.” Brundle I, 241 F. Supp. 3d at 643.\\n\\n The district court found that Constellis’s principal motivation for creating the\\n\\nESOP was to further the Sellers’ interests, not the interests of the ESOP participant\\n\\nbuyers. Id. at 616. The sale of Constellis to the ESOP enabled the Sellers to cash out\\n\\ntheir company stock, which they had tried and failed to accomplish several times, and to\\n\\nreap substantial tax savings. Moreover, the ESOP’s unique structure enabled the Sellers\\n\\nto avoid the downside risk of holding equity, yet profit from any upside, while also\\n\\nretaining control over the company. The court found that Wilmington, in its role as the\\n\\n\\n\\n 25\\n\\fESOP’s fiduciary, simply ignored these motivations rather than investigating whether\\n\\nthey affected the ESOP’s legality under ERISA. Id. at 640–42.\\n\\n The district court additionally found that making the Sellers’ interests paramount\\n\\nshortened the transaction timeline and rushed Wilmington’s due diligence process and\\n\\nprice and terms negotiations. To maximize the after-tax benefits to the Sellers, the ESOP\\n\\nsale had to conclude before the end of 2013. Accordingly, Wilmington and its agents\\n\\ncompleted their due diligence, made pricing decisions, conducted negotiations, and\\n\\nlaunched a tender offer in less than two months. Id. at 621–25. Wilmington employees\\n\\nmet to discuss the transaction only three times and met with Constellis management just\\n\\nonce. Id. at 642. All meetings lasted less than 90 minutes and several of Wilmington’s\\n\\nteam members were absent from each. Id. And the district court found that Wilmington\\n\\nviolated its own policy by repeatedly taking less than 48 hours between receiving a\\n\\nvaluation report and meeting to discuss it. Id. at 621, 625. The court concluded that this\\n\\ntype of conduct fell well short of the diligence expected of a prudent fiduciary. Id. at\\n\\n643.\\n\\n Finally, the court noted that “Wilmington’s lack of engagement and willingness to\\n\\nnegotiate so favorably with CSG may have been motivated by its significant business\\n\\nrelationship with CSG.” Id. The district court found that Wilmington, CSG, and SRR\\n\\nmaintained extensive and lucrative business relationships and that SRR was willing to\\n\\ndiscuss its valuation strategies with CSG while negotiations were ongoing. Id. The\\n\\nrecord offers ample support for all of these findings.\\n\\n\\n\\n 26\\n\\f C.\\n\\n Wilmington also maintains that the district court erred in finding that the value of\\n\\nStock Appreciation Rights (SARs) issued in connection with the ESOP’s purchase of\\n\\nConstellis should have been deducted from Constellis’s equity value for purposes of\\n\\nSRR’s valuation. SARs are incentives that Constellis would have owed to management\\n\\nhad the company’s value reached a certain price by a particular date. Wilmington argues\\n\\nthe value of the SARs should not have been deducted from Constellis’s estimated value\\n\\nbecause they were inchoate at the time of the sale. The district court disagreed and found\\n\\nthat, because Constellis intended for the SARs to be issued, their value should have been\\n\\ndeducted from Constellis’s equity value. Id. at 648.\\n\\n Wilmington rehashes the same argument on appeal but fails to identify any\\n\\nevidence that demonstrates the district court clearly erred in this factual determination.\\n\\nBecause we discern no such evidence, we reject this claim.\\n\\n D.\\n\\n In support of its final attack on the district court’s liability findings, Wilmington\\n\\nrelies on the ESOP’s subsequent sale of Constellis stock to ACADEMI LLC.\\n\\n In early February 2014, less than two months after the ESOP transaction,\\n\\nACADEMI, a major competitor in the private security market, began talks with\\n\\nConstellis management to acquire the company. Id. at 628. Initially, ACADEMI offered\\n\\nto purchase Constellis at an enterprise value of $283.3 million, in a transaction that would\\n\\nresult in $10 million in cash going to the ESOP. Seeking a better offer on the ESOP’s\\n\\nbehalf, Wilmington entered into negotiations with Constellis, the Sellers, and\\n\\n 27\\n\\fACADEMI. Id. at 629. Wilmington’s efforts proved successful: the final transaction,\\n\\nwhich closed on July 25, 2014, effectuated a sale of all the Constellis stock to ACADEMI\\n\\nat an implied enterprise value of $288.3 million. Id. at 631. The final transaction paid\\n\\n$20 million in cash to the ESOP — double the initial $10 million offer — as a result of\\n\\nthe Sellers’ agreeing to write off $33 million of the ESOP’s debt. Id. at 629.\\n\\n Wilmington argues that the ACADEMI sale proves that the ESOP did not overpay\\n\\nfor Constellis seven months earlier. Relying on the first prong of DOL’s proposed\\n\\nadequate-consideration regulations, Wilmington maintains that the ESOP paid “fair\\n\\nmarket value” for the Constellis stock because ACADEMI’s purchase of Constellis stock\\n\\nimplied an enterprise value of $288.3 million, which was within SRR’s estimated range\\n\\nof $275 to $330 million. Wilmington contends this purchase price is of particular\\n\\nsignificance because in the intervening time Constellis assertedly suffered several\\n\\nbusiness setbacks that decreased its enterprise value. 8\\n\\n This argument is unpersuasive for several reasons. The proposed DOL regulations\\n\\nupon which Wilmington relies provide that a trustee can prove consideration is\\n\\n“adequate” if it reflects the stock’s “fair market value” and is “the product of a\\n\\ndetermination made by the fiduciary in good faith.” Proposed Regulation Relating to the\\n\\n\\n 8\\n The district court carefully considered and described these setbacks in detail. See\\nBrundle I, 241 F. Supp. 3d at 627–28. Briefly, the State Department made a formal\\ndemand for payment of $62.2 million as part of its audit of Constellis’s accounting and\\nrecord-keeping practices; Constellis was forced to reduce projected revenue from a\\ncontract in Iraq by more than $100 million and push the remaining revenue further into\\nthe future; its projected revenue from a contract in Kuwait decreased by tens of millions\\nof dollars; and it lost a $338 million contract in Germany it had expected to win. Id.\\n\\n 28\\n\\fDefinition of Adequate Consideration, 53 Fed. Reg. at 17,633. Of course, because the\\n\\nDOL never enacted the proposed regulations, they are not binding. And, as we have\\n\\nexplained, courts look to the conduct of the trustee and whether it met its fiduciary\\n\\nobligations, not to whether the trustee arrived at a “fair” value. But even if we were to\\n\\nadopt the DOL’s proposed regulations, a trustee must satisfy both parts of the test to\\n\\nbenefit from the adequate consideration exception. See id. Assuming arguendo that the\\n\\npurchase was for “fair market value,” we find no error in the district court’s findings that\\n\\nWilmington failed to prove that the share price was also “the product of a determination\\n\\nmade by the fiduciary in good faith.”\\n\\n Furthermore, even if proving the ESOP paid “fair market value” sufficed to meet\\n\\nthe requirements of § 1108(e), the facts of the ACADEMI sale do not prove that the\\n\\nESOP paid only “fair market value” here. In fact, the district court found that the\\n\\nopposite was true. The court found that because ACADEMI, a private security company\\n\\nlike Constellis, would benefit from synergies resulting from its purchase of Constellis, it\\n\\nwould have been willing to pay significantly more for Constellis than the ESOP. Thus,\\n\\nthat ACADEMI actually paid less for Constellis stock suggested a significantly lower fair\\n\\nmarket value for the stock at the time of the ESOP purchase. Of course, Wilmington’s\\n\\nexperts disagreed with this synergies analysis, but the district court found the testimony\\n\\nof other experts on this point more persuasive. Brundle I, 241 F. Supp. 3d at 640. The\\n\\nrecord provides no basis to reject this finding. See Hendricks v. Cent. Reserve Life Ins.\\n\\nCo., 39 F.3d 507, 513 (4th Cir. 1994) (“An appellate court should be especially reluctant\\n\\n\\n\\n 29\\n\\fto set aside a finding based on the trial court’s evaluation of conflicting expert\\n\\ntestimony.”).\\n\\n In sum, the district court found that the ACADEMI sale did not constitute a\\n\\nmeaningful comparator. Discounting the additional synergy value, the $33 million debt\\n\\nwrite-off by the Sellers, and an expected tax refund from the sale, the court found the\\n\\nACADEMI purchase suggested that Constellis’s fair market value was closer to $200\\n\\nmillion — almost $100 million less than the enterprise value implied by the ESOP\\n\\ntransaction. Thus, the court found, the ACADEMI sale could not support Wilmington’s\\n\\nargument that the ESOP paid no more than adequate consideration for Constellis.\\n\\nBrundle I, 241 F. Supp. 3d at 640. We see no clear error in this conclusion.\\n\\n Additionally, we note that, despite paying more for Constellis stock, the ESOP did\\n\\nnot obtain nearly the level of control that ACADEMI acquired. While the ESOP\\n\\nobtained only some elements of control, ACADEMI acquired absolute and uncontested\\n\\ncontrol. Had the district court applied the “standard” 35–40% control premium\\n\\nWilmington’s experts suggested was reasonable, Constellis’s fair market value would fall\\n\\nsomewhere between $145 million and $150 million, almost half the value of the stock\\n\\npurchased by the ESOP only months earlier.\\n\\n\\n\\n III.\\n\\n Having rejected all of Wilmington’s challenges to the district court’s findings as to\\n\\nits liability, we turn to the court’s damages award. The district court concluded that\\n\\nWilmington’s fiduciary failures inflated the price the ESOP paid for Constellis stock by\\n\\n 30\\n\\f$29,773,250. “We review factual findings relating to the calculation of damages for clear\\n\\nerror.” Simms v. United States, 839 F.3d 364, 368 (4th Cir. 2016).\\n\\n A.\\n\\n To calculate the loss to an ESOP and compensate it for a fiduciary’s ERISA\\n\\nviolation, a court typically subtracts the stock’s fair market value, as determined by the\\n\\ncourt, from the inflated price paid by the ESOP. See Bruister, 823 F.3d at 265 (collecting\\n\\ncases). The district court precisely followed this approach. The court used as a baseline\\n\\nthe comprehensive damages estimate provided by Brundle’s expert — the only expert to\\n\\noffer one. 9 The court then considered the flaws in this valuation raised by Wilmington\\n\\nand made “appropriate adjustments based on the evidence adduced at trial and the\\n\\nrelative credibility of the experts.” Brundle I, 241 F. Supp. 3d at 645.\\n\\n Brundle’s expert estimated Wilmington’s lack of due diligence had caused the\\n\\nESOP to overpay for the Constellis stock by almost $103,862,000. But the district court\\n\\ndid not accept this figure. Instead, it independently analyzed each of Wilmington’s\\n\\npurported failings, considered the relevant trial testimony, and then awarded $29,773,250\\n\\n— or less than a third of the expert’s estimation — as damages. Id. at 645–49. The\\n\\nfollowing chart summarizes the district court’s damages findings:\\n\\n Error Difference between fair market value and\\n inflated price paid by ESOP (Damages)\\n Reliance on Management’s $4,325,000\\n Growth Projections\\n Use of .07 Beta $2,936,000\\n\\n 9\\n The Fifth Circuit held, in another ESOP case involving this same expert, that a\\ntrial court “was entitled to credit” his valuation methodology. Bruister, 823 F.3d at 267.\\n\\n 31\\n\\f Inclusion of Control Premium $8,186,000\\n Failure to Include Lack of $9,715,250\\n Control Discount\\n Stock Appreciation Rights $1,611,000\\n Rounding $3,000,000\\n Total Damages $29,773,250\\n\\n Wilmington did not provide the district court with an alternative damages\\n\\ncalculation or offer any evidence that the court could use to devise its own. At oral\\n\\nargument before us, Wilmington conceded as much. Accordingly, it has forfeited its\\n\\nchallenge to the methodology used by the district court when calculating the damages\\n\\naward. See Exxon Shipping Co. v. Baker, 554 U.S. 471, 487 n.6 (2008) (“[W]aiver and\\n\\nforfeiture rules . . . ensure that parties can determine when an issue is out of the case, and\\n\\nthat litigation remains, to the extent possible, an orderly progression.”).\\n\\n Moreover, Wilmington’s principal basis for urging reversal of the damages award\\n\\nconsists of a repetition of its challenge to the district court’s liability findings. Given our\\n\\naffirmance of all the district court’s liability findings — that Wilmington failed to\\n\\nadequately investigate and probe SRR as to the omission of the McLean Report, the use\\n\\nof Constellis management’s growth projections, the 0.7 beta, the 10% control premium,\\n\\nimproper rounding up, and SARs — that challenge fails.\\n\\n B.\\n\\n Wilmington additionally contends that the district court erred in declining to offset\\n\\nits damages calculation by the $20 million in cash that the ESOP received as a result of\\n\\nthe ACADEMI sale. According to Wilmington, “the district court’s failure to” do so\\n\\n“resulted in a clear windfall for the ESOP.” Wilmington Opening Br. at 53. As the\\n\\n 32\\n\\fdistrict court ably explained, see Brundle II, 258 F. Supp. 3d at 660–62, this claim is\\n\\nmeritless.\\n\\n ERISA expressly requires a fiduciary to “make good to [an ESOP] any losses”\\n\\nresulting from a given breach of duty. 29 U.S.C. § 1109(a); cf. Restatement (Second) of\\n\\nTrusts § 205 cmt. e (“If the trustee is authorized to purchase property for the trust, but in\\n\\nbreach of trust he pays more than he should pay, he is chargeable with the amount he paid\\n\\nin excess of its value.”). Thus, in cases involving overpayment for ESOP assets, courts\\n\\ngenerally compute restitution damages exactly as the district court did here: by deducting\\n\\nthe fair market value of the stock from the amount the ESOP actually paid.\\n\\n Wilmington insists that the ESOP’s subsequent and unrelated sale of the stock to\\n\\nACADEMI requires a different result. This misapprehends the nature of the breach. If\\n\\nWilmington had breached its duty by purchasing Constellis stock at all, then a damages\\n\\naward consisting of the purchase payments offset by any subsequent profits would indeed\\n\\nreturn the participants to the pre-purchase status quo.\\n\\n But Wilmington breached here by overpaying for the Constellis stock. Principles\\n\\nof restitution therefore entitle the ESOP and its participants to compensation for the loss\\n\\nfrom the overpayment. Any subsequent gains involving the stock, which the ESOP\\n\\nwould have obtained regardless of the overpayment, have no bearing on that loss. For\\n\\nthis very reason, courts have uniformly rejected analogous offsets to damage awards in\\n\\noverpayment cases. See, e.g., Bruister, 823 F.3d at 270–71 (rejecting offset to account\\n\\nfor unpaid or forgiven ESOP debt and noting that “[e]very court to consider this\\n\\nquestion” agreed); Henry v. U.S. Trust Co. of Cal., N.A., 569 F.3d 96, 98–100 (2d Cir.\\n\\n 33\\n\\f2009) (“Henry V”) (“If an investor pays $100 for 20 shares of stock and later sells those\\n\\nshares back to the original seller for $25, the result is not that the investor paid only $75\\n\\nfor the shares.”).\\n\\n Even so, Wilmington asserts that the events in this case resulted in “pure gain” to\\n\\nthe ESOP, justifying a deviation from this rule. It claims the ESOP “made $20 million\\n\\nfor the nominal cost of carrying $200 million in non-recourse debt for a few months,”\\n\\nbecause “[j]ust seven months” after the prohibited transaction, “the ESOP exchanged its\\n\\ndebt-burdened shares to ACADEMI for $20 million in cash.” Wilmington Opening Br.\\n\\nat 55–56. We disagree. As a preliminary matter, the burden imposed in additional debt\\n\\nfrom a $30 million overpayment is far from “nominal,” even for “just” seven months.\\n\\nSee Henry V, 569 F.3d at 99 n.4 (explaining “the obvious fact that the assumption of\\n\\nindebtedness has immediate legal and economic consequences even before the borrower\\n\\nbegins to repay the debt”).\\n\\n Moreover, if Wilmington seeks to portray the ACADEMI sale as an “exchange” in\\n\\nwhich the ESOP’s pre-sale debt had no effect on its post-sale assets, this is both illogical\\n\\nand untrue. Had the ESOP not initially overpaid for the stock by $30 million, it would\\n\\nhave shouldered tens of millions of dollars less in debt; in turn, it would presumably have\\n\\nbeen tens of millions of dollars better off after being compensated for the stock in the\\n\\nACADEMI sale. Put differently, although the ESOP benefited despite the breach, it\\n\\nwould have benefited at least as much — but ended in a far better position — without the\\n\\nbreach. In fact, had the ESOP initially paid a fair (lower) value for the Constellis stock\\n\\n\\n\\n 34\\n\\fand therefore carried less debt, it would have entered the ACADEMI negotiations in a\\n\\nstronger bargaining position and may have profited further still.\\n\\n Wilmington rejects this conclusion, stressing that the Sellers also agreed to write\\n\\noff more than $30 million of the ESOP’s debt, which it describes as an “effective[]\\n\\nreduc[tion]” of the 2013 purchase price. Wilmington Opening Br. at 56. But once again,\\n\\nthis independent act has no bearing on the ESOP’s loss.\\n\\n Wilmington unpersuasively contends that Henry III supports its argument. That\\n\\ncase addressed very different facts. There, the Second Circuit held that — where sellers\\n\\nfully and voluntarily repaid an ESOP after the IRS found overpayment, but before a court\\n\\nentered a damages judgment — a duplicative recovery for the same overpayment might\\n\\n“result in a windfall.” Henry III, 445 F.3d at 624. Wilmington does not even argue that\\n\\nthe Sellers’ write-off here was meant to remedy the ESOP’s overpayment. Nor could it:\\n\\nunlike the midstream repayment in Henry, the write-off here occurred more than a year\\n\\nprior to the initiation of any legal proceedings alleging Wilmington breached its fiduciary\\n\\nduties. As Wilmington concedes, the write-off was part of a negotiated agreement to\\n\\nclose the ACADEMI sale, a deal wholly unrelated to the issues raised here. Again, it is\\n\\nreasonable to assume that the ESOP would have negotiated equally favorable (if not more\\n\\nfavorable) terms had it paid a fair value in the first instance and thus entered the\\n\\nACADEMI discussions with substantially less debt.\\n\\n In sum, we find no error in the district court’s damages award.\\n\\n\\n\\n\\n 35\\n\\f IV.\\n\\n Finally, we examine the district court’s award of attorneys’ fees. The court\\n\\nawarded Brundle’s counsel $1,819,631.11 in statutory fees and an additional $1.5 million\\n\\nin fees from the ESOP’s damages judgment. No party has presented a substantive\\n\\nchallenge regarding the award of attorneys’ fees under the fee shifting statute. 10 Brundle\\n\\nchallenges the $1.5 million in additional fees (payable from the damages awarded to the\\n\\nESOP) as too small; Wilmington and Constellis, as fiduciaries for the ESOP, challenge\\n\\nthe award as legally improper. We review that award for abuse of discretion, mindful\\n\\nthat our review “is sharply circumscribed, and a fee award must not be overturned unless\\n\\nit is clearly wrong.” Berry v. Schulman, 807 F.3d 600, 617 (4th Cir. 2015) (internal\\n\\nquotation marks omitted).\\n\\n A.\\n\\n We first consider Brundle’s claim that the district court abused its discretion by\\n\\nnot awarding his counsel, Bailey & Glass, LLP (B&G), a total of $9.9 million in fees\\n\\nunder the firm’s one-third contingent fee agreement with Brundle himself. The district\\n\\ncourt initially suggested that this arrangement was indeed controlling. See Brundle II,\\n\\n258 F. Supp. 3d at 671–72. But the court held its fee decision in abeyance to consider the\\n\\n\\n 10\\n Strangely, although Brundle does not challenge the statutory fee award, he does\\nsummarily contend that he is entitled to $643,584.50 in expenses (the amount he\\nrequested when seeking statutory fees in the district court). The district court denied his\\nrequest for expenses, explaining that it was insufficiently documented. See Brundle II,\\n258 F. Supp. 3d at 669. Before us, Brundle provides neither documentation nor\\nargument. Accordingly, to the extent he even appeals the denial of expenses, we affirm\\nthe district court.\\n\\n 36\\n\\fviews of plan participants and ultimately based its award on equity rather than contract.\\n\\nWe can hardly find an abuse of discretion given that Brundle has no right to have the\\n\\nESOP fund his own fee agreement with B&G.\\n\\n Brundle contends that 29 U.S.C. § 1132(a)(2) — which empowers ESOP\\n\\nparticipants and beneficiaries to bring suit on behalf of an ESOP — additionally\\n\\nauthorizes him to enter into a legal services contract that binds the ESOP. Brundle\\n\\nmusters no caselaw to support his interpretation of the statute, and for good reason.\\n\\nWhile § 1132(a)(2) provides Brundle the right to sue on behalf of the ESOP, neither it\\n\\nnor any other statute authorizes him to unilaterally bind the ESOP to a contract or fee\\n\\nagreement. For this very reason, the vast majority of suits on behalf of ERISA plans take\\n\\nthe form of class actions, in which counsel can seek fees only after a class has been\\n\\ncertified and class members have been given the opportunity to object or opt out. Though\\n\\nB&G has a valid contingent fee agreement with Brundle, see Venegas v. Mitchell, 495\\n\\nU.S. 82 (1990), it does not have a fee agreement with the ESOP.\\n\\n As a result, only equity provides any possible basis for a fee award in addition to\\n\\nthe statutory fees awarded.\\n\\n B.\\n\\n After the district court received the views of some plan participants, it issued a\\n\\nfinal judgment awarding B&G $1.5 million in “addition[]” to the $1.8 million in statutory\\n\\n\\n\\n\\n 37\\n\\ffees — not as a contractual right, but as “a partial common fund award.” 11 Wilmington\\n\\nand Constellis assert that a trio of ERISA provisions precluded the court from awarding\\n\\nany common fund recovery. Unlike most challenges to fee awards, we review de novo\\n\\nquestions regarding a court’s legal authority. See, e.g., Country Vintner of N.C., LLC v. E\\n\\n& J. Gallo Winery, Inc., 718 F.3d 249, 254 (4th Cir. 2013).\\n\\n First, Wilmington and Constellis contend that any common fund award here would\\n\\nviolate ERISA’s “anti-alienation” and “exclusive benefit” provisions. See 29 U.S.C.\\n\\n§ 1056(d)(1) (providing that benefits under retirement plans cannot be “assigned or\\n\\nalienated”); id. § 1103(c)(1) (directing all “assets of a plan” to be “held for the exclusive\\n\\npurposes of providing benefits to participants in the plan and their beneficiaries and\\n\\ndefraying reasonable expenses of administering the plan”). But the district court properly\\n\\nrejected this argument, concluding that because the plan administrator did not yet possess\\n\\nthe damages award — in other words, the court still had jurisdiction over the funds and\\n\\nhad not distributed them to the ESOP — it could not be considered a plan asset. Brundle\\n\\nII, 258 F. Supp. 3d at 670. Of course, if the ESOP had received payment of the award,\\n\\nthose funds would have been subject to ERISA’s duties and protections. See Wilmington\\n\\n\\n 11\\n The district court made clear, and the parties do not dispute, that “[i]n granting\\nboth fee-shifting and contingent fee awards, . . . the contingent fee award must be offset\\nby the amount awarded under the fee-shifting provision.” Brundle II, 258 F. Supp. 3d at\\n672 & n.19. On appeal, Brundle seeks a total of approximately $9.9 million in fees plus\\nabout $650,000 in purported expenses, which (when offset by the $1.8 million in\\nstatutory fees paid by Wilmington) would entitle B&G to a net of approximately $8.8\\nmillion from the common fund. The district court instead awarded Brundle a net of only\\n$1.5 million in fees from the common fund, which it noted was in “addition[]” to the $1.8\\nmillion statutory fee-shifting award, for a total of $3.3 million in fees.\\n\\n 38\\n\\fShipping Co. v. New England Life Ins. Co., 496 F.3d 326, 333 (4th Cir. 2007). But where\\n\\na fund is still under the jurisdiction of the district court, the court may award fees from\\n\\nthat fund without running afoul of ERISA’s anti-alienation or exclusive benefit\\n\\nrequirements. See Kickham Hanley P.C. v. Kodak Ret. Income Plan, 558 F.3d 204, 213\\n\\n(2d Cir. 2009); Lynn v. CSX Transp., Inc., 84 F.3d 970, 975 (7th Cir. 1996).\\n\\n Next, Wilmington and Constellis argue that ERISA’s statutory fee-shifting\\n\\nprovision displaces the common fund doctrine. See 29 U.S.C. § 1132(g)(1) (authorizing\\n\\nprevailing plaintiffs to recover reasonable attorneys’ fees from defendants). They urge us\\n\\nto follow the Seventh Circuit in “limiting the common-fund approach to cases outside the\\n\\nscope of a fee-shifting statute.” Pierce v. Visteon Corp., 791 F.3d 782, 787 (7th Cir.\\n\\n2015); accord Haggart v. Woodley, 809 F.3d 1336, 1358–59 (Fed. Cir. 2016) (largely\\n\\nadopting Pierce rule). 12\\n\\n Several other circuits, however, have disagreed with this approach. See McKeage\\n\\nv. TMBC, LLC, 847 F.3d 992, 1003 (8th Cir. 2017) (“[T]he presence of a fee-shifting\\n\\nstatute precludes a common fund award only when that result is required by the statutory\\n\\nscheme involved.”); In re Bluetooth Headset Prods. Liab. Litig., 654 F.3d 935, 941 (9th\\n\\nCir. 2011) (“The award of attorneys’ fees in a class action settlement is often justified by\\n\\n[a] common fund or statutory fee-shifting[,] . . . and sometimes by both.”); Staton v.\\n\\n\\n 12\\n Pierce is in some tension with prior Seventh Circuit cases holding, in the\\ncontext of settlements, that common fund recoveries are sometimes available even where\\na case was brought under a statute with a fee-shifting provision. See Florin v.\\nNationsbank of Georgia, N.A., 34 F.3d 560, 563–64 (7th Cir. 1994); Skelton v. Gen.\\nMotors Corp., 860 F.2d 250, 252–57 (7th Cir. 1988).\\n\\n 39\\n\\fBoeing Co., 327 F.3d 938, 967–69 (9th Cir. 2003) (permitting common fund recovery\\n\\neven where statutory fees may be available); Cty. of Suffolk v. Long Island Lighting Co.,\\n\\n907 F.2d 1295, 1327 (2d Cir. 1990) (“In our view, fee-shifting statutes are generally not\\n\\nintended to circumscribe the operation of the equitable fund doctrine.”).\\n\\n To determine the proper course here, we consider the roots of the common fund\\n\\ndoctrine. The common fund principle derives from the equitable doctrines of quantum\\n\\nmeruit, Central Railroad & Banking Co. v. Pettus, 113 U.S. 116 (1885), and unjust\\n\\nenrichment, Trustees v. Greenough, 105 U.S. 527, 532 (1881). It allows a court to award\\n\\n“a reasonable attorney’s fee” to “a litigant or a lawyer who recovers a common fund for\\n\\nthe benefit of persons other than himself or his client . . . from the fund as a whole.”\\n\\nBoeing Co. v. Van Gemert, 444 U.S. 472, 478 (1980). The rationale for the doctrine is\\n\\nthat when one benefits from a lawsuit without contributing to its costs, he has been\\n\\nunjustly enriched at the successful litigant’s or lawyer’s expense. Mills v. Elec. Auto-Lite\\n\\nCo., 396 U.S. 375, 392 (1970). Courts remedy this inequity by shifting a proportional\\n\\nshare of reasonable attorneys’ fees onto these unjustly enriched beneficiaries.\\n\\n The Supreme Court has applied the “strong and uniform . . . background rule” of\\n\\nthe common fund doctrine “in a wide range of circumstances as part of [its] inherent\\n\\nauthority.” US Airways, Inc. v. McCutchen, 569 U.S. 88, 104 (2013) (collecting cases).\\n\\nWe agree with Brundle that it applies here. Scores of unnamed ESOP participants\\n\\nbenefited substantially from this lawsuit, while B&G bore the entirety of the costs and\\n\\nrisks. Equity thus demands that the enriched participants pay a proportional share of\\n\\nreasonable attorneys’ fees.\\n\\n 40\\n\\f To be sure, courts often, but not invariably, award common fund fees when a\\n\\nprocedural obstacle, such as the terms of a settlement, bars statutory fees that are\\n\\notherwise available. 13 But it does not follow that all statutory fee provisions necessarily\\n\\ndisplace the doctrine or render it superfluous. To the contrary: although both the\\n\\ncommon fund doctrine and fee-shifting statutes facilitate suit by plaintiffs who may\\n\\notherwise lack the means to hire counsel, they operate in distinct ways and serve distinct\\n\\npurposes.\\n\\n A common fund recovery places the plaintiffs’ cost of litigation on the recovering\\n\\nbeneficiaries of a lawsuit, whereas a fee-shifting statute places this burden on the losing\\n\\nparty. Cf. Venegas, 495 U.S. at 90 (differentiating between “what the losing defendant\\n\\nmust pay” to the plaintiff as attorneys’ fees under a fee-shifting statute and “what the\\n\\nprevailing plaintiff must pay his lawyer”). A fee-shifting statute thus creates an\\n\\nexception to the “American rule” that “the prevailing litigant is ordinarily not entitled to\\n\\ncollect a reasonable attorneys’ fee from the loser.” Alyeska Pipeline Serv. Co. v.\\n\\nWilderness Soc., 421 U.S. 240, 247 (1975). In contrast, the common fund doctrine —\\n\\nthough often similarly described as an exception — better accords with the American rule\\n\\n 13\\n See, e.g., Skelton, 860 F.2d at 256 (affirming common fund award where “the\\nfee-shifting provision [did] not . . . apply to a fee determination in a case settled in a\\ncommon fund”); In re Fine Paper Antitrust Litig., 751 F.2d 562, 582–83 (3d Cir. 1984)\\n(affirming common fund award where settlement released defendants from statutorily\\navailable fees). But see Reyes v. Bakery & Confectionary Union & Indus. Int’l Pension\\nFund, 281 F. Supp. 3d 833, 850 (N.D. Cal. 2017) (“[C]lass counsel may be awarded fees\\nfrom the common fund in addition to any award under ERISA’s fee-shifting statute.”);\\nHumphrey v. United Way of Tex. Gulf Coast, 802 F. Supp. 2d 847, 859 (S.D. Tex. 2011)\\n(“The Court . . . has the power and discretion to award reasonable fees under both\\n[ERISA] and the common fund doctrine.”).\\n\\n 41\\n\\fby holding the beneficiaries of a judgment or settlement responsible for compensating the\\n\\ncounsel who obtained the judgment or settlement for them. See Staton, 327 F.3d at 967.\\n\\n Furthermore, the purpose of the common fund doctrine, unlike a fee-shifting\\n\\nstatute, is to avoid unjust enrichment. Thus, although a statutory fee award against a\\n\\ndefendant generally may not include a contingency enhancement, see City of Burlington\\n\\nv. Dague, 505 U.S. 557, 565–67 (1992), courts routinely impose enhanced common fund\\n\\nawards to compensate counsel for litigation risk at the expense of beneficiaries who did\\n\\nnot shoulder this risk, see, e.g., In re Wash. Pub. Power Supply Sys. Secs. Litig., 19 F.3d\\n\\n1291, 1300 (9th Cir. 1994) (“There is nothing unfair about contingency enhancements in\\n\\ncommon fund cases . . . .”); Florin, 34 F.3d at 564–65 (similarly holding that “the policy\\n\\nconsiderations . . . that militate for forbidding risk multiples in statutory fee-shifting cases\\n\\nhave little force in common fund cases”).\\n\\n From these distinctions, it follows that a “reasonable” fee payable by a defendant\\n\\nto compensate the prevailing plaintiff’s counsel is not necessarily identical to a\\n\\n“reasonable” fee owed by a recovering beneficiary to plaintiff’s counsel, particularly\\n\\nwhere the contingency risk to plaintiff’s counsel is substantial. Cf. Venegas, 495 U.S. at\\n\\n85, 90 (affirming $406,000 contractual fee, paid by prevailing plaintiff to his counsel, as\\n\\nnot “unreasonable” even though “reasonable” statutory fee, paid by losing defendants,\\n\\nwas only $117,000); McKeage, 847 F.3d at 1004 (emphasizing “a distinction between the\\n\\namount a losing party may be required to pay” under fee-shifting provision in settlement\\n\\n“and the amount a class member should equitably be required to pay” under common\\n\\nfund doctrine).\\n\\n 42\\n\\f Consequently, we find unpersuasive the Seventh Circuit’s reasoning in Pierce. In\\n\\nlimiting the common fund doctrine to cases “outside the scope of a fee-shifting statute,”\\n\\nthe Pierce court reasoned first and foremost that “[c]ommon-law doctrines yield to\\n\\nstatutes.” 791 F.3d at 787. But the Supreme Court has instructed that courts must\\n\\n“presum[e] that Congress intended to retain the substance of the common law.”\\n\\nSamantar v. Yousuf, 560 U.S. 305, 320 n.13 (2010). We recognize, of course, that\\n\\nlegislative displacement of the common law does not require “the same sort of evidence\\n\\nof a clear and manifest congressional purpose demanded for preemption of state law.”\\n\\nAm. Elec. Power Co., Inc. v. Connecticut, 564 U.S. 410, 423 (2011) (alterations and\\n\\ninternal quotation marks omitted). Even so, a statute that shifts a reasonable fee onto a\\n\\nlosing defendant does not, without more, “speak[] directly” to congressional intent to\\n\\ndisplace recovery from a common fund. Id. at 424 (internal quotation marks omitted).\\n\\n The Pierce court additionally emphasized that “fee-shifting statutes are designed\\n\\nto ensure that the victims retain full compensation,” 791 F.3d at 787, a concern of\\n\\nindisputable importance. The common fund doctrine, however, balances this critical\\n\\ninterest against the concern of unjust enrichment, which ERISA’s fee-shifting provision\\n\\ndoes not purport to address.\\n\\n Finally, echoing the Pierce court, Wilmington and Constellis stress that B&G was\\n\\nentitled to, and received, a “reasonable” attorneys’ fee under statute. However, as we\\n\\nhave explained, what is “reasonable” as a fee from a losing defendant may well differ\\n\\nfrom what is “reasonable” as a fee from an individual directly benefited by counsel’s\\n\\nefforts. We particularly note that a “reasonable” fee under ERISA’s attorneys’ fee\\n\\n 43\\n\\fprovision (unlike a common fund award) precludes any compensation for contingency\\n\\nrisk. See Dague, 505 U.S. at 565–67. But, we have previously underscored, contingent\\n\\nfees serve an important function in providing under-resourced litigants access to counsel\\n\\nand the courts. In re Abrams & Abrams, P.A., 605 F.3d 238, 245–47 (4th Cir. 2010).\\n\\nConflating statutory attorneys’ fees with common fund recoveries would squarely\\n\\ncontravene this policy.\\n\\n We therefore agree with the Second, Eighth, and Ninth Circuits that a statutory\\n\\nfee-shifting provision (or an award of fees under such a provision) does not, as a matter\\n\\nof law, automatically preclude an award under the common fund doctrine. Accordingly,\\n\\nthe district court retained discretion to award supplemental attorneys’ fees from the\\n\\ncommon fund.\\n\\n C.\\n\\n Having established the district court’s authority to award supplemental fees, we\\n\\nturn to Brundle’s contention that the court abused its discretion in awarding its counsel\\n\\ntoo little from the common fund.\\n\\n Before setting the amount of its common fund award, the district court fashioned\\n\\nan ad hoc process analogous to class settlement procedures under Rule 23. Brundle II,\\n\\n258 F. Supp. 3d at 671–72. The court ordered Brundle’s counsel, B&G, to engage in a\\n\\ngood faith effort to notify the approximately 1,800 former ESOP participants of its\\n\\nproposed contingency fee award. After B&G did so, the court received 59 letters\\n\\nobjecting to a one-third contingency award. As a result of the objections, the court\\n\\ndecided to award B&G only $1.5 million as a supplemental fee payable from the\\n\\n 44\\n\\fdamages award, rather than granting counsel a full one-third ($9.9 million) of the ESOP’s\\n\\ntotal damages recovery.\\n\\n In reviewing the district court’s award, we note that Brundle had available a\\n\\nprocedural mechanism designed to carefully balance the interests of counsel, plaintiffs,\\n\\nand other similarly situated beneficiaries from the start — namely, class certification\\n\\npursuant to Rule 23. To be fair, Brundle and another plaintiff, Halldorson, did initially\\n\\nseek class certification, which the district court denied. But Brundle opted not to timely\\n\\nappeal this denial. And although Halldorson initially sought our review, he later\\n\\nwithdrew his appeal. See supra n.4.\\n\\n Had Brundle pursued class certification and prevailed, B&G could have secured\\n\\nattorneys’ fees from the class as a whole. Although a properly certified class might not\\n\\nhave agreed to the same one-third contingency fee that Brundle did, the district court\\n\\nmight well have awarded a fee significantly higher than the firm’s ultimate recovery\\n\\nhere. 14\\n\\n Brundle, represented by B&G, instead opted to forego Rule 23’s procedural\\n\\nstrictures — thus avoiding “the standards set for the protection of absent class members.”\\n\\nAmchem Prods., Inc. v. Windsor, 521 U.S. 591, 621 (1997). In light of this choice, the\\n\\ndistrict court’s decision to limit the common fund award was not inequitable, as\\n\\nillustrated by the objections from some of the ESOP’s participants. Nearly 60 of the\\n\\n 14\\n See, e.g., Savani v. URS Prof’l Sols. LLC, 121 F. Supp. 3d 564, 574–75 (D.S.C.\\n2015) (approving fee award of 39.57% from common fund award in ERISA settlement\\nand collecting cases); In re Marsh ERISA Litig., 265 F.R.D. 128, 149 (S.D.N.Y. 2010)\\n(approving fee award of 33.33% from common fund award).\\n\\n 45\\n\\f1,800 participants objected to the proposed common fund award, explaining that they had\\n\\nnever been informed of the case status, never agreed to B&G’s representation, and never\\n\\nauthorized the fund to pay a one-third fee. These process concerns would have been\\n\\navoided upfront had Brundle persisted in his pursuit of class certification. But because he\\n\\nand his counsel abandoned Rule 23’s class-protective procedures, equity cuts against\\n\\nawarding B&G the full one-third contingency fee.\\n\\n The district court properly weighed B&G’s efforts on behalf of the ESOP —\\n\\nincluding contingency risk — against the objections from ESOP participants to determine\\n\\na proper common fund award. Because we cannot say this balancing was clearly wrong,\\n\\nsee Berry, 807 F.3d at 617, we affirm the court’s fee award in full.\\n\\n\\n\\n V.\\n\\n For the foregoing reasons, the judgment of the district court is in all respects\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 46\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1063,"cells":{"id":{"kind":"number","value":4602366,"string":"4,602,366"},"name":{"kind":"string","value":"Sharyl Thompson ATTKISSON; James Howard Attkisson; Sarah Judith Starr Attkisson, Plaintiffs - Appellants, v. Eric Himpton HOLDER, Jr., Individually; Patrick R. Donahoe, Individually; Unknown Named Agents of the Department of Justice, in Their Individual Capacities; Unknown Named Agents of the United States Postal Service, in Their Individual Capacities; Unknown Named Agents of the United States, in Their Individual Capacities; Verizon Virginia LLC; Federal Bureau of Investigation; MCI Communications Services, Inc., D/B/A Verizon Business Services ; Cellco Partnership, D/B/A Verizon Wireless, Defendants - Appellees."},"name_abbreviation":{"kind":"string","value":"Sharyl Attkisson v. Eric Holder, Jr."},"decision_date":{"kind":"string","value":"2019-03-21"},"docket_number":{"kind":"string","value":"18-1677"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Wynn\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"020lead\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/9888176/\", \"author_raw\": \"\"}, {\"author\": \"\", \"type\": \"035concurrenceinpart\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/9888177/\", \"author_raw\": \"\"}, {\"author\": \"KING, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-1677\\n\\n\\nSHARYL THOMPSON ATTKISSON; JAMES HOWARD ATTKISSON;\\nSARAH JUDITH STARR ATTKISSON,\\n\\n Plaintiffs – Appellants,\\n v.\\n\\nERIC HIMPTON HOLDER, JR., Individually; PATRICK R. DONAHOE,\\nIndividually; UNKNOWN NAMED AGENTS OF THE DEPARTMENT OF\\nJUSTICE, In their individual capacities; UNKNOWN NAMED AGENTS OF\\nTHE UNITED STATES POSTAL SERVICE, In their individual capacities;\\nUNKNOWN NAMED AGENTS OF THE UNITED STATES, In their individual\\ncapacities; VERIZON VIRGINIA LLC; FEDERAL BUREAU OF\\nINVESTIGATION; MCI COMMUNICATIONS SERVICES, INC., d/b/a Verizon\\nBusiness Services; CELLCO PARTNERSHIP, d/b/a Verizon Wireless,\\n\\n Defendants – Appellees.\\n\\n\\nAppeal from the United States District Court for the Eastern District of Virginia, at\\nAlexandria. Leonie M. Brinkema, District Judge. (1:17-cv-00364-LMB-JFA)\\n\\n\\nArgued: January 29, 2019 Decided: March 21, 2019\\n\\n\\nBefore MOTZ, KING, and WYNN, Circuit Judges.\\n\\n\\nAffirmed by published opinion. Judge King wrote the opinion, in which Judge Motz\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4379619/\", \"author_raw\": \"KING, Circuit Judge:\"}, {\"author\": \"joined. Judge Wynn wrote an opinion concurring\", \"type\": \"concurrence\", \"text\": \"joined. Judge Wynn wrote an opinion concurring in part and dissenting in part.\\n\\n\\nARGUED: Paul Schiff Berman, Chevy Chase, Maryland, for Appellants. H. Thomas\\nByron, III, UNITED STATES DEPARTMENT OF JUSTICE, Washington, D.C.; Reid\\n\\nMason Figel, KELLOGG, HANSEN, TODD, FIGEL & FREDERICK, P.L.L.C.,\\nWashington, D.C., for Appellees. ON BRIEF: Clyde T. Turner, TURNER &\\nASSOCIATES, Little Rock, Arkansas, for Appellants. Joseph H. Hunt, Assistant\\nAttorney General, Catherine H. Dorsey, Civil Division, UNITED STATES\\nDEPARTMENT OF JUSTICE, Washington, D.C.; G. Zachary Terwilliger, United States\\nAttorney, OFFICE OF THE UNITED STATES ATTORNEY, Alexandria, Virginia, for\\nFederal Appellees. David L. Schwarz, Kylie Chiseul Kim, Albert Y. Pak, KELLOGG,\\nHANSEN, TODD, FIGEL & FREDERICK, P.L.L.C., Washington, D.C., for Appellees\\nMCI Communications Services Incorporated, Cellco Partnership, and Verizon, Virginia,\\nLLC.\\n\\n\\n\\n\\n 2\\n\\nKING, Circuit Judge:\\n\\n Plaintiffs Sharyl Thompson Attkisson, James Howard Attkisson, and Sarah Judith\\n\\nStarr Attkisson appeal from the dismissal with prejudice of their claims in the Eastern\\n\\nDistrict of Virginia. The plaintiffs sued a number of named and unnamed government\\n\\nofficials for alleged illegal intrusions into the plaintiffs’ electronic devices to conduct\\n\\nunlawful surveillance, and also sued certain corporate entities for allegedly facilitating\\n\\nthose intrusions. After three-and-a-half years of protracted preliminary litigation —\\n\\nincluding multiple amendments to the complaint — the district court dismissed the\\n\\nplaintiffs’ claims. As explained below, we are satisfied to affirm the judgment.\\n\\n\\n\\n I.\\n\\n A.\\n\\n The district court dismissed the majority of the plaintiffs’ claims pursuant to Rule\\n\\n12(b)(6) of the Federal Rules of Civil Procedure. That ruling addressed the claims raised\\n\\nin the plaintiffs’ consolidated complaint. See Attkisson v. Holder, No. 1:17-cv-00364\\n\\n(E.D. Va. Sept. 15, 2017), ECF No. 117 (the “Consolidated Complaint”). In reviewing\\n\\nthat dismissal we accept and recite the facts alleged in the Consolidated Complaint in the\\n\\nlight most favorable to the plaintiffs. See Lucero v. Early, 873 F.3d 466, 469 (4th Cir.\\n\\n2017).\\n\\n The district court then disposed of the balance of the plaintiffs’ claims as\\n\\npresented in their amended consolidated complaint. See Attkisson v. Holder, No. 1:17-\\n\\ncv-00364 (E.D. Va. Feb. 5, 2018), ECF No. 174 (the “Amended Complaint”). The court\\n\\n 3\\n\\nbased that ruling partly on Rule 12(b)(6), and otherwise on various procedural defects\\n\\nrelating to the Amended Complaint. To properly review that final decision, we recite the\\n\\npertinent facts alleged in the Amended Complaint as well as the procedural history of this\\n\\nlitigation. See, e.g., Ballard v. Carlson, 882 F.2d 93, 94 (4th Cir. 1989) (providing “full\\n\\nstatement of the facts,” including procedural history, to review dismissal for procedural\\n\\ndefects).\\n\\n 1.\\n\\n a.\\n\\n At all relevant times, plaintiff Sharyl Thompson Attkisson (“Attkisson”) was an\\n\\ninvestigative reporter for CBS News. Plaintiffs James Howard Attkisson and Sarah\\n\\nJudith Starr Attkisson are Attkisson’s husband and daughter, respectively. In early 2011,\\n\\nas alleged in the Consolidated Complaint, Attkisson worked on the CBS News\\n\\ninvestigation into “Operation Fast and Furious,” an ill-fated sting operation of the Bureau\\n\\nof Alcohol, Tobacco, and Firearms (the “ATF”). Intended as a means to sweep up gun\\n\\ntraffickers and drug cartel members at the southern border, Operation Fast and Furious\\n\\ninvolved the circulation of thousands of firearms by the ATF that were to be traced and\\n\\nrecaptured along with their purchasers. The ATF, however, lost track of a large number\\n\\nof those weapons, one of which was used to kill a Border Patrol Agent in 2010.\\n\\nAttkisson’s highly critical report of the Operation aired on CBS on February 22, 2011.\\n\\nOver the course of that year, Attkisson continued reporting on Operation Fast and\\n\\nFurious, in the face of efforts by the ATF, the Federal Bureau of Investigation (the\\n\\n\\n\\n 4\\n\\n“FBI”), and the Department of Justice (the “DOJ”) to stymie her reporting. 1 The story\\n\\nsurrounding the Operation grew to include alleged problems with then-Attorney General\\n\\nEric Holder’s testimony (apparently before Congress), as well as the DOJ’s retraction of\\n\\na letter to Congress that contained misinformation about the Operation.\\n\\n In “mid-to-late 2011,” the plaintiffs noticed “anomalies” in several electronic\\n\\ndevices at their home in Leesburg, Virginia. See Consolidated Complaint ¶ 23.\\n\\nSpecifically, a laptop and desktop computer began “turning on and off at night,” the\\n\\nhouse alarm went off without provocation, and the plaintiffs experienced phone and\\n\\ntelevision interference. Id. The plaintiffs’ devices relied on a Verizon FiOS line that\\n\\nprovided phone, internet, and television services to their home. The problems with those\\n\\ndevices continued through 2012, despite Verizon’s attempts to cure them.\\n\\n Meanwhile, Attkisson continued her work for CBS. In October 2012, Attkisson\\n\\nreported on the September 2012 attacks on our Embassy in Benghazi, Libya. Her\\n\\nreporting on those attacks criticized the actions of the Obama administration, drawing on\\n\\nconfidential sources in the federal government.\\n\\n In December 2012, the plaintiffs asked an acquaintance “with U.S. government\\n\\nintelligence experience” to examine their home. See Consolidated Complaint ¶ 43. That\\n\\nacquaintance found an extra fiber optics cable dangling from the plaintiffs’ Verizon FiOS\\n\\n 1\\n Although Attkisson asserts that the ATF, FBI, and DOJ mobilized against her\\nreporting, the specific facts underlying that claim amount to nothing more than the DOJ’s\\ndenials in response to Attkisson’s reporting; the DOJ’s attempt to identify the sources of\\ninternal leaks; and the ATF’s goal of “proactively push[ing] positive stories” to repair the\\nagency’s public image. See Consolidated Complaint ¶¶ 16-17 & n.2.\\n\\n\\n 5\\n\\nbox. When Attkisson called Verizon to ask about the cable, a Verizon representative\\n\\ndenied any knowledge of it and suggested that Attkisson contact law enforcement. Soon\\n\\nthereafter, an individual identifying herself as a Verizon employee called Attkisson and\\n\\nsaid she would send a technician to the plaintiffs’ home. The next day — January 1,\\n\\n2013 — a person “represented to be a Verizon technician” removed the cable. Id. ¶ 44.\\n\\nAttkisson later attempted to contact that technician but was unsuccessful. Through\\n\\nJanuary and February 2013, the plaintiffs continued to experience phone and internet\\n\\nproblems that Verizon could not solve.\\n\\n On January 8, 2013, Attkisson gave her Toshiba laptop (used for her work for\\n\\nCBS) to an expert to conduct a forensic analysis of the machine. That expert found\\n\\nevidence of an unauthorized intrusion, possibly using software belonging to a\\n\\ngovernment actor. Attkisson reported the expert’s findings to CBS, which retained\\n\\nanother expert to examine Attkisson’s work laptop and home desktop computers. Based\\n\\non the forensic analysis conducted by the CBS-retained expert, the plaintiffs allege that\\n\\ntheir desktop, smart phone, and Attkisson’s work laptop were the “targets of unauthorized\\n\\nsurveillance efforts,” beginning around June 2011. See Consolidated Complaint ¶¶ 27,\\n\\n48-49. That analysis also showed that someone had installed “surveillance spyware” on\\n\\nAttkisson’s work laptop around February 2012 and “executed remote actions” to remove\\n\\nevidence of the surveillance around December 2012. Id. ¶¶ 27, 42.\\n\\n In March 2013, the plaintiffs’ desktop began malfunctioning and finally shut down\\n\\nfor good. In September 2013, Attkisson “observed” that her personal laptop, a MacBook\\n\\nAir, was “accessed remotely, controlled, and [unspecified] data deleted.” See\\n\\n 6\\n\\nConsolidated Complaint ¶ 57. The plaintiffs did not obtain any expert analysis of the\\n\\nMacBook, but they allege that some of the intrusions described heretofore were executed\\n\\n“via an IP address owned, controlled, and operated by” the United States Postal Service\\n\\n(the “USPS”). Id. ¶ 27.\\n\\n In mid-2013, Attkisson and CBS announced publicly that her personal devices had\\n\\nbeen accessed and compromised. Attkisson also filed a complaint with the Inspector\\n\\nGeneral for the DOJ. In response, the FBI and DOJ privately and publicly affirmed that\\n\\nthey had no knowledge of any intrusions into the plaintiffs’ devices. The DOJ Inspector\\n\\nGeneral asked to examine the affected computers. CBS declined to release Attkisson’s\\n\\nwork laptop, but Attkisson provided her home desktop to the Inspector General. In early\\n\\n2015, the Inspector General released a report that “noted a great deal of advanced mode\\n\\ncomputer activity not attributable” to the plaintiffs, but concluded that there was “no\\n\\nevidence of intrusion” into the desktop. See Consolidated Complaint ¶ 60.\\n\\n b.\\n\\n The Consolidated Complaint, filed in September 2017, named as defendants Eric\\n\\nHolder, the Attorney General at all relevant times; Patrick R. Donahoe, the Postmaster\\n\\nGeneral during the relevant period; and “unknown named agents” of the DOJ, the USPS,\\n\\nand “the United States.” See Consolidated Complaint 1. In addition to describing the\\n\\nevents recited above, the Consolidated Complaint offers a variety of allegations to link\\n\\nthose events to the defendants listed therein.\\n\\n Regarding the defendant “unknown named agents,” or “John Doe agents,” the\\n\\nConsolidated Complaint provides almost no direct allegations concerning those agents’\\n\\n 7\\n\\nactions. Instead, it asserts that unnamed agents “are in some manner responsible and\\n\\nliable for” the acts alleged by the plaintiffs, that is, the intrusions into their personal\\n\\nelectronic devices. See Consolidated Complaint ¶ 11.\\n\\n The Consolidated Complaint also points to a number of policy-level initiatives\\n\\nundertaken by the FBI and DOJ concerning electronic surveillance, presumably to\\n\\nsupport the claim that employees of those agencies carried out the alleged intrusions. For\\n\\nexample, in 2012, the FBI and DOJ jointly announced a “new effort” to address “national\\n\\nsecurity-related cyber issues,” while simultaneously seizing “personal and phone records\\n\\nbelonging to journalists from the Associated Press.” See Consolidated Complaint ¶ 30.\\n\\nThe Consolidated Complaint does not allege, however, that those seizures were unlawful,\\n\\nand later references the DOJ’s use of search warrants to investigate internal leaks to the\\n\\nmedia. Id. ¶¶ 30, 72(Z), 72(AA). Later in 2012, the DOJ provided training for the\\n\\nNational Security Cyber Specialists Network, as well as the computer crime unit in the\\n\\nDOJ’s Criminal Division. Regarding the role of the USPS, the plaintiffs allege that the\\n\\nUSPS has a “working relationship with the FBI, Department of Homeland Security, and\\n\\nDOJ for domestic surveillance projects.” Id. ¶ 63.\\n\\n The Consolidated Complaint also references emails released by Wikileaks (no\\n\\nlonger available online), in which members of a “global intelligence company doing\\n\\nbusiness with government agencies” discussed a perceived White House “witch hunt[] of\\n\\ninvestigative journalists.” See Consolidated Complaint ¶ 33. Finally, that Complaint\\n\\nalleges that in November 2012, the FBI “initiated a body of cyber security case\\n\\ninvestigations that would later relate to the illegal intrusions” into the plaintiffs’ devices.\\n\\n 8\\n\\nId. ¶ 39. It is unclear what those investigations entailed, what relationship they had to the\\n\\nplaintiffs or the intrusions into their devices, and who or what was the focus of the FBI’s\\n\\ninquiry. The Consolidated Complaint also alleges that the “FBI investigation involving\\n\\nMs. Attkisson’s computer intrusions was circulated to the DOJ’s national cyber security\\n\\ngroup” in late 2012. Id. ¶ 59.\\n\\n With respect to Attorney General Holder’s personal involvement, the Consolidated\\n\\nComplaint identifies a number of public statements that purportedly show that Holder\\n\\nknew of (unrelated) illegal surveillance conducted by the National Security Agency (the\\n\\n“NSA”). It references a DOJ report regarding revisions to DOJ policies, including\\n\\nchanges that restricted the circumstances in which the DOJ would seek to seize a\\n\\njournalist’s work product. The Consolidated Complaint asserts that Holder was\\n\\npersonally involved in what it characterizes as illegal surveillance of a reporter named\\n\\nJames Rosen in 2010, though it also alleges that Holder signed off on search warrants\\n\\nconcerning individuals in the media at that time. Lastly, the Consolidated Complaint\\n\\nalleges that Holder discussed Attkisson’s reporting on Operation Fast and Furious; that he\\n\\ndirected an aide to call a CBS News anchor and tell him to “get a ‘handle’ on\\n\\n[Attkisson’s] reporting”; and that Holder used “DOJ assets” to work with “smear\\n\\nmachines like Media Matters to attack reporters,” including Attkisson. See Consolidated\\n\\nComplaint ¶ 72(Q)-(T), (W). 2\\n\\n\\n 2\\n The Consolidated Complaint also makes various speculative and conclusory\\nassertions against Holder, such as stating, without any supporting factual allegation or\\nindication of personal knowledge, that Holder “promulgated a policy that required or\\n(Continued)\\n 9\\n\\n With regard to Postmaster Donahoe’s involvement in the foregoing events, the\\n\\nConsolidated Complaint alleges that he was ultimately responsible for any use of the\\n\\nUSPS network, including the use of its IP addresses. That Complaint also generally\\n\\nalleges that USPS has cooperated with the DOJ and FBI in their investigations, including\\n\\nby unconstitutionally monitoring mail.\\n\\n 2.\\n\\n The Amended Complaint, filed in February 2018, added as defendants, inter alia,\\n\\nMCI Communications Services, Inc., d/b/a Verizon Business Services; Cellco Partnership\\n\\nd/b/a Verizon Wireless; and Verizon Virginia LLC (collectively, the “Verizon\\n\\ndefendants,” or “Verizon”). The central factual allegations in the Amended Complaint\\n\\nmirror those provided in the Consolidated Complaint. With respect to the Verizon\\n\\ndefendants and their involvement in the intrusions into the plaintiffs’ personal devices,\\n\\nthe Amended Complaint offers the following allegations:\\n\\n • That Verizon provided the plaintiffs’ phone, internet, and television\\n services through the Verizon FiOS cable installed in their home;\\n\\n • That Verizon made various attempts to resolve the anomalies with\\n the plaintiffs’ electronic devices and failed, as discussed above;\\n\\n • That someone purporting to be a Verizon technician removed an\\n extra FiOS cable from the plaintiffs’ home, as discussed above;\\n\\n\\n\\n\\nencouraged the violation of Plaintiffs’ rights.” See Consolidated Complaint ¶ 72(G).\\nLike the district court, we disregard such bare speculation. See Bell Atl. Corp. v.\\nTwombly, 550 U.S. 544, 555 (2007) (emphasizing that allegations in complaint must\\n“raise a right to relief above the speculative level”).\\n\\n\\n 10\\n\\n • That the FBI’s Telephone Telecommunications Intercept and\\n Collection Technology Unit has the capacity to interface with\\n Verizon’s network infrastructure; and\\n\\n • That government agents used Verizon’s network to unlawfully\\n access Attkisson’s work laptop.\\n\\nSee Amended Complaint ¶¶ 31, 33, 38-39, 54-57, 81-82, 84.\\n\\n B.\\n\\n 1.\\n\\n These proceedings began in December 2014, when the plaintiffs sued Attorney\\n\\nGeneral Holder, Postmaster Donahoe, and the John Doe agents in the Superior Court of\\n\\nthe District of Columbia. The plaintiffs’ Superior Court complaint included First and\\n\\nFourth Amendment claims based on the electronic intrusions described above. In\\n\\nFebruary 2015, Holder and Donahoe removed the lawsuit to the district court for the\\n\\nDistrict of Columbia.\\n\\n On February 23, 2015, the plaintiffs sought expedited discovery in the District of\\n\\nColumbia, requesting “limited, immediate discovery” to “determine the true identifies\\n\\n[sic] of the Doe Defendants.” See Attkisson v. Holder, No. 1:15-cv-00238 at 1 (D.D.C.\\n\\nFeb. 23, 2015), ECF No. 5. Because the plaintiffs failed to provide a more detailed\\n\\nexplanation of such discovery, the district court denied their motion without prejudice.\\n\\n The plaintiffs renewed their expedited discovery motion on March 20, 2015. The\\n\\nrenewed motion contained twenty-one interrogatories to be served on Holder, Donahoe,\\n\\nthe USPS, and DOJ. The interrogatories contained broad requests, including for “[t]he\\n\\nidentity of any person who has knowledge of existence and use of technology capable of\\n\\n\\n 11\\n\\nremotely using a ‘kickstart’ program between 2011-2013” to remove surveillance\\n\\nsoftware from a personal computer. See Attkisson v. Holder, No. 1:15-cv-00238 at 4\\n\\n(D.D.C. Mar. 20, 2015), ECF No. 21-1. The defendants opposed the plaintiffs’ renewed\\n\\ndiscovery motion on April 6, 2015, and at the same time moved to dismiss the complaint.\\n\\nIn response, the plaintiffs amended their complaint. The district court thus denied the\\n\\nmotion to dismiss as moot.\\n\\n On July 3, 2015, the district court denied the plaintiffs’ renewed motion to\\n\\nexpedite discovery. First, the court observed that the plaintiffs had failed to comply with\\n\\nthat court’s Local Rule requiring the parties to meet and confer before seeking court\\n\\nintervention. The court also determined that the plaintiffs failed to meet the “good cause”\\n\\nstandard for expedited discovery, primarily because their requests were “not narrowly\\n\\ntailored to discovering the identity of Doe defendants.” See Attkisson v. Holder, No.\\n\\n1:15-cv-00238 at 11 (D.D.C. July 3, 2015), ECF No. 34.\\n\\n Soon thereafter, the defendants renewed their motion to dismiss the then-operative\\n\\ncomplaint in the District of Columbia. In response, the plaintiffs voluntarily dismissed\\n\\ntheir claims against Holder and Donahoe without prejudice in August 2015. Because\\n\\nHolder and Donahoe had been the only named defendants in that complaint, the district\\n\\ncourt requested a “recommendation for future proceedings.” See Attkisson v. Holder, No.\\n\\n1:15-cv-00238 (D.D.C. Aug. 27, 2015). The plaintiffs responded by asserting that they\\n\\nintended to file a separate claim “against the named defendants and others” under the\\n\\nFederal Tort Claims Act (the “FTCA”). See Attkisson v. Holder, No. 1:15-cv-00238 at 1\\n\\n(D.D.C. Aug. 27, 2015), ECF No. 39. They also represented to the court that they were\\n\\n 12\\n\\n“in the process of serving” subpoenas on the USPS in an effort to identify the John Doe\\n\\nagents. Id. at 2. The plaintiffs thus requested “that no action be taken in this case”\\n\\npending that discovery and the filing of their FTCA suit. Id. No further action occurred\\n\\nin the original District of Columbia lawsuit until October 2015, when the plaintiffs\\n\\nmoved to compel the USPS to comply with their discovery efforts.\\n\\n Over the next several months, the plaintiffs and the Government litigated the\\n\\nplaintiffs’ motion to compel, which was fully briefed by March 2016. No party took any\\n\\naction thereafter until July 28, 2016, when the district court consolidated the plaintiff’s\\n\\ninitial lawsuit with the FTCA complaint, pursuant to Federal Rule of Civil Procedure\\n\\n42(a). The FTCA case — which the plaintiffs had filed in September 2015 — arose from\\n\\nthe same facts as the initial lawsuit, and identified as defendants Holder, Donahoe, the\\n\\nJohn Doe agents, and the United States. In light of the change in named parties that was\\n\\noccasioned by consolidation, the court denied the plaintiffs’ pending motion to compel as\\n\\nmoot. On March 29, 2017, the consolidated lawsuit was transferred from the District of\\n\\nColumbia to the Eastern District of Virginia because the FTCA claims lacked venue in\\n\\nthe District of Columbia. We thus turn to a review of the post-transfer events in the\\n\\nEastern District of Virginia.\\n\\n 2.\\n\\n a.\\n\\n After their consolidated lawsuit was transferred to the Eastern District of Virginia\\n\\nin March 2017, the plaintiffs’ lawyers failed to notice their appearances there until April\\n\\n\\n\\n 13\\n\\n21, 2017 — nearly a month later. The plaintiffs then took no action at all for three more\\n\\nmonths.\\n\\n On July 18, 2017, the case was reassigned from Judge Cacheris to Judge\\n\\nBrinkema, and the court ordered that any motion to dismiss the plaintiffs’ claims be filed\\n\\nby early August 2017. The plaintiffs filed their first motion in the Eastern District of\\n\\nVirginia on July 26, 2017, moving for reconsideration of their most recent motion to\\n\\ncompel discovery, which the District of Columbia court had denied as moot upon\\n\\nconsolidating the two lawsuits. The plaintiffs’ motion sought USPS records and a taped\\n\\ndeposition of a USPS representative, to cover topics including, inter alia, “[a]ny and all\\n\\nrecords, logs, or other form of identification material that will or may assist in\\n\\nidentifying” any persons with access to the IP address identified by the plaintiffs’\\n\\nforensic analysis. See Attkisson v. Holder, No. 1:17-cv-00364 at 5 (E.D. Va. July 26,\\n\\n2017), ECF No. 91-1. On July 28, 2017, the plaintiffs amended their discovery request to\\n\\ncover information relating to a second IP address.\\n\\n On August 9, 2017, the defendants moved to dismiss the plaintiffs’ claims for\\n\\nfailure to state a claim. Defendants Holder and Donahoe also invoked a qualified\\n\\nimmunity defense. On August 14, 2017, the defendants filed a joint opposition to the\\n\\nplaintiffs’ motion for reconsideration, emphasizing the breadth of the plaintiffs’\\n\\ndiscovery requests, the high bar for granting motions for reconsideration, and reasserting\\n\\nthe individual defendants’ right to immunity.\\n\\n On September 1, 2017, the magistrate judge heard argument on the plaintiffs’\\n\\nmotion to reconsider. After the hearing, the magistrate judge denied the reconsideration\\n\\n 14\\n\\nmotion without prejudice “as to the subject matter of the discovery sought by plaintiffs,”\\n\\nfor reasons “stated from the bench.” Attkisson v. Holder, No. 1:17-cv-00364 (E.D. Va.\\n\\nSept. 1, 2017), ECF No. 107.\\n\\n On September 5, 2017, the district court entered a scheduling order, which\\n\\nestablished a discovery deadline of January 12, 2018. That same day, the plaintiffs\\n\\nresponded to the motion to dismiss. A week later, in light of confusion among the parties\\n\\nconcerning what constituted the operative complaint after the transfer to the Eastern\\n\\nDistrict of Virginia, the court ordered the plaintiffs to file the Consolidated Complaint. It\\n\\nwas filed on September 15, 2017.\\n\\n b.\\n\\n The Consolidated Complaint named as defendants Holder, Donahoe, and the John\\n\\nDoe agents. Notably, it did not name the United States as a defendant. It alleged the\\n\\nfollowing claims: a First Amendment claim pursuant to Bivens v. Six Unknown Federal\\n\\nNarcotics Agents, 403 U.S. 388 (1971) (Count 1); a Fourth Amendment Bivens claim\\n\\n(Count 2); violations of the Electronic Communications Privacy Act (the “ECPA”)\\n\\n(Count 3), the Stored Communications Act (the “SCA”) (Count 4), the Computer Fraud\\n\\nand Abuse Act (the “CFAA”) (Count 5), the Foreign Intelligence Surveillance Act\\n\\n(“FISA”) (Count 6), and the Virginia Computer Crimes Act (Count 7); plus common law\\n\\ntrespass (Count 8).\\n\\n The pending motion to dismiss the Consolidated Complaint was fully briefed by\\n\\nSeptember 18, 2017, and the district court conducted a hearing on the dismissal motion\\n\\n\\n\\n 15\\n\\non September 22, 2017. During the hearing, the lawyers thoroughly argued the motion to\\n\\ndismiss. The court also inquired about discovery issues:\\n\\n THE COURT: [T]here still are these John Does out there, and you still, I\\n believe, have matters pending, or do you not, before [the magistrate judge]\\n in terms of discovery requests?\\n\\n PLAINTIFFS’ COUNSEL: I don’t believe we do. I think he denied with\\n permission for us to re-raise any issues if there was a problem.\\n\\nSee Attkisson v. Holder, No. 1:17-cv-00364 at 20-21 (E.D. Va. Oct. 16, 2017), ECF No.\\n\\n127 (transcript of September 22 hearing). The court “strongly suggest[ed]” that the\\n\\nplaintiffs’ lawyers “start pursuing your discovery about that [USPS] IP address.” Id. at\\n\\n21. The court then entered an order dismissing Counts 7 and 8 of the Consolidated\\n\\nComplaint with prejudice, but held the remainder of the dismissal motion in abeyance.\\n\\nNotably, the order observed that, although the United States had previously been named\\n\\nas a defendant, “it was not named as a defendant in the Consolidated Complaint.” See\\n\\nAttkisson v. Holder, No. 1:17-cv-00364 at 1 (E.D. Va. Sept. 22, 2017), ECF No. 122.\\n\\nThe plaintiffs did not seek reconsideration of that order.\\n\\n c.\\n\\n Meanwhile, the parties filed a joint discovery plan (for which they had jointly\\n\\nobtained a brief extension), which the magistrate judge approved on September 25, 2017.\\n\\nThat plan retained the final discovery deadline of January 12, 2018. On September 27,\\n\\n2017, the plaintiffs noticed their first deposition in the Eastern District of Virginia — six\\n\\nmonths after the litigation was transferred there. That notice again sought to depose a\\n\\nUSPS representative and requested various records from that agency. The topics\\n\\n\\n 16\\n\\nspecified in the notice were similar to those identified in the plaintiffs’ previous\\n\\ndiscovery motion, litigated in August 2017. It retained a request for “any and all records,\\n\\nlogs, or other form of identification material” that “will or may assist in identifying” any\\n\\nperson who had access to the listed IP addresses. See Attkisson v. Holder, No. 1:17-cv-\\n\\n00364 at 3 (E.D. Va. Sept. 27, 2017), ECF No. 125. According to the briefs, the\\n\\nplaintiffs deposed a USPS representative in mid-October 2017.\\n\\n On October 27, 2017, Holder and Donahoe — the two remaining named\\n\\ndefendants — moved to stay discovery until the district court resolved the balance of\\n\\ntheir motion to dismiss the Consolidated Complaint. Holder and Donahoe emphasized\\n\\nthat, if they prevailed on qualified immunity, they were entitled to immunity from suit,\\n\\nincluding discovery. They also represented to the court that the plaintiffs had recently\\n\\nserved wide-ranging document subpoenas on nine federal agencies and departments,\\n\\nincluding the FBI, the ATF, the Central Intelligence Agency (the “CIA”), and the NSA.\\n\\nThe defendants submitted as support the plaintiffs’ subpoena to the NSA, which included,\\n\\ninter alia, a request for all records relating to “Sharyl Attkisson’s and/or CBS reporting\\n\\non Benghazi” between 2004 and 2017. See Attkisson v. Holder, No. 1:17-cv-00364 at 12\\n\\n(E.D. Va. Oct. 27, 2017), ECF No. 130-1. As an alternative to their motion to stay\\n\\ndiscovery, the defendants sought a protective order.\\n\\n d.\\n\\n Shortly thereafter, on November 1, 2017, the district court dismissed with\\n\\nprejudice Counts 1 through 6 of the Consolidated Complaint as to Holder and Donahoe.\\n\\nSee Attkisson v. Holder, 1:17-cv-00364 (E.D. Va. Nov. 1, 2017), ECF No. 133 (the “First\\n\\n 17\\n\\nDismissal”). The court also dismissed with prejudice Count 4 of the Consolidated\\n\\nComplaint as to all parties. With the filing of the First Dismissal, the only pending\\n\\naspects of the litigation were Counts 1, 2, 3, 5, and 6, as to the John Doe agents. In the\\n\\ncircumstances, the First Dismissal also denied as moot Holder and Donahoe’s motion to\\n\\nstay discovery.\\n\\n On the very day the district court filed the First Dismissal, the plaintiffs moved to\\n\\nagain name the United States as a defendant, asserting that they had inadvertently omitted\\n\\nto name the United States in the Consolidated Complaint. The court denied that motion\\n\\ntwo weeks later, on November 16, 2017, ruling that the plaintiffs had failed to show good\\n\\ncause and that “[a]llowing plaintiffs to add a defendant back into the litigation at this\\n\\nstage would lead to a regression of the litigation and impair judicial economy.” See\\n\\nAttkisson v. Holder, No. 1:17-cv-00364, at 4 (E.D. Va. Nov. 16, 2017), ECF No. 140.\\n\\nThe court emphasized that the plaintiffs had not sought relief when the court’s September\\n\\n22, 2017 order referenced the omission of the United States as a defendant. The court\\n\\nobserved, however, that the plaintiffs were entitled to pursue their remaining claims\\n\\nagainst the John Doe agents. 3\\n\\n\\n\\n\\n 3\\n More than a month later, on December 26, 2017, the plaintiffs filed another\\ncomplaint against the United States in the Eastern District of Virginia. See Attkisson v.\\nUnited States, No. 1:17-cv-01474 (E.D. Va. Dec. 26, 2017). In April 2018, the district\\ncourt dismissed that complaint for lack of service, pursuant to Federal Rule of Civil\\nProcedure 4(m) (requiring dismissal of any defendant not served within ninety days after\\ncomplaint is filed, absent good cause).\\n\\n\\n 18\\n\\n Accordingly, the plaintiffs continued to pursue discovery, including seeking\\n\\ninformation from non-party Verizon entities. On December 1, 2017, the magistrate judge\\n\\ngranted the plaintiffs’ request to vacate the existing scheduling order and authorized the\\n\\nplaintiffs to “substitute new parties for the John Doe defendants by no later than January\\n\\n5, 2018, at 10:00 a.m.” See Attkisson v. Holder, No. 1:17-cv-00364, at 1 (E.D. Va. Dec.\\n\\n1, 2017), ECF No. 145. The judge explained: “Once the substituted parties have been\\n\\nserved and make an appearance in this case, a new scheduling order will be entered.” Id.\\n\\n Two weeks later, the plaintiffs sought to extend the substitution deadline. That\\n\\nmotion was granted and the deadline for naming the John Doe agents was extended to\\n\\nFebruary 5, 2018. In its order, the district court emphasized that the John Doe agents\\n\\nwere “the only defendants remaining in this civil action,” and explicitly advised that this\\n\\norder constituted the plaintiffs’ final extension “because the interests of judicial economy\\n\\nand fairness to third parties and potential future defendants dictate that plaintiffs move\\n\\nforward with this litigation in as timely a fashion as possible.” See Attkisson v. Holder,\\n\\nNo. 1:17-cv-00364, at 1-2 (E.D. Va. Dec. 29, 2017), ECF No. 151.\\n\\n e.\\n\\n On January 5, 2018, Verizon Virginia LLC (“Verizon”) sought a protective order\\n\\nagainst the plaintiffs’ pending discovery requests. Verizon represented to the court that\\n\\nthe plaintiffs had first sought third-party discovery from Verizon on October 16, 2017,\\n\\nrequesting records related to purported surveillance of the Attkissons. Verizon had\\n\\nresponded that it possessed no documents responsive to that request. During the next two\\n\\nmonths, the plaintiffs served five additional discovery requests on Verizon, some of\\n\\n 19\\n\\nwhich did not match the notices the plaintiffs filed with the court, and most of which\\n\\nwere broader in scope than the October 16 request. For example, a discovery request of\\n\\nDecember 7, 2017, sought to depose a Verizon representative regarding “Verizon’s cyber\\n\\nsecurity operations between 2010 and 2014,” including “the relationship between\\n\\nVerizon and the U.S. Intelligence Community.” See Attkisson v. Holder, No. 1:17-cv-\\n\\n00364 at 2 (E.D. Va. Dec. 7, 2017), ECF No. 147.\\n\\n On the very day that Verizon sought the protective order — January 5, 2018 — the\\n\\nplaintiffs filed a motion to compel discovery from the various third-party government\\n\\nentities they had served with document subpoenas, including the FBI, the CIA, and the\\n\\nNSA. Importantly, the January 5 motion to compel was the first — and only — effort to\\n\\ncompel discovery that the plaintiffs pursued in the Eastern District of Virginia. 4\\n\\n A week later, on January 12, 2018, the magistrate judge conducted a hearing on\\n\\nVerizon’s protective order request and the plaintiffs’ motion to compel. The judge first\\n\\naddressed Verizon’s motion, which it granted in part and denied in part, addressing each\\n\\ndisputed request individually. As part of the approved requests, the judge authorized the\\n\\ndeposition of Todd Haskell, the Verizon technician who made a service call to the\\n\\nAttkissons’ home on January 1, 2013. See Attkisson v. Holder, No. 1:17-cv-00364 at 6,\\n\\n17 (E.D. Va. Jan. 24, 2018), ECF No. 173 (transcript of January 12 hearing). The judge\\n\\n\\n\\n\\n 4\\n The plaintiffs filed another motion to compel in February 2018, after their\\nAmended Complaint was filed. They soon withdrew that motion to compel.\\n\\n\\n 20\\n\\nalso approved a deposition of a Verizon corporate representative, either Haskell or some\\n\\nother designated employee.\\n\\n Turning to the plaintiffs’ motion to compel, the magistrate judge expressed\\n\\nskepticism concerning the plaintiffs’ need for documents dating back to 2004, and\\n\\ncriticized the requested discovery as overly broad. The judge emphasized to the lawyers\\n\\nthat they should focus on “identification discovery” rather than “liability discovery,” and\\n\\nadvised that “a new scheduling order” would be issued if “Doe defendants” were\\n\\nsuccessfully named. See Attkisson v. Holder, No. 1:17-cv-00364 at 24 (E.D. Va. Jan. 24,\\n\\n2018), ECF No. 173. The judge explained that, with the Does being the only remaining\\n\\ndefendants, identification discovery had to come first, because “the party involved in the\\n\\nlawsuit . . . needs to be involved in that discovery.” Id. at 25. The plaintiffs answered\\n\\nthat they had “tried to focus [their] discovery” on “attribution.” Id. In response, the\\n\\njudge advised that their requests did not reflect such a focus and, in fact, were so\\n\\n“generic” and of such “astounding” scope that it was difficult to rule on them. Id. at 26-\\n\\n27.\\n\\n Nevertheless, the magistrate judge instructed the parties to proceed with discovery\\n\\nfor the purpose of “identify[ing] the Doe defendants.” Id. at 35. No discovery outside\\n\\nthe identification purpose was permitted. That said, the judge required “more specific\\n\\ninformation” before he could grant a motion to compel. Id. at 36. The judge thus denied\\n\\nthe motion to compel without prejudice. As the hearing concluded, the judge instructed\\n\\nthe plaintiffs’ lawyers “to focus on this and get it done as quickly as possible” to\\n\\n“hopefully meet the February 5 deadline” for naming the John Doe defendants. Id. at 37.\\n\\n 21\\n\\n f.\\n\\n Despite those warnings, the plaintiffs made no motions or requests of the district\\n\\ncourt between the January 12, 2018 hearing and the February 5, 2018 deadline for\\n\\nnaming the John Doe defendants. That is, for twenty-three days the plaintiffs neither\\n\\nsought the court’s aid with discovery nor requested an extension of the deadline. And the\\n\\nplaintiffs’ lawyers later admitted to the court that they had not submitted any revised\\n\\ndiscovery requests to the government agencies until January 28, 2018 — just one week\\n\\nbefore the deadline. See Attkisson v. Holder, No. 1:17-cv-00364 at 2 (E.D. Va. Feb. 13,\\n\\n2018), ECF No. 176. Verizon has since represented to this Court that the plaintiffs did\\n\\nnot take the depositions of the two Verizon employees that the magistrate judge\\n\\nauthorized at the January 12 hearing. See Br. of Verizon Defendants-Appellees 3. 5\\n\\n Instead, on February 5, 2018, the plaintiffs purported to file their Amended\\n\\nComplaint. The plaintiffs were only authorized to amend their complaint by substitution\\n\\nof named parties for the John Doe defendants, as ordered by the district court.\\n\\nNevertheless, the Amended Complaint failed to substitute any named parties for the John\\n\\nDoe agents. It again identified as defendants the United States and unknown named\\n\\nagents of the DOJ, the USPS, and the United States. The Amended Complaint also added\\n\\n 5\\n In the proceedings below and on appeal, the plaintiffs have maintained that they\\nwere “permitted only to conduct a grand total of one deposition,” which is false. See Br.\\nof Appellants 48. It appears, however, that the plaintiffs never deposed a Verizon\\nrepresentative, despite receiving the magistrate judge’s authorization. See Attkisson v.\\nHolder, No. 1:17-cv-00364 at 2 (E.D. Va. Apr. 23, 2018), ECF No. 207 (plaintiffs’\\nrepresentation that “there has been exactly one deposition in this case” of a USPS\\nrepresentative).\\n\\n\\n 22\\n\\nas new defendants the FBI and the Verizon defendants. Additionally, it realleged Counts\\n\\n4, 7, and 8, which the court had already dismissed with prejudice. The named defendants\\n\\n— that is, the United States, the FBI, and the Verizon defendants — promptly moved in\\n\\nMarch 2018 to dismiss the Amended Complaint.\\n\\n On May 15, 2018, the district court granted the motions of the named defendants\\n\\nto dismiss the Amended Complaint and disposed of the plaintiffs’ claims. See Attkisson\\n\\nv. Holder, No. 1:17-cv-00364 (E.D. Va. May 15, 2018), ECF No. 213 (the “Second\\n\\nDismissal”). The Second Dismissal ruled that the plaintiffs had violated several of the\\n\\ncourt’s earlier orders with regard to amending the complaint. By way of example, the\\n\\nAmended Complaint added defendants who were not appropriate substitutes for the John\\n\\nDoe agents and simply ignored the court’s prior order denying leave to name the United\\n\\nStates as a defendant.\\n\\n Although the plaintiffs’ procedural violations sufficed to dismiss the Amended\\n\\nComplaint, the court provided additional explanations for its rulings. First, the court\\n\\ndismissed the resurrected claims against the United States because it had already denied\\n\\nleave to rename the United States as a defendant. Next, the court dismissed the claims\\n\\nagainst the FBI because no such lawsuit was authorized by any of the statutory provisions\\n\\nunder which the plaintiffs sought to sue the Bureau. See Second Dismissal 5 (citing\\n\\nBlackmar v. Guerre, 342 U.S. 512 (1952)). The court dismissed the claims against the\\n\\nVerizon defendants as procedurally barred and for failure to state a plausible claim to\\n\\nrelief. Finally, the court dismissed the claims against the John Doe agents because, after\\n\\n\\n\\n 23\\n\\nmore than three years of litigation, those unnamed agents had never been identified or\\n\\nserved, and the plaintiffs had “made no substantial progress” in that regard. Id. at 6 n.3.\\n\\n Because of the plaintiffs’ multitude of procedural violations, and because the\\n\\ndistrict court decided that further amendments “would be futile,” the court declined to\\n\\nauthorize the plaintiffs to again amend their complaint. See Second Dismissal 5-6.\\n\\nAccordingly, the court entered final judgment in favor of the defendants.\\n\\n The plaintiffs have timely noted this appeal. They challenge only the dismissal of\\n\\ntheir Fourth Amendment Bivens claim with respect to Holder and Donahoe, the dismissal\\n\\nof their ECPA claim with respect to those defendants, and the district court’s dismissal of\\n\\nthe Amended Complaint — including the claims against the John Doe agents and the\\n\\nVerizon defendants — with its concomitant denial of leave to further amend their\\n\\ncomplaint. We possess appellate jurisdiction pursuant to 28 U.S.C. § 1291.\\n\\n\\n\\n II.\\n\\n This Court reviews de novo a dismissal under Federal Rule of Civil Procedure\\n\\n12(b)(6). See Nemet Chevrolet, Ltd. v. Consumeraffairs.com, Inc., 591 F.3d 250, 253\\n\\n(4th Cir. 2009). In so doing, we accept all well-pleaded facts as true and draw all\\n\\nreasonable inferences in favor of the plaintiffs. Id. That said, we “need not accept legal\\n\\nconclusions couched as facts or unwarranted inferences, unreasonable conclusions, or\\n\\narguments.” Wag More Dogs, LLC v. Cozart, 680 F.3d 359, 365 (4th Cir. 2012) (internal\\n\\nquotation marks omitted). Viewing the complaint in that light, it must provide “sufficient\\n\\nfactual matter, accepted as true, to state a claim to relief that is plausible on its face.’”\\n\\n 24\\n\\nAshcroft v. Iqbal, 556 U.S. 662, 678 (2009) (quoting Bell Atl. Corp. v. Twombly, 550 U.S.\\n\\n544, 570 (2007)).\\n\\n By contrast, we review the dismissal of a complaint for violation of court orders\\n\\nfor abuse of discretion. See Simpson v. Welch, 900 F.2d 33, 35-36 (4th Cir. 1990). We\\n\\nlikewise review for abuse of discretion a district court’s denial of leave to amend a\\n\\ncomplaint, see Scott v. Family Dollar Stores, Inc., 733 F.3d 105, 112 (4th Cir. 2013), and\\n\\nthe dismissal of a defendant for lack of service, see Shao v. Link Cargo (Taiwan) Ltd.,\\n\\n986 F.2d 700, 708 (4th Cir. 1993).\\n\\n\\n\\n III.\\n\\n The plaintiffs present three challenges to the district court’s rulings. First, they\\n\\ncontend that the court erred in dismissing their Fourth Amendment Bivens claim against\\n\\nAttorney General Holder and Postmaster Donahoe as a matter of law. Second, they\\n\\ndispute the court’s dismissal of their ECPA claim against Holder and Donahoe. Third,\\n\\nthe plaintiffs contest the court’s dismissal of the John Doe agents and Verizon defendants\\n\\non procedural grounds, along with its simultaneous denial of leave to further amend their\\n\\ncomplaint. We address these contentions in turn.\\n\\n A.\\n\\n The plaintiffs first contest the district court’s dismissal of their Fourth Amendment\\n\\nBivens claim against Attorney General Holder and Postmaster Donahoe for failure to\\n\\npresent a cognizable claim under the Supreme Court’s controlling precedent. In the\\n\\nConsolidated Complaint, the plaintiffs allege that Holder, Donahoe, and the John Doe\\n\\n 25\\n\\nagents violated their Fourth Amendment rights by unlawfully surveilling the plaintiffs\\n\\nthrough their electronic devices. They seek damages for that alleged injury pursuant to\\n\\nthe Court’s ruling in Bivens v. Six Unknown Federal Narcotics Agents, which authorized\\n\\ndamages for certain constitutional violations by federal officials. See 403 U.S. 388, 395\\n\\n(1971). In its First Dismissal, the district court rejected that claim as to Holder and\\n\\nDonahoe because, under more recent precedent, the plaintiffs failed to state a viable\\n\\nBivens claim against those named defendants. We agree.\\n\\n The Supreme Court’s 2017 decision in Ziglar v. Abbasi narrowed the\\n\\ncircumstances in which a plaintiff may successfully state a claim under the principles\\n\\nestablished in Bivens. See 137 S. Ct. 1843, 1857-58 (2017). As the Court explained in\\n\\nAbbasi, the Bivens decision created an implied cause of action, permitting civil suits for\\n\\ndamages for constitutional violations by federal officials where Congress had not\\n\\nindicated that such a remedy was foreclosed. Id. at 1854. Bivens itself authorized\\n\\ndamages in a situation involving an unlawful search and arrest in the plaintiff’s home.\\n\\nSee 403 U.S. at 389. In the years since Bivens, the Court has recognized implied causes\\n\\nof action in two additional situations: for the violation of a prisoner’s Eighth Amendment\\n\\nright to adequate medical care, and for a federal employee’s Fifth Amendment due\\n\\nprocess right against gender discrimination. See Abbasi, 137 S. Ct. at 1854-55 (citing\\n\\nCarlson v. Green, 446 U.S. 14 (1980); Davis v. Passman, 442 U.S. 228 (1979)). 6 In\\n\\n\\n 6\\n The Supreme Court may have recognized a fourth Bivens context in Farmer v.\\nBrennan, which sustained a prisoner’s Eighth Amendment claim for damages against\\nfederal prison officials for failure to protect. See 511 U.S. 825, 823-49 (1994). Although\\n(Continued)\\n 26\\n\\nAbbasi, the Court clarified the inquiry as to whether a cognizable Bivens remedy exists\\n\\nwith regard to a specific type of alleged official misconduct. First, a court must\\n\\ndetermine whether the claim “presents a new Bivens context.” Id. at 1859. If it does, the\\n\\ncourt must assess whether any “special factors counsel[] hesitation” in recognizing a new\\n\\nremedy “in the absence of affirmative action by Congress.” Id. at 1857.\\n\\n A Bivens claim arises in a “new context” if the case differs “in a meaningful way\\n\\nfrom previous Bivens cases decided by” the Supreme Court. See Abbasi, 137 S. Ct. at\\n\\n1859. Examples of such meaningful differences include:\\n\\n the rank of the officers involved; the constitutional right at issue; the\\n generality or specificity of the official action; the extent of judicial\\n guidance as to how an officer should respond to the problem or emergency\\n to be confronted; the statutory or other legal mandate under which the\\n officer was operating; the risk of disruptive intrusion by the Judiciary into\\n the function of other branches; or the presence of potential special factors\\n that previous Bivens cases did not consider.\\n\\nId. at 1860. Although Bivens itself approved a remedy for an alleged Fourth Amendment\\n\\nviolation, we agree with the district court that the claim asserted by the plaintiffs here\\n\\npresents a “new Bivens context.”\\n\\n The plaintiffs’ Fourth Amendment Bivens claim against Holder and Donahoe\\n\\ndiffers meaningfully from the claim raised in Bivens in numerous ways that are material\\n\\n\\n\\n\\nthe Abbasi Court did not include Farmer in its list of recognized Bivens contexts, the\\nThird Circuit recently held that a prisoner’s failure-to-protect claim did not present a new\\nBivens context in light of Farmer. See Bistrian v. Levi, 912 F.3d 79, 90-92 (3d Cir.\\n2018). Because the plaintiffs’ claim here is entirely distinct from that raised in Farmer,\\nwe need not and do not decide whether such a claim would present a new Bivens context.\\n\\n\\n 27\\n\\nunder Abbasi. First, Holder and Donahoe held much higher ranks than the line-level FBI\\n\\nagents sued in Bivens. Second, a claim based on unlawful electronic surveillance\\n\\npresents wildly different facts and a vastly different statutory framework from a\\n\\nwarrantless search and arrest. Finally, the plaintiffs seek to hold high-level officials\\n\\naccountable for what they themselves frame as policy-level decisions to target internal\\n\\nleaks to the media. In these circumstances, the plaintiffs’ claim against Holder and\\n\\nDonahoe assuredly presents a “new Bivens context.”\\n\\n Moreover, the plaintiffs’ Fourth Amendment Bivens claim fails at the second step\\n\\ndescribed in Abbasi. Various “special factors” identified in the Abbasi decision counsel\\n\\nhesitation against recognizing a Bivens claim here. See 137 S. Ct. at 1857. It is\\n\\nsufficient, however, to note that Congress has legislated extensively in the area of\\n\\nelectronic surveillance and intrusions into electronic devices without authorizing\\n\\ndamages for a Fourth Amendment violation in such circumstances. Indeed, Congress has\\n\\ncreated several private causes of actions under various statutes governing the surveillance\\n\\nand the integrity of personal computing devices, including the SCA, FISA, and the\\n\\nCFAA. That legislation suggests that Congress’s “failure to provide a damages remedy”\\n\\nfor Fourth Amendment violations in similar factual circumstances is “more than\\n\\ninadvertent,” and strongly counsels hesitation before creating such a remedy ourselves.\\n\\nSee Abbasi, 137 S. Ct. at 1862. Indeed, “if there is an alternative remedial structure\\n\\npresent in a certain case, that alone may limit the power of the Judiciary to infer a new\\n\\nBivens cause of action.” Id. at 1858; see also Schweiker v. Chilicky, 487 U.S. 412, 423\\n\\n(1988) (same).\\n\\n 28\\n\\n In these circumstances, we discern “sound reasons to think Congress might doubt\\n\\nthe efficacy or necessity of a damages remedy as part of the system for enforcing the law\\n\\nand correcting a wrong,” and we are therefore obliged to “refrain from creating the\\n\\nremedy.” See Abbasi, 137 S. Ct. at 1858. Accordingly, we are satisfied to affirm the\\n\\ndistrict court’s dismissal of the plaintiffs’ Fourth Amendment Bivens claim with respect\\n\\nto Holder and Donahoe.\\n\\n B.\\n\\n By way of their second appellate contention, the plaintiffs maintain that the district\\n\\ncourt erred in rejecting their ECPA claim as part of the First Dismissal. The plaintiffs\\n\\nassert that Holder and Donahoe violated the ECPA’s prohibition on the unauthorized\\n\\ninterception and disclosure of wire, oral, or electronic communications, codified at 18\\n\\nU.S.C. § 2511. Section 2511 provides that\\n\\n any person who — (a) intentionally intercepts, endeavors to intercept, or\\n procures any other person to intercept or endeavor to intercept, any wire,\\n oral or electronic communication; (b) intentionally uses, endeavors to use,\\n or procures any other person to use or endeavor to use any electronic,\\n mechanical, or other device to intercept any oral communication when\\n [certain undisputed elements are met]; (c) intentionally discloses, or\\n endeavors to disclose, to any other person the contents of any wire, oral, or\\n electronic communication, knowing or having reason to know that the\\n information was obtained through the interception of a wire, oral, or\\n electronic communication in violation of this subsection [has violated the\\n ECPA, unless authorized by law as detailed elsewhere in the statute].\\n\\nSpecifically, the Consolidated Complaint alleges that Holder and Donahoe procured\\n\\ngovernment agents to intercept the plaintiffs’ electronic communications. The plaintiffs\\n\\npursued that claim under the ECPA’s private right of action, which provides that\\n\\n\\n\\n 29\\n\\n any person whose wire, oral, or electronic communication is intercepted,\\n disclosed, or intentionally used in a violation of this chapter may in a civil\\n action recover from the person or entity, other than the United States, which\\n engaged in that violation such relief as may be appropriate.\\n\\nSee 18 U.S.C. § 2520. Comparing § 2511 and § 2520, the district court determined that\\n\\nthe cause of action authorized by § 2520 does not extend to persons who procured\\n\\nanother to intercept, disclose, or intentionally use a covered communication. Rather, the\\n\\ncourt concluded that a suit under § 2520 may only target an individual who directly\\n\\nintercepted, disclosed, or used such a communication in violation of § 2511.\\n\\n On appeal, the plaintiffs challenge the district court’s interpretation and argue that\\n\\n§ 2520 is better read to permit civil suits with regard to any violation of § 2511. We\\n\\ndecline to address that interpretive issue, however, because we agree with the\\n\\nGovernment that, even if § 2520 supports a civil ECPA claim for procurement, Holder\\n\\nand Donahoe are entitled to qualified immunity. 7\\n\\n Qualified immunity protects government officials from civil liability and suit\\n\\n“insofar as their conduct does not violate clearly established statutory or constitutional\\n\\nrights of which a reasonable person would have known.” See Harlow v. Fitzgerald, 457\\n\\nU.S. 800, 818 (1982). To overcome an official’s claim of qualified immunity, the\\n\\nplaintiff must show: “(1) that the official violated a statutory or constitutional right, and\\n\\n 7\\n The district court did not premise its dismissal ruling on qualified immunity, but\\nHolder and Donahoe raised that defense below and we are entitled to affirm on any\\nground fairly presented in the record. See Attkisson v. Holder, No. 1:17-cv-00364, at 19\\n(E.D. Va. Aug. 9, 2017), ECF No. 100 (defendants invoking qualified immunity); see\\nalso United States v. Smith, 395 F.3d 516, 519 (4th Cir. 2005) (confirming that we may\\naffirm “on any grounds apparent from the record”).\\n\\n\\n 30\\n\\n(2) that the right was clearly established at the time of the challenged conduct.” See\\n\\nAshcroft v. al-Kidd, 563 U.S. 731, 735 (2011) (internal quotation marks omitted). A\\n\\ncourt need not address those inquiries in sequence, but instead may exercise its “sound\\n\\ndiscretion” in deciding which issue to first address. See Pearson v. Callahan, 555 U.S.\\n\\n223, 236 (2009). The official is entitled to qualified immunity if either prong is not\\n\\nsatisfied. Id. at 244-45.\\n\\n Assessing the plaintiffs’ ECPA claim, we conclude that, to the extent Holder and\\n\\nDonahoe procured any wrongful interception, use, or disclosure of the plaintiffs’\\n\\nelectronic communications, they did not violate a clearly established right. To show a\\n\\nclearly established right, a plaintiff must identify existing precedent that “placed the\\n\\nstatutory or constitutional question beyond debate.” See al-Kidd, 563 U.S. at 741. This\\n\\nthe plaintiffs have failed to do. Compare Peavy v. WFAA-TV, Inc., 221 F.3d 158, 169\\n\\n(5th Cir. 2000) (ruling that § 2520 only authorizes suits based on “illegal interception,\\n\\ndisclosure, or use, and not to procuring interception by another”), with Lonegan v. Hasty,\\n\\n436 F. Supp. 2d 419, 427-28 (E.D.N.Y. 2006) (concluding that § 2520 permits suits\\n\\nbased on procurement).\\n\\n Whatever our view of the procurement issue, the lack of settled precedent\\n\\nsupporting the plaintiffs’ ECPA claim demonstrates that Holder and Donahoe are now\\n\\nentitled to qualified immunity. See Abbasi, 137 S. Ct. at 1868 (“When the courts are\\n\\ndivided on an issue so central to the cause of action alleged, a reasonable official lacks\\n\\n\\n\\n\\n 31\\n\\nthe notice required before imposing liability.”). Consequently, we affirm the district\\n\\ncourt’s dismissal of the ECPA claim with regard to Holder and Donahoe. 8\\n\\n C.\\n\\n The plaintiffs’ third and final appellate contention challenges the district court’s\\n\\nSecond Dismissal. More specifically, the plaintiffs object to the dismissal of their claims\\n\\nagainst the Verizon defendants and the John Doe agents — which they argue should\\n\\nsurvive the dismissal of their claims against Holder and Donahoe — as well as the court’s\\n\\ndenial of leave to further amend their complaint.\\n\\n The district court dismissed the remaining defendants and denied the plaintiffs\\n\\nleave to further amend their complaint based on similar reasoning. Put simply, the court\\n\\nwas dissatisfied with the plaintiffs’ lack of progress in pursuing their claims after more\\n\\nthan three years of litigation, and their lack of respect for court orders. The court\\n\\nobserved that the plaintiffs had failed to identify or serve any of the John Doe agents,\\n\\neven after receiving multiple extensions to the court’s deadline. Indeed, the plaintiffs had\\n\\nmade little or no progress in that regard, despite filing five complaints (not counting two\\n\\ncomplaints that were replaced with corrected versions).\\n\\n Moreover, the Amended Complaint contravened the court’s prior orders and the\\n\\nFederal Rules of Civil Procedure in multiple ways:\\n\\n\\n 8\\n In their appellate brief, the plaintiffs suggest — apparently for the first time —\\nthat Holder and Donahoe “might” have directly intercepted, used, or disclosed the\\nplaintiffs’ electronic communications. See Br. of Appellants 33 n.6. The Consolidated\\nComplaint, however, fails to support that idle speculation or reflect such a claim.\\n\\n\\n 32\\n\\n • The Amended Complaint failed to comply with the court’s order to\\n substitute named parties for the John Doe agents and instead retained\\n the Doe defendants while adding new defendants;\\n\\n • The plaintiffs had leave of court to amend their complaint solely to\\n name the John Doe agents and violated that leave by adding new\\n defendants;\\n\\n • The plaintiffs never sought additional leave to amend their complaint\\n nor challenged the leave they were granted;\\n\\n • The new defendants included the United States, despite the court’s\\n prior order denying leave to rename the United States as a defendant;\\n and\\n\\n • The Amended Complaint attempted to resurrect several claims that\\n the court had already dismissed with prejudice.\\n\\nIn discussing those procedural defects, the court emphasized its warnings to the plaintiffs\\n\\nthat the February 5, 2018 deadline was necessary to avoid prejudicing the defendants (or\\n\\npotential future defendants), and to protect the interests of judicial economy. Those\\n\\nconcerns, as the court explained, also motivated the Second Dismissal.\\n\\n The court concluded that further amendment to the complaint would, in any event,\\n\\nbe futile, because the claims against the FBI had no statutory basis and the claims against\\n\\nthe Verizon defendants failed to state any plausible claim to relief. With regard to the\\n\\nJohn Doe agents, the court ruled that, given the lack of “substantial progress in\\n\\nidentifying them,” the time had come “to end this litigation against them as well, and for\\n\\nthis reason, the claims against them are also dismissed.” See Second Dismissal 6 n.3.\\n\\n On appeal, the plaintiffs contest only the dismissal of the Verizon defendants and\\n\\nthe John Doe agents, as well as the district court’s denial of leave to further amend their\\n\\ncomplaint. Despite its detailed discussion in the Second Dismissal of the procedural\\n\\n 33\\n\\ndefects of the Amended Complaint, the court did not specify the rules of procedure that\\n\\nprovided the bases for its rulings. Nevertheless, we are entitled to affirm “on any\\n\\ngrounds supported by the record.” See Kerr v. Marshall Univ. Bd. of Governors, 824\\n\\nF.3d 62, 75 n.13 (4th Cir. 2016). And we are entirely satisfied that the Amended\\n\\nComplaint was properly subject to dismissal pursuant to Rule 41(b). With respect to the\\n\\nJohn Does, the claims against those unknown defendants were subject to dismissal under\\n\\nRule 4(m), which requires the dismissal of a defendant who remains unserved ninety days\\n\\nafter a complaint is filed, absent good cause. Accordingly, the court did not abuse its\\n\\ndiscretion in dismissing the Amended Complaint and denying the plaintiffs leave to\\n\\nfurther amend their complaint. We will expand on those rulings.\\n\\n 1.\\n\\n As the Supreme Court has recognized, a court has the “inherent power” to dismiss\\n\\nan action for want of prosecution. See Link v. Wabash R. Co., 370 U.S. 626, 630 (1962).\\n\\nAlthough Rule 41(b) of the Federal Rules of Civil Procedure provides an “explicit basis\\n\\nfor this sanction,” it is not the source of that inherent power. See Doyle v. Murray, 938\\n\\nF.2d 33, 34 (4th Cir. 1991). Rather, that judicial power derives from “the control\\n\\nnecessarily vested in courts to manage their own affairs so as to achieve the orderly and\\n\\nexpeditious disposition of cases.” See Link, 370 U.S. at 630-31. As provided by Rule\\n\\n41(b), such involuntary dismissals are appropriate when “the plaintiff fails to prosecute or\\n\\nto comply with [the Federal Rules of Civil Procedure] or a court order.” Given the\\n\\ninherent judicial authority to make such dismissals, a court may, in appropriate\\n\\n\\n\\n 34\\n\\ncircumstances, enter such a dismissal sua sponte, even absent advance notice of “the\\n\\npossibility of dismissal.” See Link, 370 U.S. at 632-33.\\n\\n That said, recognizing the severity of dismissal as a sanction, we have identified\\n\\nfour criteria that guide a district court’s discretion in dismissing a case under Rule 41(b).\\n\\nSuch an exercise should weigh: “(1) the plaintiff’s degree of personal responsibility; (2)\\n\\nthe amount of prejudice caused the defendant; (3) the presence of a drawn out history of\\n\\ndeliberately proceeding in a dilatory fashion; and (4) the effectiveness of sanctions less\\n\\ndrastic than dismissal.” See Hillig v. C.I.R., 916 F.2d 171, 174 (4th Cir. 1990). Those\\n\\ncriteria, however, “are not a rigid four-prong test.” See Ballard v. Carlson, 882 F.2d 93,\\n\\n95 (4th Cir. 1989) (Powell, J.). Rather, the propriety of an involuntary dismissal\\n\\nultimately depends on “the facts of each case,” which we review to determine “whether\\n\\nthe trial court exercised sound discretion.” See Reizakis v. Loy, 490 F.2d 1132, 1135 (4th\\n\\nCir. 1974); see also Link, 370 U.S. at 633. 9\\n\\n\\n\\n\\n 9\\n Contrary to the assertion of our dissenting friend, we have never ruled that a\\ndistrict court’s failure to expressly analyze the four factors guiding involuntary dismissals\\nis itself an abuse of discretion. See post at 67. Rather, we have consistently reviewed the\\nfull circumstances of each such dismissal. See Reizakis, 490 F.2d at 1135 (evaluating\\n“the circumstances of this case,” including, inter alia, whether trial court had\\n“consider[ed] measures less drastic than dismissal”). Our approach accords with the\\nSupreme Court’s decision in Link, which emphasized the context-dependent nature of\\nsuch dismissals and affirmed the lower court’s involuntary dismissal based on its implicit\\nconsideration of “all the circumstances” before it. See 370 U.S. at 634-35. In any event,\\nwe are entitled to affirm a judgment where “the outcome is not in doubt.” See Garnett v.\\nRemedi Seniorcare of Va., LLC, 892 F.3d 140, 142 (4th Cir.), cert. denied, 139 S.Ct. 605\\n(2018) (citing Singleton v. Wulff, 428 U.S. 106, 120 (1976)).\\n\\n\\n 35\\n\\n In the circumstances of these proceedings, we are satisfied that the district court\\n\\ndid not abuse its discretion in dismissing the Amended Complaint. This Court has\\n\\npreviously upheld an involuntary dismissal under Rule 41(b) where the plaintiff “failed to\\n\\nrespond to a specific directive from the [trial] court.” See Ballard, 882 F.2d at 95. Our\\n\\nreasoning in Ballard applies directly to the Amended Complaint’s multiple violations of\\n\\nthe Federal Rules and the applicable court orders. To start, the plaintiffs amended their\\n\\ncomplaint beyond the leave authorized, in violation of Rule 15(a)(2) and the court’s order\\n\\nof December 29, 2017. 10 Nor did the plaintiffs even attempt to show good cause for\\n\\nthose additional amendments, which Rule 16(b) requires after the entry of a scheduling\\n\\norder. See Nourison Rug Corp. v. Parvizian, 535 F.3d 295, 298 (4th Cir. 2008) (ruling\\n\\nthat “after the deadlines provided by a scheduling order have passed, the good cause\\n\\nstandard must be satisfied to justify leave to amend the pleadings”). 11 The plaintiffs\\n\\nfailed to substitute named parties for the John Doe agents and retained the John Doe\\n\\ndefendants in the Amended Complaint, in violation of the court’s December 29, 2017\\n\\norder. The plaintiffs also renamed the United States as a defendant, in direct violation of\\n\\nthe court’s order of November 16, 2017. Lastly, the Amended Complaint improperly\\n\\n 10\\n Indeed, because the plaintiffs failed to obtain leave for their various\\namendments, the Amended Complaint was also “without legal effect” and thus “rightly\\ndisallowed” by the district court. See Schmidt v. United States, 749 F.3d 1064, 1069\\n(D.C. Cir. 2014); acc. Angles v. Dollar Tree Stores, 494 F. App’x 326, 329 (4th Cir.\\n2012).\\n 11\\n The only argument pursued by the plaintiffs in the district court to defend their\\naddition of the Verizon defendants in the Amended Complaint was that those entities\\nwere proper substitutes for the John Doe agents. That position was not supported by the\\nplaintiffs’ allegations and was justifiably rejected.\\n\\n\\n 36\\n\\nsought to resurrect Counts 4, 7, and 8 of the Consolidated Complaint, which the court had\\n\\ndismissed with prejudice months earlier.\\n\\n Providing further context for the Second Dismissal, the district court and the\\n\\nmagistrate judge had both repeatedly warned the plaintiffs to focus on identifying the\\n\\nJohn Doe agents prior to the February 5, 2018 deadline. See Ballard, 882 F.2d at 95\\n\\n(considering warning issued by magistrate judge in assessing 41(b) dismissal). Contrary\\n\\nto the view of our dissenting colleague, the record simply fails to show that the plaintiffs\\n\\nacted “diligently” in pursuing that discovery. See post at 43. Rather, they filed a single\\n\\nmotion to compel, which the magistrate judge promptly ruled on. And the magistrate\\n\\njudge then authorized depositions of Verizon employees which the plaintiffs never took.\\n\\nPrior to that motion to compel, there were significant periods of inactivity by the\\n\\nplaintiffs, compounded by (unopposed) extensions sought by the defendants. See Davis\\n\\nv. Williams, 588 F.2d 69, 70-71 (4th Cir. 1978) (sustaining 41(b) dismissal where two-\\n\\nyear litigation reflected “long history of delay” and plaintiff’s counsel “refused to take\\n\\nthe initiative”).\\n\\n This is not a situation where a plaintiff’s lawyer has briefly failed to comply with a\\n\\ncourt’s order without any participation of or blame on his client. Cf. Hillig, 916 F.2d at\\n\\n174 (reversing 41(b) dismissal in part because counsel’s noncompliance spanned only\\n\\nthree months, resulted from miscommunication, and was not known to client); Reizakis,\\n\\n490 F.2d at 1134-35 (reversing 41(b) dismissal because lack of trial preparation resulted\\n\\nfrom miscommunication between retained counsel and local counsel despite plaintiff’s\\n\\nsteps in anticipation of trial). Nor does this litigation involve a pro se or incarcerated\\n\\n 37\\n\\ninmate who had limited opportunities to “follow the progress of his case.” Cf. Doyle, 938\\n\\nF.2d at 35. Courts should — and regularly do — take such realities into account. These\\n\\nplaintiffs were well represented and free to fully prosecute their case.\\n\\n In sum, the plaintiffs contravened multiple rules and court orders while failing to\\n\\nalert the district court to any problems justifying their actions. And they acted in the face\\n\\nof explicit instructions from the court and the magistrate judge. Those circumstances\\n\\nsupport the dismissal with prejudice of their claims under Rule 41(b). See Ballard, 882\\n\\nF.2d at 94-95; acc. Thomas v. Arn, 474 U.S. 140, 147 (1985) (observing that if petitioner\\n\\n“failed to comply with a scheduling order” court “could certainly dismiss the appeal”).12\\n\\nOn this record, we cannot rule that the court abused its discretion in dismissing the\\n\\nAmended Complaint.\\n\\n 2.\\n\\n The foregoing analysis applies equally to the plaintiffs’ claims against the John\\n\\nDoe agents and suffices to affirm the district court’s dismissal thereof. That said, the\\n\\ndismissal of the Doe defendants is also supported by Rule 4(m) of the Federal Rules of\\n\\nCivil Procedure. 13 Rule 4(m) requires the dismissal of defendants who remain unserved\\n\\nninety days after the filing of a complaint unless “the plaintiff shows good cause.” The\\n\\n\\n 12\\n The dismissal of the plaintiffs’ claims is with prejudice except as to the John\\nDoe agents, as explained further herein.\\n 13\\n We are satisfied that the district court implicitly relied on Rule 4(m) in\\ndismissing the John Doe defendants. The Second Dismissal emphasized the plaintiffs’\\nfailure to identify or serve those defendants, and their lack of progress in that regard.\\n\\n\\n 38\\n\\nplaintiffs failed to show good cause in the district court, nor do we discern any on this\\n\\nrecord. As with other procedural dismissals, we review a dismissal under Rule 4(m) for\\n\\nabuse of discretion. See Shao v. Link Cargo (Taiwan) Ltd., 986 F.2d 700, 708 (4th Cir.\\n\\n1993) (reviewing Rule 4(m)’s predecessor — Rule 4(j) — for abuse of discretion).\\n\\n Generally, for purposes of Rule 4(m), “good cause” requires some showing of\\n\\ndiligence on the part of the plaintiffs. Put conversely, good cause generally exists when\\n\\nthe failure of service is due to external factors, such as the defendant’s intentional evasion\\n\\nof service. See Mann v. Castiel, 681 F.3d 368, 374 (D.C. Cir. 2012) (collecting cases and\\n\\ncommentary). While “good cause” is a flexible standard, diligence provides a touchstone\\n\\nfor an appellate court that is reviewing a dismissal under Rule 4(m). See, e.g., Cardenas\\n\\nv. City of Chicago, 646 F.3d 1001, 1007 (7th Cir. 2011) (emphasizing that “the district\\n\\ncourt retained its discretion to hold the Plaintiffs accountable” for their “inaction” by\\n\\n“dismissing the case”); McCurdy v. Am. Bd. of Plastic Surgery, 157 F.3d 191, 196-97 (3d\\n\\nCir. 1998) (affirming Rule 4(m) dismissal where plaintiff did not show diligence in\\n\\ntimely serving defendants and failed to seek extension of time before deadline lapsed).\\n\\n Whatever the minimum requirement for good cause may be, the plaintiffs have\\n\\nfailed to show it. The facts that support the dismissal of the Amended Complaint under\\n\\nRule 41(b) also show the plaintiffs’ lack of diligence for purposes of Rule 4(m). The\\n\\nplaintiffs’ significant periods of inactivity during three full years of litigation, their\\n\\npersistence in unjustifiably broad discovery requests despite repeated admonishments of\\n\\nthe district court and the magistrate judge, and their decisions not to present additional\\n\\ndifficulties with discovery to the court, show a lack of diligence in pursuit of their claims.\\n\\n 39\\n\\nSee Scott v. Hern, 216 F.3d 897, 912 (10th Cir. 2000) (affirming dismissal under Rule\\n\\n4(m) where plaintiffs failed to pursue authorized discovery against unnamed defendants);\\n\\nFigueroa v. Rivera, 147 F.3d 77, 82-83 (1st Cir. 1998) (affirming Rule 4(m) dismissal of\\n\\nJohn Doe defendants after seventeen months during which plaintiffs made no effort to\\n\\nidentify them); Shao, 986 F.2d at 708 (affirming dismissal under Rule 4(m)’s predecessor\\n\\nwhere, after two extensions to service deadline, plaintiff showed no progress).\\n\\n Our good dissenting colleague overstates our precedent by contending that a court\\n\\nmay dismiss a suit for failure to name a John Doe defendant “only ‘if it does not appear\\n\\nthat the true identity of an unnamed party can be discovered through discovery or through\\n\\nintervention by the court.’” See post at 56 (quoting Schiff v. Kennedy, 691 F.2d 196, 198\\n\\n(4th Cir. 1982)). Our decision in Schiff merely explained that “if it does not appear” that\\n\\nthe unnamed party could be identified, then “the court could dismiss the action without\\n\\nprejudice.” See 691 F.2d at 198 (emphasis added). In fact, the Schiff decision repeatedly\\n\\nemphasized that, as to John Doe defendants, the “district court is in a better position than\\n\\nwe now are to ascertain what treatment should be given, and when.” Id. Judge\\n\\nWidener’s fine opinion for the Schiff panel thus deferred to the district court as to\\n\\n“whether the case against Doe should be now permitted to proceed or whether the case at\\n\\nthis stage should be terminated.” Id. We will adhere to that good example and defer to\\n\\nthe wisdom of the district judge in dismissing the John Doe defendants.\\n\\n That said, pursuant to Rule 4(m), and consistent with this Court’s prior treatment\\n\\nof Doe defendants, the dismissal of the John Doe agents must be without prejudice. See\\n\\nFed. R. Civ. P. 4(m) (“If a defendant is not served within 90 days after the complaint is\\n\\n 40\\n\\nfiled, the court . . . must dismiss the action without prejudice against that defendant[.]”);\\n\\nsee also Schiff, 691 F.2d at 198 (“Should the district court persist in its dismissal of Doe\\n\\nwithout further proceedings, the dismissal will be without prejudice.”). That rule flows\\n\\nfrom the principle that a court generally lacks personal jurisdiction over unserved parties.\\n\\nSee, e.g., Koehler v. Dodwell, 152 F.3d 304, 306 (4th Cir. 1998) (“Absent waiver or\\n\\nconsent, a failure to obtain proper service on the defendant deprives the court of personal\\n\\njurisdiction over the defendant.”). With that clarification, we are satisfied to affirm\\n\\nwithout prejudice the John Doe dismissals.\\n\\n\\n\\n IV.\\n\\n Pursuant to the foregoing, we affirm the dismissals of Holder and Donahoe with\\n\\nprejudice; we affirm the dismissal of the Amended Complaint and the parties named\\n\\ntherein with prejudice; and we affirm the dismissal of the unnamed John Doe agents\\n\\nwithout prejudice.\\n\\n AFFIRMED\\n\\n\\n\\n\\n 41\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4379619/\", \"author_raw\": \"joined. Judge Wynn wrote an opinion concurring\"}, {\"author\": \"WYNN, Circuit Judge, concurring\", \"type\": \"concurrence\", \"text\": \"WYNN, Circuit Judge, concurring in part\\n1\\n and dissenting in part:\\n\\n “When we saw the fours go up, game’s over.”\\n —David Chadwick, Forward, University of North Carolina, 1967–71 2\\n\\n Beginning in the late 1960s, when the University of North Carolina Tar Heels\\n\\nseized the lead in the second half of a basketball game, Hall of Fame head coach Dean\\n\\nSmith would raise his arm and put up four fingers. Requiring no further instruction, two\\n\\npost players would run to the two corners of the court formed by the baseline and the\\n\\nsidelines, and two wing players would move to the corners formed by the mid-court line\\n\\nand the sidelines. The point guard—most famously, Phil Ford—would then dribble the\\n\\nball at the top of the key as the clock ticked down, occasionally exchanging the ball with\\n\\none of the wing or post players if the defense applied too much pressure. In this\\n\\noffense—commonly referred to as the “Four Corners”—the clock was the Tar Heels’ best\\n\\nfriend. The longer the Tar Heels held the ball on offense, the less time their opponent\\n\\nhad to try to score and cut into the Tar Heels’ lead. The Four Corners proved so\\n\\nsuccessful that college basketball’s powers-that-be effectively outlawed it through the\\n\\nadoption of the shot clock in 1985.\\n\\n 1\\n I concur in the majority opinion’s judgment that the district court properly\\ndismissed Attkisson’s claims against the former Attorney General and former Postmaster\\nGeneral. I believe that Attkisson failed to plausibly allege that the former Attorney\\nGeneral and former Postmaster General were involved in any potential violation of\\nAttkisson’s constitutional or statutory rights.\\n 2\\n Brendan Marks, With Four Corners Offense, Dean Smith Changed Basketball,\\nDaily Tar Heel (Feb. 9, 2015), https://www.dailytarheel.com/article/2015/02/with-four-\\ncorners-offense-dean-smith-changed-basketball.\\n\\n\\n 42\\n\\n In this case, the government—not unlike Dean Smith’s Tar Heels—put up the\\n\\n“fours” when Plaintiff-Appellant Sharyl Attkisson, 3 a journalist formerly employed by\\n\\nCBS News, filed suit against unnamed employees and agents of the federal government\\n\\n(the “Doe Defendants”). Attkisson alleged that the Doe Defendants conspired to violate\\n\\nher constitutional and statutory rights by accessing and commandeering her home and\\n\\nwork internet-connected devices for surveillance purposes. But Attkisson never got a\\n\\nmeaningful opportunity to pursue her claims because the government did everything in its\\n\\npower to run out the clock on Attkisson’s action—it filed motions challenging venue and\\n\\njurisdiction, motions challenging the sufficiency of service, motions for extension of\\n\\ntime, motions to dismiss, and motions for protective orders.\\n\\n And just as the Tar Heels had great success running the Four Corners, the\\n\\ngovernment’s strategy worked. Although Attkisson diligently sought to identify the Doe\\n\\nDefendants for nearly four years—including by repeatedly serving discovery on the\\n\\ngovernment and third-parties directed at identifying the Doe Defendants—the district\\n\\ncourt dismissed her case with prejudice against the Doe Defendants for failing to comply\\n\\nwith a court order to identify the names of the Doe Defendants by a date certain. The\\n\\ndistrict court did so even though the government’s delaying tactics deprived Attkisson of\\n\\nany meaningful opportunity to engage in the discovery necessary to identify the Doe\\n\\nDefendants.\\n\\n 3\\n Attkisson’s husband, James, and daughter, Judith, are also named plaintiffs\\nbecause the alleged intrusions and commandeering of the Attkissons’ home computers\\nand devices allegedly violated their statutory and constitutional rights as well.\\n\\n\\n 43\\n\\n The majority opinion affirms the district court’s dismissal of Attkisson’s claims\\n\\nagainst the Doe Defendants on grounds that the dismissal constituted a permissible\\n\\nexercise of the court’s discretion to oversee discovery and sanction a party for failing to\\n\\ncomply with a court order. But this Court long has held that plaintiffs—like Attkisson—\\n\\nwho state a plausible claim that unnamed defendants violated their constitutional or\\n\\nstatutory rights are entitled to a meaningful opportunity to engage in discovery aimed at\\n\\nidentifying the “true identity of an unnamed party.” Schiff v. Kennedy, 691 F.2d 196,\\n\\n197–98 (4th Cir. 1982). And this Court has held that dismissal of an action for failure to\\n\\ncomply with a court order is a “drastic” sanction, Hillig v. C.I.R., 916 F.2d 171, 174 (4th\\n\\nCir. 1990), that courts should impose only in “extreme circumstances,” Reizakis v. Loy,\\n\\n490 F.2d 1132, 1135 (4th Cir. 1974).\\n\\n Because the government deprived Attkisson of a meaningful opportunity to\\n\\nidentify the Doe Defendants and the district court never determined that the requisite\\n\\n“extreme circumstances” were present to warrant dismissal for failure to comply with a\\n\\ncourt order, I disagree with the majority opinion’s determination that the district court\\n\\npermissibly exercised its discretion in dismissing Attkisson’s claims against the Doe\\n\\nDefendants. Not only should we disapprove of the tactics the government used to run out\\n\\nthe clock on Attkisson’s claims, but we should also reject the troubling “game plan” it\\n\\nprovided for the government and private parties to prevent disclosure of—and, therefore,\\n\\nresponsibility for—their potentially unconstitutional or illegal electronic surveillance\\n\\nactivities. Accordingly, I respectfully dissent as to the dismissal of Attkisson’s claims\\n\\nagainst the Doe Defendants.\\n\\n 44\\n\\n I.\\n\\n A.\\n\\n Because the district court dismissed Attkisson’s action prior to meaningful\\n\\ndiscovery, the relevant allegations, which this Court must accept as true, are set forth in\\n\\nAttkisson’s complaint. At the time of the events giving rise to her claim, Attkisson had\\n\\nbeen working as an investigative reporter for CBS News for 20 years. In early 2011,\\n\\nAttkisson began reporting on the “Fast & Furious” initiative, under which the Bureau of\\n\\nAlcohol, Tobacco, and Firearms (“ATF”) purposely allowed firearms dealers to sell\\n\\nmarked weapons to straw buyers, in anticipation that the weapons would later be sold to\\n\\nMexican drug cartels, thereby facilitating the identification and apprehension of key\\n\\nfigures in the cartels. CBS aired a report on the Fast & Furious program on February 22,\\n\\n2011. That report quoted and relied on confidential sources procured by Attkisson.\\n\\nAttkisson continued to report the story, which the Department of Justice initially denied,\\n\\nover the next several months. According to the complaint, Attkisson’s sources within\\n\\nATF told Attkisson “that the [a]gency was actively seeking to identify government\\n\\ninsiders who were providing information or ‘leaking’ to her and CBS.” J.A. 123.\\n\\n In October 2011, the government’s Fast & Furious program came under renewed\\n\\nscrutiny when law enforcement officers found weapons distributed through the Fast &\\n\\nFurious program at several crime scenes, including the scene of the murder of an ATF\\n\\nagent. That fall, Attkisson “began to notice anomalies in numerous electronic devices at\\n\\ntheir home in Virginia.” J.A. 124. According to the complaint, Attkisson’s home and\\n\\nwork computers would turn on and off at random, her house’s alarm would “chirp[] daily\\n\\n 45\\n\\nat different times,” and her phone and television experienced problems. J.A. 124. All the\\n\\naffected devices were connected to the Internet via Verizon’s fiber optic service, FiOS.\\n\\nVerizon failed to cure the problems, despite making multiple attempts over a period of\\n\\nmore than a year, including through installation of a new router. J.A. 124.\\n\\n During 2012, Attkisson continued to experience “anomalies” with her internet-\\n\\nconnected devices, which anomalies Attkisson repeatedly reported to Verizon, friends,\\n\\nand business associates. In December 2012, one of Attkisson’s “contact[s] with U.S.\\n\\ngovernment intelligence experience” inspected Attkisson’s home and found an “extra”\\n\\nfiber optic cable “dangling” from Attkisson’s exterior Verizon box. J.A. 129. After\\n\\nAttkisson contacted Verizon regarding the “extra” cable, “a person represented to be a\\n\\nVerizon technician” visited Attkisson’s home on January 1, 2013 and removed the cable.\\n\\nJ.A. 129. According to the complaint, notwithstanding that Attkisson told the technician\\n\\nto leave the cable, it disappeared. Over the next week, the Attkissons continued to\\n\\nexperience problems with their internet service, which Verizon repeatedly, but\\n\\nunsuccessfully, tried to resolve.\\n\\n On January 8, 2013, “an individual with special expertise in computer forensics”\\n\\nconducted a forensic examination of Attkisson’s laptop. J.A. 130. The expert reported\\n\\nthat the “laptop showed clear evidence of outside and unauthorized ‘intrusion,’ that the\\n\\nsources of the intrusion were state-supported due to the sophisticated nature of the\\n\\ntechnology used,” and that “the software fingerprint indicated that the software was\\n\\nproprietary to the federal government.” J.A. 130. According to the forensic analysis\\n\\nreport, “[t]he intrusion included, among other surveillance, keystroke monitoring,\\n\\n 46\\n\\nexfiltration of data, audio surveillance of [Attkisson’s] conversations and activities at\\n\\nhome by activating Skype, mining personal passwords, monitoring work and personal\\n\\nemail, and probable compromise of [Attkisson’s] work and personal smartphones.” J.A.\\n\\n130. “The report also stated the intruders had accessed CBS network systems . . . and\\n\\nthat the perpetrator had also place three (3) classified documents deep in the computer’s\\n\\noperating system.” J.A. 130. The forensic analysis determined that the intrusion began\\n\\nas early as June 2011 and traced the intrusion to an Internet Protocol (“IP”) “address\\n\\nowned, controlled, and operated by the United States Postal Service,” which “has been\\n\\npublicly reported, including in [Inspector General] internal audits, to have a working\\n\\nrelationship with the FBI, Department of Homeland Security, and [the Department of\\n\\nJustice] for domestic surveillance projects.” J.A. 125, 134.\\n\\n Several days later, Attkisson notified CBS, which hired an “independent forensic\\n\\ncomputer analyst” to inspect Attkisson’s home and internet-connected devices. J.A. 131.\\n\\nThat forensic investigation, conducted on February 2, 2013, found that Attkisson’s work\\n\\nand home computers had been subjected to a “coordinated, highly-skilled series of\\n\\nactions and attacks directed at the operation of the computers and the storage of data\\n\\nthereon.” J.A. 131. Several days after that second investigation, Attkisson’s desktop\\n\\ncomputer began to malfunction, shut down, emitted a “burning odor,” and was rendered\\n\\npermanently inoperable. J.A. 131. The complaint further alleges that Attkisson’s\\n\\nBlackBerry, which was connected to the Verizon network, also was compromised.\\n\\n On June 11, 2013, CBS issued a public statement, reporting that Attkisson’s\\n\\ncomputer had been accessed using “sophisticated methods” by an unauthorized party on\\n\\n 47\\n\\nmultiple occasions. J.A. 132. The independent security firm hired by CBS to analyze\\n\\nAttkisson’s computer publicly confirmed that report. The government issued a statement,\\n\\nstating that to its “knowledge, the Justice Department has never compromised Ms.\\n\\nAttkisson’s computers, or otherwise sought any information from or concerning any\\n\\ntelephone, computer or other media device she may own or use.” J.A. 131.\\n\\n B.\\n\\n On December 30, 2014, Attkisson brought a Bivens action under the First and\\n\\nFourth Amendments against named and unnamed federal defendants in the Superior\\n\\nCourt for the District of Columbia. The government removed the case to the U.S. District\\n\\nCourt of the District of Columbia. Within two months of first filing suit, Attkisson\\n\\nsought leave of the court “to serve limited, immediate discovery . . . to determine the true\\n\\n[identities] of the Doe Defendants.” J.A. 8. Attkisson argued that “good cause” existed to\\n\\nafford such discovery because she could not further prosecute her action until she\\n\\nidentified the Doe Defendants.\\n\\n The government opposed Attkisson’s discovery request for two reasons: (1) none\\n\\nof the defendants—named or unnamed—had been served and therefore the parties could\\n\\nnot, according to the government, conduct a Rule 26 discovery conference and (2)\\n\\nbecause the case “implicate[d] qualified immunity issues, . . . the Court should resolve\\n\\nthose issues and similar preliminary issues before any discovery occurs.” Defs.’ Opp. To\\n\\nPls.’ Mot. to Expedited Disc., Attkisson v. Holder, No. 15-238 (March 3, 2015), ECF No.\\n\\n11 (emphasis added). The government’s position, therefore, was tantamount to asserting\\n\\nthat early discovery should never be available in a Bivens case against unnamed\\n\\n 48\\n\\ndefendants. The government opposed Attkisson’s requested discovery pertaining to the\\n\\nidentity of the Doe Defendants, even as it simultaneously denied—and continues to\\n\\ndeny—that it represents the Doe Defendants. The district court denied without prejudice\\n\\nAttkisson’s request for expedited discovery on grounds that Attkisson had not yet\\n\\ncompleted service of the named defendants and that the discovery request was\\n\\n“overbroad” because Attkisson had not provided an “explanation of precisely what\\n\\ndiscovery [she] seeks to take.” J.A. 8.\\n\\n On March 20, 2015, having completed service of the named defendants, Attkisson\\n\\nagain moved for expedited discovery. To respond to the district court’s concern\\n\\nregarding the scope of the discovery she sought, Attkisson attached twenty-one\\n\\ninterrogatories and three requests for production. The interrogatories sought “[t]he\\n\\nidentity of any person” who had knowledge as to the various specific types of electronic\\n\\nincursions allegedly perpetrated between 2011 and 2013 “on computers owned or\\n\\noperated by Ms. Attkisson”—including “remotely altering computer VPN settings,”\\n\\n“smbclient,” “kcpassword,” “kickstart,” and “use of Intel AMT software.” Pls.’ Renewed\\n\\nMot. for Expedited Disc. 3–5, Attkisson v. Holder, No. 15-238 (March 20, 2015), ECF\\n\\nNo. 21-1. The interrogatories also sought the “identity and contact information of all\\n\\npersons” who had “access to,” “us[ed],” and were “responsible for maintaining,\\n\\nmonitoring, securing, and otherwise controlling” the Postal Service-owned IP address the\\n\\nforensic analysis connected to the incursions. Id. at 5–6.\\n\\n Less than a month later, the government moved to dismiss and again opposed\\n\\nAttkisson’s request for expedited discovery, asserting that her discovery requests were\\n\\n 49\\n\\nboth too numerous and not “narrowly tailored” to identifying the Doe Defendants.\\n\\nAttkisson filed an amended complaint on April 30, 2015. On July 6, 2015, the district\\n\\ncourt denied Attkisson’s second request for expedited discovery. The next day, the\\n\\ngovernment again moved to dismiss. Concurrently, Attkisson served notices of\\n\\ndepositions and subpoenas on several third parties, including the United States Postal\\n\\nService, seeking testimony and documents pertaining to the IP address identified in the\\n\\nforensic analysis so as to identify the Doe Defendants.\\n\\n In October 2015—after Attkisson repeatedly and unsuccessfully sought the\\n\\ngovernment’s voluntary compliance with her discovery requests—Attkisson moved the\\n\\ndistrict court to compel compliance with those requests. The government successfully\\n\\nsought several extensions of time, eventually filing on December 7, 2015, a brief in\\n\\nopposition to the motion to compel and a motion for protective order. Conceding that\\n\\nAttkisson’s discovery sought “to uncover the identities of the ‘Unknown Federal Agents’\\n\\nor ‘Doe defendants’”—i.e., that the discovery requests were tailored to the appropriate\\n\\nissue—the government argued that Attkisson could not obtain such discovery because, in\\n\\npart, “there [wa]s no evidence that Plaintiffs have conferred with the remaining ‘Doe’\\n\\ndefendants in this case for purposes of discovery,” which, according to the government,\\n\\nFederal Rule of Civil Procedure 26 required. Third-Party U.S. Postal Serv.’s Opp. To\\n\\nPls.’ Mot. to Compel And Mot. to Quash Subpoena and/or for Protective Order 13,\\n\\nAttkisson v. Holder, No. 15-238 (Dec. 7, 2015), ECF No. 47. Put differently, the\\n\\ngovernment took the position that Attkisson could not obtain discovery to identify the\\n\\n\\n\\n 50\\n\\nDoe Defendants because she had not engaged in a Rule 26 conference with the\\n\\nunidentified Doe Defendants.\\n\\n The parties engaged in additional briefing regarding Attkisson’s motion to compel\\n\\nduring the first half of 2016, with the government successfully obtaining several deadline\\n\\nextensions. On July 28, 2016—and still without Attkisson having had an opportunity to\\n\\nconduct any discovery—the district court consolidated Attkisson’s Bivens action with a\\n\\nseparate action under the Federal Tort Claims Act that Attkisson had brought against\\n\\nseveral parties, including the United States, related to the same alleged conduct. When it\\n\\nconsolidated the two actions, the district court dismissed Attkisson’s pending discovery\\n\\nmotions in the Bivens action as moot. Attkisson moved the district court to reconsider its\\n\\ndismissal of her motion to compel, which the government again opposed. Around the\\n\\nsame time, the government filed a third motion to dismiss. On March 19, 2017, the\\n\\nDistrict of Columbia district court denied, without prejudice, the government’s motion to\\n\\ndismiss and transferred the case to the U.S. District for the Eastern District of Virginia,\\n\\nagain denying Attkisson’s motion to compel as moot.\\n\\n On July 26, 2017—after waiting nearly four months for the court to assign a judge\\n\\nto her case and only eight days after that assignment 4—Attkisson again sought to compel\\n\\ncompliance with her previously served discovery requests. In early August 2017—and\\n\\nafter obtaining several more deadline extensions—the government filed a brief in\\n\\n 4\\n Because the parties had to wait several months for the appointment of a judge,\\nAttkisson bears no responsibility for the inaction in the case between March and July\\n2017 highlighted in the majority opinion. Ante at 13–14.\\n\\n\\n 51\\n\\nopposition to Attkisson’s renewed motion to compel and a fourth motion to dismiss, this\\n\\ntime for failure to state a claim and for lack of jurisdiction. On September 1, 2017, a\\n\\nmagistrate judge denied Attkisson’s motion to compel without prejudice.\\n\\n The district court directed Attkisson to file a consolidated complaint, which she\\n\\nfiled on September 18, 2017. That eight-count complaint, which names the Doe\\n\\nDefendants as defendants, asserted Bivens claims under the First and Fourth Amendments\\n\\nand violations of the Electronic Communications Privacy Act (“ECPA”), the Stored\\n\\nCommunications Act, the Computer Fraud and Abuse Act, the Foreign Intelligence\\n\\nSurveillance Act, and the Virginia Computer Crimes Act, as well common law trespass to\\n\\nchattel and land claims. On September 22, 2017, the parties filed a joint discovery plan.\\n\\nNotwithstanding that the discovery plan purported to establish a January 12, 2018,\\n\\ndeadline for completion of discovery, the government made clear in a footnote its\\n\\nposition that “discovery—including discovery not specifically directed at the individually\\n\\nsued government officials—may not proceed in this action” until the district court ruled\\n\\non the government’s motion to dismiss. Joint Proposed Disc. Plan, Attkisson v. Holder,\\n\\nNo. 1:17-cv-00364 (Sept. 22, 2017), ECF No. 123 (emphasis added).\\n\\n Within two weeks of the filing of the consolidated complaint, the district court\\n\\nissued an opinion and order dismissing most, but not all, of Attkisson’s claims. Attkisson\\n\\nv. Holder, No. 1:17-CV-364, 2017 WL 5013230 (E.D. Va. Nov. 1, 2017). Of particular\\n\\nrelevance to this dissent, the district court did not dismiss Attkisson’s Bivens and ECPA\\n\\nclaims against the Doe Defendants. Id. at *1.\\n\\n\\n\\n 52\\n\\n Following the district court’s motion-to-dismiss order, Attkisson sought\\n\\ntestimonial and documentary discovery from numerous federal agencies as well as\\n\\nVerizon’s Virginia subsidiary. For example, Attkisson noticed a deposition of the Postal\\n\\nService pursuant to Rule 30(b)(6), requesting that the Postal Service make available for\\n\\ndeposition “one or more persons” to testify as to the “ownership and control” of two\\n\\nspecific IP version 4 (“IPv4”) addresses that Attkisson’s forensic analyses identified were\\n\\nused in the alleged intrusions. In particular, Attkisson sought testimony regarding “[w]ho\\n\\nwas responsible for managing, tracking, and monitoring these IPv4 addresses within the\\n\\nPostal Service”; “[w]hat persons or organizations were permitted access to or use of the\\n\\nIPv4 address in the designated time frame”; “[a]ny and all records, logs, or other form of\\n\\nidentification material that will or may assist in identifying what person or persons\\n\\nprovided for each such use of these IPv4 addresses during the referenced time frame”;\\n\\nand “[a]ny and all records, logs, or other form of identification material that will or may\\n\\nassist in identifying the operational use of these IPv4 addresses.” J.A. 209–10.\\n\\n The government consented to a limited deposition of a United States Postal\\n\\nService employee regarding the IPv4 addresses identified in the forensic analysis, which\\n\\ndeposition revealed that Verizon contracted with the Postal Service to provide network\\n\\nservices and identified twelve other IP addresses connected to the alleged incursion. But\\n\\notherwise the government and Verizon successfully moved for a protective order on\\n\\noverbreadth grounds. Thereafter—and in accordance with the position it took in the Joint\\n\\nDiscovery Plan—the government sought a stay of all discovery pending resolution of its\\n\\nanticipated (renewed) motion to dismiss.\\n\\n 53\\n\\n On December 1, 2017, a magistrate judge entered a revised scheduling order\\n\\ndirecting Attkisson “to substitute named parties for the Doe Defendants no later than\\n\\nJanuary 5, 2018 at 10:00 a.m.” J.A. 259. In an order entered December 29, 2017, the\\n\\ndistrict court extended that deadline until February 5, 2018, emphasizing that “[t]his\\n\\nextension is the final extension that plaintiffs will receive because the interests of judicial\\n\\neconomy and fairness to third parties and potential future defendants dictate that plaintiffs\\n\\nmove forward with this litigation in as timely a fashion as possible.” J.A. 274–75.\\n\\n Thereafter, Attkisson reserved discovery against the federal agencies and Verizon,\\n\\nand moved to compel. Verizon again moved for a protective order. J.A. 276. The\\n\\nmagistrate granted in part the motion for protective order, allowing Attkisson to conduct\\n\\na 30(b)(6) deposition of Verizon employee as to the twelve Verizon-linked IP addresses\\n\\nidentified in the Postal Service deposition. The magistrate rendered that determination\\n\\nbecause he concluded that, at that stage of the litigation, discovery should be “limited to\\n\\ntrying to identify the Doe [D]efendants,” with liability discovery “com[ing] later.” J.A.\\n\\n512. The government also continued to resist Attkisson’s discovery requests on\\n\\noverbreadth grounds, maintaining that it was obliged to permit discovery only of “readily\\n\\navailable” information pertaining to the identities of the Doe Defendants. J.A. 521. At a\\n\\nJanuary 12, 2018 hearing—less than a month before the district court’s deadline for\\n\\nAttkisson to identify the Doe Defendants—the magistrate denied without prejudice\\n\\nAttkisson’s motion to compel on grounds that it appeared that the parties were moving\\n\\ntowards an agreed-on discovery plan related to identifying the Doe Defendants. J.A. 524.\\n\\n\\n\\n 54\\n\\n On February 5, 2018, Attkisson filed a proposed amended complaint that\\n\\ncontinued to list John Doe federal employee and agent defendants, but also added new\\n\\ncauses of action and several Verizon-affiliated entities, the United States of America, and\\n\\nthe Federal Bureau of Investigation as defendants. In an order entered May 15, 2018, the\\n\\ndistrict court denied Attkisson leave to amend and dismissed Attkisson’s pending action\\n\\nagainst the Doe Defendants with prejudice. The Court held that dismissal was warranted\\n\\nbecause Attkisson’s proposed complaint failed to offer substitutes for the Doe\\n\\nDefendants, as its December 29, 2017 order required, and, also in contravention of that\\n\\norder, added new defendants without seeking the court’s leave. As to the Doe\\n\\nDefendants, in particular, the court stated:\\n\\n Since 2014 when the plaintiffs’ first complaint was filed, none of the John\\n Doe defendants has been identified or served and plaintiffs have made no\\n substantial progress in identifying them. As such, the time has come to end\\n this litigation against them as well and for this reason, the claims against\\n them are also dismissed by this Order.\\n\\nJ.A. 669. Attkisson timely appealed.\\n\\n II.\\n\\n Attkisson argues that the district court erred in dismissing her claims against the\\n\\nDoe Defendants. Although its order is not a model of clarity, the district court appears to\\n\\nhave dismissed those claims for two related reasons: (A) Attkisson failed to make\\n\\n“substantial progress” in identifying the Doe Defendants and (B) Attkisson failed to\\n\\ncomply with the court’s order to substitute named parties for the Doe Defendants by\\n\\nFebruary 5, 2018. I do not believe that either purported failure justified the district\\n\\ncourt’s decision to dismiss Attkisson’s claims against the Doe Defendants.\\n\\n 55\\n\\n A.\\n\\n “Ordinarily a tort victim”—like Attkisson—“who does not know who the\\n\\ntortfeasor is cannot sue.” Billman v. Ind. Dep’t of Corrs., 56 F.3d 785, 789 (7th Cir.\\n\\n1995). But this Court and other courts long have recognized that if a tort complaint\\n\\nplausibly alleges that an unnamed defendant is an “actual” person or entity, then an\\n\\naction may “proceed against real, but unidentified, defendants.” Schiff, 691 F.2d at 197\\n\\n(citing Bivens v. Six Unknown Agents of Fed. Bureau of Narcotics, 403 U.S. 388 (1971)).\\n\\nIn such cases, a district court should dismiss the action on grounds that the plaintiff failed\\n\\nto allege the defendant’s true identity only “if it does not appear that the true identity of\\n\\nan unnamed party can be discovered through discovery or through intervention by the\\n\\ncourt.” Id. at 198; see also Davis v. Kelly, 160 F.3d 917, 921 (2d Cir. 1998) (collecting\\n\\ncases); Billman, 56 F.3d at 789 (holding that a plaintiff’s “initial inability to identify the\\n\\ninjurers is not by itself a proper ground for the dismissal of the suit”); Munz v. Parr, 758\\n\\nF.2d 1254, 1257 (8th Cir. 1985) (“Dismissal is proper only when it appears that the true\\n\\nidentity of the defendant cannot be learned through discovery or the court’s intervention.”\\n\\n(emphasis added)).\\n\\n Courts allow plaintiffs to sue unnamed tortfeasors—and, in appropriate\\n\\ncircumstances, engage in early discovery to identify the true identity of those alleged\\n\\ntortfeasors—when, as here, a plaintiff lacks the capacity to identify the names of the\\n\\ntortfeasors absent the power of the courts. For example, courts allow an injured party to\\n\\nsue an unnamed tortfeasor when circumstances outside the injured party’s control posed\\n\\nobstacles to the injured party identifying the tortfeasor prior to filing suit. See, e.g.,\\n\\n 56\\n\\nBillman, 56 F.3d at 789 (holding that a prison inmate was entitled to discovery when his\\n\\nconditions of confinement rendered it difficult, if not impossible, for him to identify the\\n\\nalleged tortfeasor prior to suit). Likewise, courts allow an injured party to sue an\\n\\nunnamed tortfeasor when the allegedly tortious conduct, by its nature, conceals the\\n\\nidentity of the tortfeasor. See, e.g., id. (noting that when “the plaintiff has been injured as\\n\\nthe consequence of the actions of an unknown member of a collective body, identification\\n\\nof the responsible party may be impossible without pretrial discovery”); Columbia Ins.\\n\\nCo. v. seescandy.com, 185 F.R.D. 573, 578 (N.D. Cal. 1999) (noting that when a plaintiff\\n\\nis injured by a tortious act allegedly committed via the internet by a “pseudonymous[] or\\n\\nanonymous[]” party, the plaintiff is “likely to find [her]self chasing the tortfeasor from\\n\\nInternet Service Provider (ISP) to ISP, with little hope of actually discovering the identity\\n\\nof the tortfeasor” absent compulsory judicial discovery).\\n\\n Considering this precedent, the district court abused its discretion in dismissing\\n\\nAttkisson’s action against the Doe Defendants without providing Attkisson with a\\n\\nmeaningful opportunity to engage in discovery to determine their true identity. To begin,\\n\\nAttkisson’s operative complaint—which we must accept as true—includes sufficient non-\\n\\nconclusory allegations against the Doe Defendants to state a Fourth Amendment Bivens\\n\\nclaim and a claim under the ECPA. The complaint recites at length, and with factual\\n\\nspecificity, the technical “anomalies” Attkisson experienced with her internet connected\\n\\ndevices. The complaint also discusses with factual specificity the various forensic\\n\\nanalyses of Attkisson’s devices conducted by security consultants—including a security\\n\\nconsultant hired by CBS—revealing that those devices had been compromised and\\n\\n 57\\n\\ncommandeered. The forensic analyses further revealed that those incursions included\\n\\nsearching records stored on Attkisson’s devices, monitoring Attkisson’s electronic\\n\\ncommunications, and using Attkisson’s internet connected devices to listen to her\\n\\nconversations at home. According to the complaint, those forensic analyses concluded\\n\\nthat the intrusions were “sophisticated”—and therefore “state-sponsored”—and derived\\n\\nfrom IPv4 addresses owned, controlled, and operated by the government, and the Postal\\n\\nService, in particular.\\n\\n Based on those allegations, it is “plausible” that the government—and/or a private\\n\\nentity operating on the government’s behalf—searched and commandeered Attkisson’s\\n\\ndevices and infringed on her right to privacy, in violation of the Fourth Amendment. See\\n\\nBuonocore v. Harris, 65 F.3d 347, 356 (4th Cir. 1995) (“[T]he special protection to be\\n\\nafforded a person’s right to privacy within his own home has also been continuously and\\n\\nconsistently recognized by the Court. The right to ‘sanctity of private dwellings,’ has\\n\\nbeen held to be the right ‘ordinarily afforded the most stringent Fourth Amendment\\n\\nprotection.’”). Likewise, the complaint adequately alleges that these same government\\n\\nactors “intercepted” Attkisson’s electronic communications in violation of the ECPA. 18\\n\\nU.S.C. § 2520.\\n\\n Second, the allegations in the complaint render it plausible that “actual” persons—\\n\\ni.e., the Doe Defendants—violated Attkisson’s constitutional and statutory rights. Schiff,\\n\\n691 F.2d at 197. Put simply, the “sophisticated” nature of the intrusions; the broad\\n\\nvariety of alleged surveillance, including “keystroke monitoring, exfiltration of data,\\n\\naudio surveillance of [Attkisson’s] conversations and activities at home by activating\\n\\n 58\\n\\nSkype, mining personal passwords, monitoring work and personal email, and probable\\n\\ncompromise of [Attkisson’s] work and personal smartphones,” J.A. 130; the years-long\\n\\nduration of the anomalies and incursions, despite repeated efforts to resolve them; and the\\n\\nefforts to hide evidence of the incursions provide factual support for the allegations that\\n\\n“actual” persons perpetrated the alleged constitutional and statutory violations.\\n\\n Additionally, in criminal proceedings, the government routinely argues—and\\n\\ncourts often agree—that when a specific IP address is used to perpetrate alleged\\n\\nwrongdoing online there is a “fair probability”—i.e., probable cause—that the individual\\n\\nor entity that owns or controls the IP address engaged in, or possesses evidence of, the\\n\\nwrongdoing. See, e.g., United States v. Vosburgh, 602 F.3d 512, 526 & n.13 (3d Cir.\\n\\n2010) (noting that “several Courts of Appeals have held that evidence that the user of a\\n\\ncomputer employing a particular IP address possessed or transmitted child pornography\\n\\ncan support a search warrant for the physical premises linked to that IP address”); United\\n\\nStates v. Perrine, 518 F.3d 1196, 1201–04 (10th Cir. 2008). Attkisson’s complaint\\n\\nidentified two specific IPv4 addresses owned and controlled by the government that were\\n\\nused to perpetrate the alleged unlawful surveillance. Accordingly, the complaint\\n\\nestablished that it is plausible that the individuals employed by, or acting on behalf of, the\\n\\ngovernment who used and maintained those IPv4 addresses perpetrated the allegedly\\n\\nunlawful surveillance or have information that will facilitate identification of the\\n\\nindividuals responsible for perpetrating the wrongdoing.\\n\\n Third, there was no basis for the district court to determine that “the true identity\\n\\nof [the Doe Defendants could not] be discovered through discovery or through\\n\\n 59\\n\\nintervention by the court.” Schiff, 691 F.2d at 198. Indeed, the government itself\\n\\nroutinely uses IP addresses to identify unknown wrongdoers. For example, the\\n\\ngovernment uses IP addresses as the starting point to identify unknown individuals who\\n\\npossess or share child pornography. See, e.g., Vosburgh, 602 F.3d at 526 & n.13\\n\\n(collecting cases); United States v. Bynum, 604 F.3d 161, 162–63 (4th Cir. 2010).\\n\\nLikewise, private parties such as copyright holders frequently use IP addresses to identify\\n\\nunknown defendants who allegedly engage in online copyright infringement. See, e.g.,\\n\\nPurzel Video GmbH v. St. Pierre, 10 F. Supp. 3d 1158, 1164 (D. Colo. 2014); Malibu\\n\\nMedia, LLC v. Roldan, No. 8:13-cv-3007, 2014 WL 3805494, at *1 (M.D. Fla. Aug. 1,\\n\\n2014); Loud Records LLC v. Minervini, 621 F. Supp. 2d 672, 676 (W.D. Wisc. 2009).\\n\\nGiven that the government as well as private parties successfully use IP addresses to\\n\\nidentify wrongdoers in other contexts, there is no reason to believe that pre-trial\\n\\ndiscovery would not allow Attkisson to use the IPv4 addresses to identify the true identity\\n\\nof the Doe Defendants.\\n\\n To be sure, the government is a “collective body,” rather than a single user, which\\n\\nmay somewhat complicate the process for identifying which, if any, government\\n\\nemployees perpetrated the allegedly unlawful surveillance of Attkisson’s devices.\\n\\nBillman, 56 F.3d at 789. But the difficulty a plaintiff faces in identifying pre-filing a\\n\\nparticular wrongdoer that works for a multi-member organization, like the government, is\\n\\none of the reasons courts allow a plaintiff to sue unnamed wrongdoers and to use pre-trial\\n\\ndiscovery to identify the wrongdoers’ identities. Id.; see also Palmer v. Bd. of Educ. of\\n\\nCmty. Unit Sch. Dist. 201-U, Will Cnty., Ill., 46 F.2d 682, 688 (7th Cir. 1995) (holding\\n\\n 60\\n\\nthat the district court erred in dismissing plausible claim against unnamed governmental\\n\\nemployees because “[w]hen a collective body . . . takes a complex series of actions over a\\n\\nspan of years, it may be difficult to pin down individual responsibility without\\n\\ndiscovery”). That is particularly true when, as here, members of a collective body\\n\\nallegedly perpetrate a wrong using the Internet, which allows wrongdoers to “act\\n\\npseudonymously and anonymously,” and thereby evade legal liability absent an injured\\n\\nparty’s use of discovery to determine the wrongdoers’ identity. Columbia Ins., 185\\n\\nF.R.D. at 578.\\n\\n Finally, the district court failed to afford Attkisson a meaningful opportunity to\\n\\nengage in discovery to determine the true identity of the Doe Defendants.\\n\\nNotwithstanding that Attkisson repeatedly served discovery on the government and\\n\\nrepeatedly moved the district court to compel the government to comply with the\\n\\ndiscovery requests, the sum of the discovery Attkisson obtained from the government\\n\\nduring the four years her case was pending was a limited deposition of a single Postal\\n\\nService employee. The government never turned over any documents in response to\\n\\nAttkisson’s subpoenas, nor did it answer any interrogatories. In such circumstances,\\n\\nAttkisson should not be faulted for failing to identify the Doe Defendants.\\n\\n The district court refused to compel the government to comply with Attkisson’s\\n\\ndiscovery requests because it believed that some of the requests were unrelated to the\\n\\nidentification of the Doe Defendants. But most of Attkisson’s requests sought\\n\\ninformation directly related to the identities of the Doe Defendants, including “[w]ho was\\n\\nresponsible for managing, tracking, and monitoring these IPv4 addresses within the\\n\\n 61\\n\\nPostal Service”; “[w]hat persons or organizations were permitted access to or use of the\\n\\nIPv4 address in the designated time frame”; “[a]ny and all records, logs, or other form of\\n\\nidentification material that will or may assist in identifying what person or persons\\n\\nprovided for each such use of these IPv4 addresses during the referenced time frame”;\\n\\nand “[a]ny and all records, logs, or other form of identification material that will or may\\n\\nassist in identifying the operational use of these IPv4 addresses.” J.A. 209–10. And\\n\\nAttkisson’s request for “[t]he identity of any person” who had knowledge regarding the\\n\\nvarious specific types of electronic incursions allegedly perpetrated against Attkisson’s\\n\\ndevices—including “remotely altering computer VPN settings,” “smbclient,”\\n\\n“kcpassword,” “kickstart,” and “use of Intel AMT software”—also specifically related to\\n\\nthe identity of the Doe Defendants. Pls.’ Renewed Mot. for Expedited Disc., Attkisson v.\\n\\nHolder, No. 15-238 (March 20, 2015), ECF No. 21-1. To the extent the district court\\n\\nbelieved any of Attkisson’s other requests swept too broadly, it could have granted\\n\\nAttkisson’s motion to compel only as to those requests bearing on the identity of the Doe\\n\\nDefendants.\\n\\n The district court also denied Attkisson’s final motion to compel because it\\n\\nbelieved that the parties were working towards a consensual discovery plan. I do not\\n\\nquestion the district court’s judgment that a consensual discovery plan is preferable to\\n\\ncourt-ordered discovery. But at the time it denied Attkisson’s final motion to compel, the\\n\\ncourt’s deadline for Attkisson to substitute names for the Doe Defendants was less than a\\n\\nmonth away. Given the government’s longstanding opposition to affording Attkisson any\\n\\ndiscovery—including its initial Kafkaesque position that Attkisson was not entitled to\\n\\n 62\\n\\nobtain discovery regarding the identity of the Doe Defendants until Attkisson conducted a\\n\\nRule 26(d) discovery conference with the unidentified Doe Defendants and the\\n\\ngovernment’s later, equally unsupported position, which the magistrate judge rightly\\n\\nrejected, that Attkisson was entitled to discover only whatever information the\\n\\ngovernment deemed “readily available”—and the court’s fast approaching substitution\\n\\ndeadline, it was incumbent on the district court to ensure that the government did not use\\n\\nits ongoing discovery negotiations with Attkisson to run out the clock on her claims. Put\\n\\nsimply, the district court needed to either (1) toll its deadline until Attkisson and the\\n\\ngovernment reached an agreement as to a discovery plan that would allow Attkisson to\\n\\nmeaningfully pursue the identity of the Doe Defendants or (2) compel the government to\\n\\ncomply with Attkisson’s reasonable discovery requests in advance of the deadline. It did\\n\\nneither; instead, it enforced its deadline even though Attkisson never obtained meaningful\\n\\ndiscovery, effectively rewarding the government for its intransigence.\\n\\n In sum, the district court reversibly erred when it dismissed Attkisson’s action\\n\\nagainst the Doe Defendants for failing to identify their names. That conclusion accords\\n\\nwith the approach taken by our sister circuits, which have held that a district court abused\\n\\nits discretion when—as here—it dismissed a plausible claim against an unnamed\\n\\ndefendant without allowing the plaintiff a meaningful opportunity to engage in discovery\\n\\nto determine the defendant’s identity. See, e.g., Vohra v. Cnty. of Orange, 288 Fed.\\n\\nApp’x 395, 396 (9th Cir. 2008); Green v. Doe, 260 Fed. App’x 717, 719 (5th Cir. 2007);\\n\\nValentin v. Dinkins, 121 F.3d 72, 75–76 (2d Cir. 1997); Billman, 56 F.3d at 787–89.\\n\\n\\n\\n 63\\n\\n And there is more. The district court compounded its error in dismissing\\n\\nAttkisson’s action against the Doe Defendants by failing to grant, at least in part,\\n\\nAttkisson’s repeated motions to compel. In the context of allegedly tortious acts\\n\\ncommitted over the Internet, in particular—like the Doe Defendants’ alleged unlawful\\n\\nsurveillance of Attkisson—courts have adopted several multi-factorial tests to guide a\\n\\ndistrict court’s analysis in determining whether to allow the plaintiff early or expedited\\n\\ndiscovery to facilitate identification of an unnamed defendant.\\n\\n For example, the Second Circuit has directed district courts to weigh “(1) the\\n\\nconcreteness of the plaintiff’s showing of a prima facie claim of actionable harm, (2) the\\n\\nspecificity of the discovery request, (3) the absence of alternative means to obtain the\\n\\nsubpoenaed information, (4) the need for the subpoenaed information to advance the\\n\\nclaim, and (5) the objecting party’s expectation of privacy.” See Arista Records, LLC v.\\n\\nDoe 3, 604 F.3d 110, 119 (2d Cir. 2010) (internal alterations omitted) (citing Sony Music\\n\\nEntm’t Inc. v. Does 1–40, 326 F. Supp. 2d 556, 564–65 (S.D.N.Y. 2004)). Other courts\\n\\napply similar tests. See, e.g., Columbia Ins., 185 F.R.D. at 578–80 (holding that a\\n\\nplaintiff is entitled to early discovery targeted at identifying an unnamed defendant if the\\n\\nplaintiff (1) “identif[ies] the missing party with sufficient specificity such that the Court\\n\\ncan determine that defendant is a real person or entity who could be sued in federal court;\\n\\n(2) “identif[ies] all previous steps taken to locate the elusive defendant”; (3)\\n\\n“establish[es] to the Court’s satisfaction that plaintiff’s suit against defendant could\\n\\nwithstand a motion to dismiss”; and (4) “file[s] a request for discovery with the Court,\\n\\nalong with a statement of reasons justifying the specific discovery requested as well as\\n\\n 64\\n\\nidentification of a limited number of persons on whom discovery process might be served\\n\\nand for which there is a reasonable likelihood that the discovery process will lead to\\n\\nidentifying information about the defendant that would make service of process\\n\\npossible.”).\\n\\n Here, the considerations other courts have deemed relevant supported awarding\\n\\nAttkisson early discovery targeted at identifying the Doe Defendants. As explained\\n\\nabove, Attkisson plausibly alleged that unnamed defendants violated her constitutional\\n\\nand statutory rights and that those defendants were “actual” individuals capable of\\n\\nidentification through discovery. The complaint also set forth several steps Attkisson had\\n\\ntaken to identify the perpetrators of the alleged violations, including obtaining multiple\\n\\nforensic analyses of her devices, filing a complaint with the Department of Justice\\n\\nInspector General, allowing the government to inspect her laptop computer, and\\n\\nsubmitting Freedom of Information Act requests. And even if a few requests were\\n\\nsomewhat overbroad, Attkisson served numerous discovery requests directly bearing on\\n\\nthe identity of the Doe Defendants. Finally, because information potentially relevant to\\n\\nthe identity of the Doe Defendants lies exclusively in the hands of the government—and\\n\\nbecause her other efforts to identify the Doe Defendants had proven unsuccessful—\\n\\nAttkisson established that she lacked alternative means to identify the Doe Defendants.\\n\\n B.\\n\\n The district court also dismissed Attkisson’s action against the Doe Defendants for\\n\\nfailure to comply with the court’s December 29, 2017, order that Attkisson substitute\\n\\nnames for the Doe Defendants on or before February 5, 2018. Federal Rule of Civil\\n\\n 65\\n\\nProcedure 41(b) permits a district court to involuntarily dismiss an action if a plaintiff\\n\\nfails to comply with a court order. We review for abuse of discretion a district court’s\\n\\ndismissal of an action for failure to comply with a court order. See Ballard v. Carlson,\\n\\n882 F.2d 93, 96 (4th Cir. 1989).\\n\\n This Court, like our sister circuits, has recognized that dismissal under Rule 41(b)\\n\\nis a “drastic” penalty, Hillig, 916 F.2d at 174, that should be limited to “extreme\\n\\ncircumstances,” Reizakis, 490 F.2d at 1135; see also, e.g., Dahl v. City of Huntington\\n\\nBeach, 84 F.3d 363, 366 (9th Cir. 1996) (holding that dismissal under Rule 41(b) “is so\\n\\nharsh a penalty it should be imposed as a sanction only in extreme circumstances”);\\n\\nJackson v. City of New York, 22 F.3d 71, 75 (2d Cir. 1994) (“Although dismissal pursuant\\n\\nto Rule 41(b) is a matter committed to the discretion of a district court . . . dismissal is a\\n\\nharsh remedy to be utilized only in extreme situations.” (internal quotation marks\\n\\nomitted)); Flaksa v. Little River Marine Const. Co., 389 F.2d 885, 888 (5th Cir. 1968)\\n\\n(dismissal under Rule 41(b) warranted only in “extreme circumstances”).\\n\\n In deciding whether to dismiss a case under Rule 41(b), “[a]gainst the power to\\n\\nprevent delays must be weighed the sound public policy of deciding cases on the merits.”\\n\\nHillig, 916 F.2d at 173–74. In making that determination, “[t]his Circuit requires that the\\n\\ntrial court consider four factors before dismissing a case for failure to prosecute: (1) the\\n\\nplaintiff’s degree of personal responsibility; (2) the amount of prejudice caused the\\n\\ndefendant; (3) the presence of a drawn out history of deliberately proceeding in a dilatory\\n\\n\\n\\n\\n 66\\n\\nfashion; and (4) the effectiveness of sanctions less drastic than dismissal.” Id. at 174\\n\\n(emphasis added). 5\\n\\n Considering this precedent, the district court abused its discretion in dismissing\\n\\nAttkisson’s claims against the Doe Defendants based on Attkisson’s failure to comply\\n\\nwith the court’s order. The district court never expressly considered this Court’s\\n\\nmandatory four-factor test for dismissing an action for failure to comply with a court\\n\\norder. That legal error, by itself, amounts to an abuse of discretion. See Verisign, Inc. v.\\n\\nXYZ.COM LLC, 891 F.3d 481, 484–86 (4th Cir. 2018) (holding that district court abuses\\n\\nits discretion when it applies the wrong legal test); United States v. Cargill, 134 F.3d 364\\n\\n(4th Cir. 1998) (table) (same); see also Koon v. United States, 518 U.S. 81, 100 (1996)\\n\\n(“A district court by definition abuses its discretion when it makes an error of law.”).\\n\\n And although the district court adverted, in a conclusory fashion, to some aspects\\n\\nof those four considerations—referencing “prejudic[e]” to defendants and “judicial\\n\\neconomy,” J.A. 668—it never considered, much less ruled out, “less drastic” sanctions, as\\n\\nthis Court requires. Notably, this Court and other courts have held that a district court\\n\\nabused its discretion in dismissing an action under Rule 41(b) when it failed to consider\\n\\n\\n 5\\n The majority opinion states that the factors identified in Hillig should “guide” the\\ndistrict court’s analysis in determining whether to dismiss a case under Rule 41(b), and\\ntherefore that the district court did not reversibly err in failing to consider those factors.\\nAnte at 34. The majority opinion nowhere reconciles its reasoning with Hillig’s\\ncontrolling holding that district courts are “required” to consider those four factors. 916\\nF.2d at 174. The majority opinion also nowhere reconciles its conclusion with the\\nunanimous conclusion of the Courts of Appeal that dismissals under Rule 41(b) should be\\nlimited to “extreme circumstances.”\\n\\n\\n 67\\n\\nlesser sanctions. See Reizakis, 490 F.2d at 1135; In re Se. Banking Corp., 204 F.3d 1322,\\n\\n1335 (11th Cir. 2000).\\n\\n Additionally, had the district court considered the mandatory factors set forth in\\n\\nHillig, it should have rendered a different judgment. First, there is no evidence that\\n\\nAttkisson had any degree of personal responsibility in her attorney’s purported failure to\\n\\ncomply with the court’s order. Second, although the passage of time may somewhat\\n\\nprejudice the Doe Defendants, Attkisson correctly notes that any such prejudice is\\n\\nattributable to the government’s repeated efforts to delay and resist any discovery.\\n\\nAppellant’s Br. at 48. Third, the record belies any finding that Attkisson engaged in “a\\n\\ndrawn-out history of deliberately proceeding in a dilatory fashion.” Hillig, 916 F.2d at\\n\\n74. On the contrary, since the filing of the original complaint, Attkisson has repeatedly\\n\\nsought to engage in discovery to identify the Doe Defendants and faced largely\\n\\nsuccessful resistance from the government and third-parties at every turn. Finally, any\\n\\nnumber of less drastic remedies, such as denying further leave to amend the complaint to\\n\\nadd new defendants or causes of action, were available. 6\\n\\n\\n 6\\n I agree with the majority opinion that the district court did not abuse its\\ndiscretion in denying Attkisson leave to amend her complaint to rename the United States\\nas a defendant, add several Verizon-affiliated entities as defendants, and resurrect several\\npreviously dismissed claims. Ante at 34–36. The court’s order did not authorize\\nAttkisson to make such amendments, and Attkisson never sought the court’s leave to do\\nso. But the majority opinion improperly conflates the district court’s (correct) disposition\\nof Attkisson’s proposed amended complaint with the district court’s (incorrect) dismissal\\nof Attkisson’s claims against the Doe Defendants, who had been listed as defendants\\nsince the case’s inception. Whether Attkisson’s proposed amended complaint was proper\\nhad no bearing on whether Attkisson’s long-standing claims against the Doe Defendants,\\nas set forth in her operative complaint, warranted dismissal.\\n\\n\\n 68\\n\\n Additionally, the district court’s Rule 41(b) dismissal runs contrary to this Court’s\\n\\nstated preference to resolve cases on the merits. Put simply, this case did not present the\\n\\n“extreme circumstances” warranting dismissal under Rule 41(b). Accordingly, I disagree\\n\\nwith the majority opinion’s conclusion that the district court did not reversibly err in\\n\\ndismissing Attkisson’s claim against the Doe Defendants. 7\\n\\n III.\\n\\n The most troubling aspect of the district court’s decision to dismiss Attkisson’s\\n\\nclaims against the Doe Defendants is that it rewards the government’s concerted effort to\\n\\ndeprive Attkisson any opportunity to pursue her claims and, by doing so, creates a game\\n\\nplan for the government and private parties to follow in future cases in which plaintiffs\\n\\nseek to challenge governmental or private electronic surveillance activities.\\n\\n At the outset of cases challenging alleged electronic surveillance, the defendants\\n\\nnearly always have exclusive control over virtually all information necessary to identify\\n\\nthe individuals responsible for engaging in allegedly unconstitutional or unlawful\\n\\nelectronic surveillance. In cases involving governmental surveillance programs, for\\n\\nexample, the individuals and entities responsible for the challenged surveillance\\n\\nprograms generally will be protected by statutes and regulations preventing the disclosure\\n\\n 7\\n The majority opinion further concludes that the district court “implicitly relied”\\non Federal Rule of Civil Procedure 4(m) in dismissing Attkisson’s claims against the Doe\\nDefendants because Attkisson failed to establish “good cause” for her failure to timely\\nserve the Doe Defendants. Ante at 38 n.13. But the district court’s terse footnote\\ndismissing the Doe Defendants nowhere mentions Rule 4(m). And Attkisson did have\\n“good cause” for failing to serve the Doe Defendants—she never obtained the discovery\\nfrom the government necessary for her to identify the Defendants.\\n\\n\\n 69\\n\\nof classified documents and programs as well as judicial orders sealing records related to\\n\\nwarrants issued in criminal and national security investigations. The nature of the\\n\\nInternet, which allows wrongdoers to conceal their identity in a variety of ways, poses\\n\\nfurther obstacles to identifying individuals responsible for electronic surveillance without\\n\\nthe benefit of pre-trial discovery.\\n\\n This profound information asymmetry sets electronic surveillance cases apart from\\n\\nearlier cases involving tort claims against unnamed defendants. Whereas the plaintiff in\\n\\nBivens, for example, could point to a specific number of officers employed by a specific\\n\\nagency who were in a specific place at a specific time, a plaintiff challenging electronic\\n\\nsurveillance faces fatally greater obstacles to narrowing the universe of wrongdoers\\n\\nabsent court-supervised discovery.\\n\\n If a district court creates a deadline for identifying unnamed defendants accused of\\n\\nunlawful electronic surveillance and that deadline is not tethered to whether the defendant\\n\\naffords the plaintiff a meaningful opportunity to discover the identity of the\\n\\nwrongdoers—as was the case here—the defendant has a strong incentive to resist all\\n\\ndiscovery of information bearing on the identity of wrongdoer. Put simply, when the\\n\\ndefendant is not compelled to provide discovery, the plaintiff will be unable to meet the\\n\\ncourt’s deadline to substitute names for the unnamed defendants and the case will be\\n\\ndismissed, just as occurred here.\\n\\n But “the children’s game of pin the tail on the donkey is [not] a proper model for\\n\\nconstitutional tort law,” nor is the time-limited game of pin-the-tail-on-the-donkey that\\n\\nthe district court imposed here. Billman, 56 F.3d at 789. That is particularly true in cases\\n\\n 70\\n\\ninvolving electronic surveillance in which the complexity of modern telecommunications\\n\\nsystems—coupled with the numerous avenues such systems afford users to conceal their\\n\\nidentities—may require more extensive discovery to identify an unnamed defendant. In\\n\\nsuch instances, artificial time constraints on identifying an unnamed defendant are all the\\n\\nmore inappropriate.\\n\\n In recent years, newspapers have been rife with reports of actual or alleged\\n\\nundisclosed electronic surveillance by the government and private entities. See, e.g.,\\n\\nCarole Cadwalladr & Emma Graham-Harrison, Facebook Accused of Conducting Mass\\n\\nSurveillance Through Its Apps, Guardian (May 24, 2018),\\n\\nhttps://www.theguardian.com/technology/2018/may/24/facebook-accused-of-conducting-\\n\\nmass-surveillance-through-its-apps; Charlie Savage, N.S.A. Halts Collection of\\n\\nAmericans’ Emails About Foreign Targets, N.Y. Times, Apr. 29, 2017, at A1. Such\\n\\nsurveillance has the potential to reveal to the government and private entities broad\\n\\nswaths of highly sensitive personal and commercial information. This case is\\n\\nillustrative—according to the complaint, the incursion not only entailed the searching of\\n\\nAttkisson’s computers and the monitoring of her electronic communications, but also\\n\\ninvolved using her devices to eavesdrop on her oral conversations and interactions with\\n\\nher family in her home. As the government’s and private entities’ capacity to hoover up\\n\\ndata increases—and as we move beyond accessing the Internet through a limited universe\\n\\nof devices to the Internet of things—the potential intrusion on privacy only increases.\\n\\n Under the government’s playbook—which the district court effectively\\n\\nendorsed—plaintiffs would be deprived all opportunity to challenge the legality of most,\\n\\n 71\\n\\nif not all, these electronic surveillance efforts, notwithstanding the significant intrusion\\n\\non individual rights posed by such surveillance. To be sure, it can be difficult to apply\\n\\nanalog law in the digital age, and courts must tread carefully in so doing. But courts must\\n\\nnot avoid the difficult legal issues raised by new technology by erecting procedural\\n\\nbarriers that ensure they never will be addressed. The district court’s disposition of\\n\\nAttkisson’s claims against the Doe Defendants, which the majority opinion affirms, does\\n\\nprecisely that.\\n\\n Accordingly, I respectfully dissent.\\n\\n\\n\\n\\n 72\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4379619/\", \"author_raw\": \"WYNN, Circuit Judge, concurring\"}]}"},"judge1":{"kind":"string","value":"WYNN"},"judge2":{"kind":"string","value":"WYNN"},"judge3":{"kind":"string","value":""},"exactly_three_caps":{"kind":"number","value":0,"string":"0"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":5,"string":"5"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":3,"string":"3"},"other_count":{"kind":"number","value":2,"string":"2"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4602366/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":1,"string":"1"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":1,"string":"1"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Sharyl Thompson ATTKISSON; James Howard Attkisson; Sarah Judith Starr Attkisson, Plaintiffs - Appellants, v. Eric Himpton HOLDER, Jr., Individually; Patrick R. Donahoe, Individually; Unknown Named Agents of the Department of Justice, in Their Individual Capacities; Unknown Named Agents of the United States Postal Service, in Their Individual Capacities; Unknown Named Agents of the United States, in Their Individual Capacities; Verizon Virginia LLC; Federal Bureau of Investigation; MCI Communications Services, Inc., D/B/A Verizon Business Services ; Cellco Partnership, D/B/A Verizon Wireless, Defendants - Appellees.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-03-21\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: Yes\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-1677\n\n\nSHARYL THOMPSON ATTKISSON; JAMES HOWARD ATTKISSON;\nSARAH JUDITH STARR ATTKISSON,\n\n Plaintiffs – Appellants,\n v.\n\nERIC HIMPTON HOLDER, JR., Individually; PATRICK R. DONAHOE,\nIndividually; UNKNOWN NAMED AGENTS OF THE DEPARTMENT OF\nJUSTICE, In their individual capacities; UNKNOWN NAMED AGENTS OF\nTHE UNITED STATES POSTAL SERVICE, In their individual capacities;\nUNKNOWN NAMED AGENTS OF THE UNITED STATES, In their individual\ncapacities; VERIZON VIRGINIA LLC; FEDERAL BUREAU OF\nINVESTIGATION; MCI COMMUNICATIONS SERVICES, INC., d/b/a Verizon\nBusiness Services; CELLCO PARTNERSHIP, d/b/a Verizon Wireless,\n\n Defendants – Appellees.\n\n\nAppeal from the United States District Court for the Eastern District of Virginia, at\nAlexandria. Leonie M. Brinkema, District Judge. (1:17-cv-00364-LMB-JFA)\n\n\nArgued: January 29, 2019 Decided: March 21, 2019\n\n\nBefore MOTZ, KING, and WYNN, Circuit Judges.\n\n\nAffirmed by published opinion. Judge King wrote the opinion, in which Judge Motz\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Sharyl Thompson ATTKISSON; James Howard Attkisson; Sarah Judith Starr Attkisson, Plaintiffs - Appellants, v. Eric Himpton HOLDER, Jr., Individually; Patrick R. Donahoe, Individually; Unknown Named Agents of the Department of Justice, in Their Individual Capacities; Unknown Named Agents of the United States Postal Service, in Their Individual Capacities; Unknown Named Agents of the United States, in Their Individual Capacities; Verizon Virginia LLC; Federal Bureau of Investigation; MCI Communications Services, Inc., D/B/A Verizon Business Services ; Cellco Partnership, D/B/A Verizon Wireless, Defendants - Appellees.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-03-21\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: Yes\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-1677\\n\\n\\nSHARYL THOMPSON ATTKISSON; JAMES HOWARD ATTKISSON;\\nSARAH JUDITH STARR ATTKISSON,\\n\\n Plaintiffs – Appellants,\\n v.\\n\\nERIC HIMPTON HOLDER, JR., Individually; PATRICK R. DONAHOE,\\nIndividually; UNKNOWN NAMED AGENTS OF THE DEPARTMENT OF\\nJUSTICE, In their individual capacities; UNKNOWN NAMED AGENTS OF\\nTHE UNITED STATES POSTAL SERVICE, In their individual capacities;\\nUNKNOWN NAMED AGENTS OF THE UNITED STATES, In their individual\\ncapacities; VERIZON VIRGINIA LLC; FEDERAL BUREAU OF\\nINVESTIGATION; MCI COMMUNICATIONS SERVICES, INC., d/b/a Verizon\\nBusiness Services; CELLCO PARTNERSHIP, d/b/a Verizon Wireless,\\n\\n Defendants – Appellees.\\n\\n\\nAppeal from the United States District Court for the Eastern District of Virginia, at\\nAlexandria. Leonie M. Brinkema, District Judge. (1:17-cv-00364-LMB-JFA)\\n\\n\\nArgued: January 29, 2019 Decided: March 21, 2019\\n\\n\\nBefore MOTZ, KING, and WYNN, Circuit Judges.\\n\\n\\nAffirmed by published opinion. Judge King wrote the opinion, in which Judge Motz\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1064,"cells":{"id":{"kind":"number","value":4602938,"string":"4,602,938"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"Tim Brundle v. Wilmington Trust, N.A."},"decision_date":{"kind":"string","value":"2019-03-22"},"docket_number":{"kind":"string","value":"17-1873"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before GREGORY, Chief Judge, and MOTZ and FLOYD, Circuit Judges.\", \"parties\": \"\", \"opinions\": [{\"author\": \"DIANA GRIBBON MOTZ, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 17-1873\\n\\n\\nTIM P. BRUNDLE, on behalf of the Constellis Employee Stock Ownership Plan,\\n\\n Plaintiff - Appellee,\\n\\n and\\n\\nANDREW HALLDORSON, on behalf of the Constellis Employee Stock\\nOwnership Plan, and on behalf of a class of all other persons similarly situated,\\n\\n Plaintiff,\\n\\n v.\\n\\nWILMINGTON TRUST, N.A., as successor to Wilmington Trust Retirement and\\nInstitutional Services Company,\\n\\n Defendant - Appellant.\\n\\n-------------------------------------------\\n\\nAMERICAN SOCIETY OF APPRAISERS,\\n\\n Amicus Supporting Appellant,\\n\\nSECRETARY OF THE UNITED STATES DEPARTMENT OF LABOR,\\n\\n Amicus Supporting Appellee.\\n\\n\\n No. 17-2224\\n\\n\\nTIM P. BRUNDLE, on behalf of the Constellis Employee Stock Ownership Plan,\\n\\f Plaintiff - Appellant,\\n\\n and\\n\\nANDREW HALLDORSON, on behalf of the Constellis Employee Stock\\nOwnership Plan, and on behalf of a class of all other persons similarly situated,\\n\\n Plaintiff,\\n\\n v.\\n\\nWILMINGTON TRUST, N.A., as successor to Wilmington Trust Retirement and\\nInstitutional Services Company,\\n\\n Defendant - Appellee.\\n\\n-------------------------------------------\\n\\nSECRETARY OF THE UNITED STATES DEPARTMENT OF LABOR,\\n\\n Amicus Supporting Appellant,\\n\\nAMERICAN SOCIETY OF APPRAISERS,\\n\\n Amicus Supporting Appellee.\\n\\n\\n No. 17-2323\\n\\n\\nTIM P. BRUNDLE, on behalf of the Constellis Employee Stock Ownership Plan,\\n\\n Plaintiff - Appellee,\\n\\n and\\n\\nANDREW HALLDORSON, on behalf of the Constellis Employee Stock\\nOwnership Plan, and on behalf of a class of all other persons similarly situated,\\n\\n Plaintiff,\\n\\nCONSTELLIS GROUP, INC.,\\n\\n\\n 2\\n\\f Party-in-Interest,\\n\\n v.\\n\\nWILMINGTON TRUST, N.A., as successor to Wilmington Trust Retirement and\\nInstitutional Services Company,\\n\\n Defendant - Appellant.\\n\\n-------------------------------------------\\n\\nAMERICAN SOCIETY OF APPRAISERS,\\n\\n Amicus Supporting Appellant,\\n\\nSECRETARY OF THE UNITED STATES DEPARTMENT OF LABOR,\\n\\n Amicus Supporting Appellee.\\n\\n\\n No. 17-2324\\n\\n\\nTIM P. BRUNDLE, on behalf of the Constellis Employee Stock Ownership Plan,\\n\\n Plaintiff - Appellee,\\n\\n and\\n\\nANDREW HALLDORSON, on behalf of the Constellis Employee Stock\\nOwnership Plan, and on behalf of a class of all other persons similarly situated,\\n\\n Plaintiff,\\n\\n v.\\n\\nCONSTELLIS GROUP, INC.,\\n\\n Party-in-Interest - Appellant,\\n\\n and\\n\\n\\n\\n 3\\n\\fWILMINGTON TRUST, N.A., as successor to Wilmington Trust Retirement and\\nInstitutional Services Company,\\n\\n Defendant.\\n\\n\\n No. 18-1029\\n\\n\\nTIM P. BRUNDLE, on behalf of the Constellis Employee Stock Ownership Plan,\\n\\n Plaintiff - Appellant,\\n\\n and\\n\\nANDREW HALLDORSON, on behalf of the Constellis Employee Stock\\nOwnership Plan, and on behalf of a class of all other persons similarly situated,\\n\\n Plaintiff,\\n\\n v.\\n\\nWILMINGTON TRUST, N.A., as successor to Wilmington Trust Retirement and\\nInstitutional Services Company,\\n\\n Defendant - Appellee,\\n\\nCONSTELLIS GROUP, INC.,\\n\\n Party-in-Interest.\\n\\n\\nAppeals from the United States District Court for the Eastern District of Virginia, at\\nAlexandria. Leonie M. Brinkema, District Judge. (1:15-cv-01494-LMB-IDD)\\n\\n\\nArgued: December 11, 2018 Decided: March 21, 2019\\n Amended: March 22, 2019\\n\\n\\nBefore GREGORY, Chief Judge, and MOTZ and FLOYD, Circuit Judges.\\n\\n\\n\\n 4\\n\\fAffirmed by published opinion. Judge Motz wrote the opinion, in which Chief Judge\\nGregory and Judge Floyd joined.\\n\\n\\nARGUED: Carter Glasgow Phillips, SIDLEY AUSTIN LLP, Washington, D.C., for\\nAppellant/Cross-Appellee Wilmington Trust, N.A. Gregory Y. Porter, BAILEY &\\nGLASSER LLP, Washington, D.C., for Appellee/Cross-Appellant. Robin Springberg\\nParry, UNITED STATES DEPARTMENT OF LABOR, Washington, D.C., for Amicus\\nSecretary of Labor. ON BRIEF: James P. McElligott, Jr., Summer L. Speight,\\nRichmond, Virginia, Stephen W. Robinson, MCGUIRE WOODS LLP, Tysons, Virginia;\\nJacqueline G. Cooper, Kurt A. Johnson, SIDLEY AUSTIN LLP, Washington, D.C., for\\nAppellant/Cross-Appellee Wilmington Trust, N.A. Edward Lee Isler, Micah E. Ticatch,\\nISLER DARE, P.C., Vienna, Virginia, for Appellant Constellis Group, Inc. Tillman J.\\nBreckenridge, Ryan T. Jenny, BAILEY & GLASSER LLP, Washington, D.C., for\\nAppellee/Cross-Appellant. J. Christian Nemeth, Chicago, Illinois, Sophia A. Luby,\\nWashington, D.C.; Eliot T. Burriss, Erin Turley, Calli Turner, MCDERMOTT WILL &\\nEMERY LLP, Dallas, Texas, for Amicus American Society of Appraisers. Kate S.\\nO’Scannlain, Solicitor of Labor, G. William Scott, Associate Solicitor for Plan Benefits\\nSecurity, Thomas Tso, Counsel for Appellate and Special Litigation, UNITED STATES\\nDEPARTMENT OF LABOR, Washington, D.C., for Amicus Secretary of Labor.\\n\\n\\n\\n\\n 5\\n\\fDIANA GRIBBON MOTZ, Circuit Judge:\\n\\n After owners of a closely held corporation sold the company to its Employee\\n\\nStock Ownership Plan (“ESOP”), a participant in the ESOP brought this action. The\\n\\nparticipant contended that the trustee chosen for the ESOP by the corporation breached\\n\\nits fiduciary duties to the ESOP and overpaid for the stock — improperly enriching the\\n\\ncorporation’s owners at the expense of its employees.\\n\\n Following a multi-day bench trial, the district court issued detailed findings of fact\\n\\nconcluding that the trustee had indeed breached its fiduciary duties, causing the ESOP to\\n\\noverpay for the corporation’s stock by $29,773,250. The court entered judgment for the\\n\\nESOP in that amount and awarded attorneys’ fees to the participant’s counsel. These\\n\\nappeals and cross-appeals followed. As explained within, we affirm the careful findings\\n\\nof the district court.\\n\\n\\n\\n I.\\n\\n To facilitate understanding of the issues here, we begin with the governing legal\\n\\nprinciples and background facts that gave rise to this suit. The parties do not challenge\\n\\nthese principles or facts. All are more fully set forth in the comprehensive district court\\n\\nopinions, upon which we rely throughout. See Brundle v. Wilmington Tr. N.A., 241\\n\\nF. Supp. 3d 610 (E.D. Va. 2017) (“Brundle I”); Brundle v. Wilmington Tr. N.A., 258\\n\\nF. Supp. 3d 647 (E.D. Va. 2017) (“Brundle II”).\\n\\n\\n\\n\\n 6\\n\\f A.\\n\\n The Employee Retirement Income Security Act of 1974 (ERISA) allows an\\n\\nemployer to create an ESOP, an employee pension plan that invests primarily in the\\n\\nemployer’s stock. The employer makes contributions to the plan that are used to\\n\\npurchase stock in the employer’s company. Because — and only because — an ESOP\\n\\ncontribution qualifies as employee compensation, an employer can deduct the total value\\n\\nof its ESOP contribution from its income tax liability as an ordinary business expense.\\n\\n26 U.S.C. § 404; 26 C.F.R. § 1.404(a)–1(b). 1 In this way, an ESOP benefits both\\n\\nemployees and employers by providing deferred compensation to the former and a\\n\\nvaluable tax deduction to the latter.\\n\\n ERISA imposes duties and obligations on all pension plan fiduciaries, including\\n\\nthose of ESOPs. These duties “ensure that employees will not be left empty-handed once\\n\\nemployers have guaranteed them certain benefits.” Lockheed Corp. v. Spink, 517 U.S.\\n\\n882, 887 (1996). One such provision prohibits the fiduciary of any ERISA plan from\\n\\ncausing a “sale or exchange . . . of any property between the plan and a party in interest.”\\n\\n29 U.S.C. § 1106(a)(1)(A). Absent a statutory exception, this provision would ban\\n\\nESOPs because their creation necessarily requires the ESOP to purchase stock from its\\n\\nsponsoring employer, which is a party in interest. Congress, however, has carved out an\\n\\n\\n\\n 1\\n An employer’s contributions to an ESOP thus constitute a valuable form of\\ndeferred compensation, rather than a gift to employees. See, e.g., Reich v. Hall Holding\\nCo., 990 F. Supp. 955, 961 (N.D. Ohio 1998), aff’d sub nom. Chao v. Hall Holding Co.,\\n285 F.3d 415 (6th Cir. 2002). Wilmington wisely does not suggest otherwise.\\n\\n 7\\n\\fexception to this prohibition to permit the creation of an ESOP if the stock purchase\\n\\nmeets certain conditions. See 29 U.S.C. § 1108(e).\\n\\n To protect employees from losing the value of their earned retirement savings, the\\n\\nexception to the ERISA ban on party-in-interest transactions requires that an ESOP pay\\n\\nno more than “adequate consideration” for the employer’s stock. Id. § 1108(e)(1). If an\\n\\nemployer’s “stock was not worth what the ESOP paid for it,” then the ESOP paid more\\n\\nthan adequate consideration and “the ESOP and its participants suffered a loss under\\n\\nERISA.” See Reich, 990 F. Supp. at 961.\\n\\n ERISA does not define what constitutes “adequate consideration” under the\\n\\n§ 1108(e) exception; the Department of Labor (DOL) has proposed, but never enacted,\\n\\nregulations doing so. 2 Although courts look to these regulations for guidance, the focus\\n\\nof the adequate-consideration inquiry rests on the conduct of a fiduciary, as judged by\\n\\nERISA’s “prudent man” standard of care. See Perez v. Bruister, 823 F.3d 250, 263 (5th\\n\\nCir. 2016); Henry III, 445 F.3d at 619; Chao, 285 F.3d at 437; Howard v. Shay, 100 F.3d\\n\\n1484, 1489 (9th Cir. 1996).\\n\\n Under this standard, “ESOP fiduciaries are subject to the duty of prudence just as\\n\\nother ERISA fiduciaries are.” Fifth Third Bancorp v. Dudenhoeffer, 134 S. Ct. 2459,\\n\\n 2\\n These proposed regulations, to which courts look for guidance, provide that\\n“adequate” consideration must (1) reflect the stock’s “fair market value,” and (2) be “the\\nproduct of a determination made by the fiduciary in good faith.” Proposed Regulation\\nRelating to the Definition of Adequate Consideration, 53 Fed. Reg. 17,632, 17,633\\n(proposed May 17, 1988) (to be codified at 29 C.F.R. pt. 2510). “[I]n practice, the ‘fair\\nmarket value’ inquiry overlaps considerably with the ‘good faith’ inquiry.’” Henry v.\\nChamplain Enters., Inc., 445 F.3d 610, 618–19 (2d Cir. 2006) (Sotomayor, J.) (“Henry\\nIII”) (collecting cases).\\n\\n 8\\n\\f2467 (2014). Thus an ESOP fiduciary, like any other ERISA fiduciary, must “discharge\\n\\nhis duties . . . with the care, skill, prudence, and diligence under the circumstances then\\n\\nprevailing that a prudent man acting in a like capacity and familiar with such matters\\n\\nwould use in the conduct of an enterprise of a like character and with like aims.” 29\\n\\nU.S.C. § 1104(a)(1)(B).\\n\\n Although these fiduciary duties “draw much of their content from the common law\\n\\nof trusts . . . ERISA’s standards and procedural protections partly reflect a congressional\\n\\ndetermination that the common law of trusts did not offer completely satisfactory\\n\\nprotection.” Tatum v. RJR Pension Inv. Comm., 761 F.3d 346, 357 (4th Cir. 2014)\\n\\n(internal quotation marks omitted). Courts apply the “prudent man rule . . . bearing in\\n\\nmind the special nature and purpose of employee benefit plans.” Id. (internal quotation\\n\\nmarks and alterations omitted). For this reason, “[t]he fiduciary obligations of the\\n\\ntrustees to the participants and beneficiaries [of an ERISA] plan are . . . the highest\\n\\nknown to the law.” Id. at 356 (alterations in original) (quoting Donovan v. Bierwith, 680\\n\\nF.2d 263, 272 n.8 (2d Cir. 1982)).\\n\\n Because an ESOP fiduciary that raises an affirmative defense under the § 1108(e)\\n\\nexception seeks to avoid ERISA liability for an otherwise prohibited transaction, the\\n\\nfiduciary bears the burden of proving by a preponderance of the evidence that the sale\\n\\nwas for adequate consideration. See Elmore v. Cone Mills Corp., 23 F.3d 855, 864 (4th\\n\\nCir. 1994) (en banc). “This burden is a heavy one.” Shay, 100 F.3d at 1488.\\n\\n B.\\n\\n With these principles in mind, we turn to the facts of this case.\\n\\n 9\\n\\f Since its inception, Constellis Group, Inc., the closely held parent company of a\\n\\ngroup of private security subsidiaries, has offered some form of deferred compensation to\\n\\nits employees, who are primarily retired members of the U.S. Armed Forces. Brundle I,\\n\\n241 F. Supp. 3d at 614. After initially offering a stock option program, Constellis\\n\\nreplaced that program with a profit-sharing plan in 2010. Id. In mid-2013, looking for an\\n\\n“exit strategy” after having twice tried and failed to effectuate a sale of the company, the\\n\\nowners of Constellis (hereinafter “the Sellers”) 3 began exploring the possibility of\\n\\ncreating an ESOP to purchase Constellis. Id. at 615.\\n\\n To that end, Constellis retained CSG International, an investment banking firm.\\n\\nCSG reported that sale of Constellis to an ESOP would not only enable the Sellers to\\n\\nliquidate their shares but would save them 23.8% in federal capital gains taxes. Id.\\n\\nAlthough noting that an ESOP would also benefit employees, CSG emphasized that\\n\\nselling Constellis to an ESOP provided the best option to optimize the Sellers’ after-tax\\n\\ncash return. See, e.g., id. at 616 (noting that CSG reported to the Sellers that, having\\n\\n“looked at every possible scenario,” it had not seen “any possible alternative that\\n\\nproduce[d] more after tax cash” than the proposed ESOP (internal quotation marks\\n\\nomitted)).\\n\\n CSG suggested that Constellis create what several trial witnesses characterized as\\n\\na “unique” ESOP structure to effectuate the sale. This unique structure would permit the\\n\\nSellers to retain de facto control of Constellis, even after the ESOP purchased all of the\\n\\n 3\\n Four individuals owned 77% of Constellis stock at the time of the sale at issue\\nhere. See Brundle I, 241 F. Supp. 3d at 615.\\n\\n 10\\n\\fcompany stock. Rather than sell 100% of their ownership interest to the ESOP, as is the\\n\\nusual practice, the Sellers would sell 90% of their shares to the ESOP and then exchange\\n\\nthe remaining 10% for “equity-like” warrants. These warrants would entitle the Sellers to\\n\\nbuy back equity in Constellis from the ESOP at a designated price and guarantee the\\n\\nSellers a majority on the board of directors. Id. at 626.\\n\\n To fund the ESOP’s purchase, Constellis would contribute 24% of the purchase\\n\\nprice and the ESOP would borrow the remainder from Constellis and the Sellers\\n\\nthemselves. Id. at 625. In late September 2013, Constellis decided to move forward with\\n\\nCSG’s proposal to create this unique ESOP. Id. To maximize the Sellers’ tax savings,\\n\\nConstellis had to complete the sale by the end of the calendar year. Id. at 622.\\n\\n On the recommendation of CSG, Constellis engaged Wilmington Trust, N.A., to\\n\\nserve as trustee for the ESOP. Id. at 616. In its role as trustee, Wilmington hired Stout\\n\\nRisius Ross (SRR) to be the financial advisor on the ESOP’s purchase of Constellis. Id.\\n\\nat 617. CSG, Wilmington, and SRR maintained significant long-term business\\n\\nrelationships, having worked together on more than twenty ESOP deals. Id. at 643\\n\\n(calling “the ESOP world . . . a very incestuous community”) (internal quotation marks\\n\\nomitted); id. at 617.\\n\\n On November 12, 2013, SRR submitted a draft valuation of Constellis stock to\\n\\nWilmington (the “SRR Report”). The SRR Report concluded that the fair market value\\n\\nfor a single share of Constellis stock lay between $3,865 and $4,600 — resulting in a\\n\\nrounded median price per share of $4,235. This placed the company’s worth, or its\\n\\n“enterprise value,” within a range of $275 to $330 million. Id. at 620–21. On November\\n\\n 11\\n\\f14, Wilmington met with analysts from SRR to discuss its report and valuation. At the\\n\\nmeeting’s conclusion, Wilmington set out to negotiate the ESOP’s purchase of Constellis\\n\\nwith authorization to offer a share price of $3,900 to $4,235. Id. at 622.\\n\\n The next day, Wilmington submitted an opening bid on behalf of the ESOP for\\n\\n$3,900 per share. Id. at 642. CSG, on behalf of Constellis, countered with $4,350 and\\n\\nsuggested to Wilmington that the ESOP and Constellis agree on a price first and then\\n\\nadjust the terms of the agreement at a later date. Wilmington agreed and raised its own\\n\\nbid to $4,100. CSG then countered with $4,250. By the end of the day, Wilmington and\\n\\nCSG had settled on a share price of $4,235 — the very top of Wilmington’s authorized\\n\\nnegotiation range. The negotiations lasted little more than five hours.\\n\\n The ESOP issued a tender offer for the shares on November 18 with a closing date\\n\\nof December 20. The parties finalized the term sheet on November 22. Between the\\n\\nconclusion of negotiations and the closing date for the transaction, SRR revised its\\n\\nvaluation of the draft enterprise range downward from $275–$330 million to $275–$325\\n\\nmillion, but the per share purchase price remained $4,235. On December 19, after\\n\\nmeeting with SRR for half an hour to discuss SRR’s valuation, Wilmington approved the\\n\\npurchase. Id. at 624. On December 20, the ESOP’s purchase of Constellis closed for a\\n\\nper share price of $4,235. Id. at 625.\\n\\n Subsequently, Tim P. Brundle, a former Constellis employee and ESOP\\n\\nparticipant, brought this action contending that Wilmington caused the ESOP to enter\\n\\n\\n\\n\\n 12\\n\\finto a transaction prohibited under ERISA § 1106. 4 Brundle alleged that the $4,235 per\\n\\nshare paid by the ESOP for Constellis was too high and resulted in the ESOP overpaying\\n\\nthe Sellers for the stock. The district court initially held that the 2013 purchase of\\n\\nConstellis by the ESOP constituted a prohibited transaction under § 1106(a)(1). Brundle\\n\\nv. Wilmington Tr., N.A., 2016 WL 6542718, at *12 (E.D. Va. Nov. 3, 2016). Wilmington\\n\\nconceded as much before the district court but raised the adequate-consideration\\n\\naffirmative defense available under § 1108(e)(1). Id.\\n\\n Following a bench trial, the district court issued meticulous factual findings and\\n\\nconcluded on the basis of those findings that Wilmington had not established the\\n\\n§ 1108(e) affirmative defense. Rather, the court found that Wilmington had violated its\\n\\nfiduciary duty to the ESOP. The district court concluded that Wilmington’s fiduciary\\n\\nfailures resulted in the ESOP overpaying for the Constellis stock by $29,773,250, and so\\n\\nawarded that amount to the ESOP as damages. Brundle I, 241 F. Supp. 3d at 613.\\n\\n Brundle then moved for attorneys’ fees. The court first ordered Wilmington to\\n\\npay attorneys’ fees pursuant to ERISA’s fee-shifting provision, 29 U.S.C. § 1132(g)(1),\\n\\nin the amount of $1,819,631.11. Brundle II, 258 F. Supp. 3d at 663–69. It subsequently\\n\\nawarded an additional $1.5 million in fees from the damages award.\\n\\n 4\\n Andrew Halldorson, another former Constellis employee and an ESOP\\nparticipant, filed the initial complaint against Wilmington. Halldorson later amended his\\ncomplaint to add Brundle as a named plaintiff. Both Halldorson and Brundle moved for\\nclass certification, which the district court denied. Following a motion for summary\\njudgment by Wilmington, the district court dismissed Halldorson because of a release he\\nsigned barring his suit against Wilmington. Halldorson appealed both his dismissal and\\nthe denial of class certification but later withdrew his appeal of the class certification\\nissue. Brundle did not timely appeal the denial of class certification.\\n\\n 13\\n\\f On appeal, Wilmington challenges the court’s liability and damages\\n\\ndeterminations and its award of $1.5 million in non-statutory attorneys’ fees. Brundle\\n\\ncross-appeals, challenging as inadequate the same portion of the attorneys’ fees award.\\n\\n\\n\\n II.\\n\\n Wilmington initially and principally contends that the district court erred in\\n\\nconcluding that it violated ERISA. Following a bench trial, we review a district court’s\\n\\nfactual findings for clear error and its legal conclusions de novo. Nat’l Fed’n of the Blind\\n\\nv. Lamone, 813 F.3d 494, 502 (4th Cir. 2016).\\n\\n At the outset of both its principal brief and its oral argument, Wilmington\\n\\nemphasized that there is no claim in this case that it acted in bad faith. But of course, an\\n\\nESOP participant seeking recovery from its fiduciary need not prove that the fiduciary\\n\\nacted in bad faith. Rather, an ESOP fiduciary is liable to the plan participants if it\\n\\nbreached its fiduciary duties, i.e., failed to act “solely in the interest of the participants,”\\n\\nwith the care, skill, prudence, and diligence used by a “prudent man acting in a like\\n\\ncapacity.” 29 U.S.C. § 1104(a) (emphasis added). Thus our focus is not on\\n\\nWilmington’s motives (good or bad) but on whether it acted “solely in the interest” of the\\n\\nplan participants, id., and “engaged in a reasoned decisionmaking process, consistent\\n\\nwith that of a prudent man in like capacity,” DiFelice v. U.S. Airways, Inc., 497 F.3d 410,\\n\\n420 (4th Cir. 2007) (internal quotation marks omitted); accord Tatum, 761 F.3d at 356.\\n\\nAs the Fifth Circuit has put it, “a pure heart and an empty head are not enough.”\\n\\nDonovan v. Cunningham, 716 F.2d 1455, 1467 (5th Cir. 1983).\\n\\n 14\\n\\f A.\\n\\n The district court found that because Wilmington failed to prove by a\\n\\npreponderance of the evidence that the ESOP’s purchase of Constellis was for adequate\\n\\nconsideration — and no more than adequate consideration — the transaction failed to\\n\\nqualify for the § 1108(e) affirmative defense. 5 In challenging this holding, Wilmington\\n\\nheavily relies on the valuation of Constellis stock submitted by its advisor, SRR.\\n\\n Expert advice, like an advisor’s independent valuation, can of course serve as\\n\\nevidence of prudence in the discharge of an ESOP trustee’s duties under § 1108(e). See\\n\\nBussian v. RJR Nabisco, Inc., 223 F.3d 286, 300–01 (5th Cir. 2000). But such advice “is\\n\\nnot a magic wand that fiduciaries may simply wave over a transaction to ensure that their\\n\\nresponsibilities are fulfilled.” Cunningham, 716 F.2d at 1474. Rather, a plan trustee\\n\\nmust at least show that it (1) “investigate[d] the expert’s qualifications,” (2) “provide[d]\\n\\nthe expert with complete and accurate information,” and (3) “[made] certain that reliance\\n\\non the expert’s advice was reasonably justified under the circumstances.” Shay, 100 F.3d\\n\\nat 1489. Because ERISA demands a high level of scrutiny from fiduciaries, a trustee\\n\\nmust prove that it considered these factors “and any others relevant under the particular\\n\\n\\n 5\\n For this defense to apply, in addition to being for adequate consideration, (1) the\\nsale or exchange must be of “qualifying employer securities,” (2) the trustee cannot\\ncharge a commission, and (3) the plan must qualify as “an eligible individual account\\nplan.” 29 U.S.C. § 1108(e).\\n All parties agree that the transaction here was for “qualifying employer securities.”\\nThey further agree that Wilmington did not charge a commission, and they do not dispute\\nthe district court’s finding that Wilmington’s fees were reasonable. See Brundle I, 241 F.\\nSupp. 3d at 617. The parties do contest, however, whether the ESOP qualifies as an\\n“eligible plan.” The district court did not reach this issue, nor do we.\\n\\n 15\\n\\fcircumstances it faced at the time of the decision,” and took care to avoid any identified\\n\\nconflicts of interest. See Bruister, 823 F.3d at 263 (internal quotation marks omitted).\\n\\n The district court properly recognized that the above legal principles guided its\\n\\ninquiry. The court then issued extensive factual findings in support of its conclusion that\\n\\nWilmington had “not demonstrated that its reliance on SRR’s [valuation] report was\\n\\n‘reasonably justified’ in light of all the circumstances because [Wilmington] ha[d] not\\n\\nshown that it thoroughly probed the gaps and internal inconsistencies in that report.”\\n\\nBrundle I, 241 F. Supp. 3d at 634.\\n\\n The court found Wilmington’s decision-making process inadequate in four major\\n\\nrespects. Id. It explained that “[a]lthough these failings independently” might not be\\n\\ndispositive, cumulatively they demonstrated that “Wilmington failed to meet its duty”\\n\\nunder ERISA, id., which, of course, includes the obligation to act “solely in the interest”\\n\\nof plan participants, 29 U.S.C. § 1104(a). Wilmington challenges the district court’s\\n\\nexhaustive findings of fact and conclusions of law as to each of the four designated\\n\\nfailures.\\n\\n 1.\\n\\n First, Wilmington maintains the district court erred in finding fault with\\n\\nWilmington’s failure to investigate SRR’s omission from its report of another, much\\n\\nlower, valuation of Constellis stock. That valuation, termed the “McLean Report” by the\\n\\nparties, had been completed just months earlier by the McLean Group, an investment\\n\\nbank that had regularly provided annual share valuations for Constellis. Brundle I, 241 F.\\n\\nSupp. 3d at 619, 634–35.\\n\\n 16\\n\\f Wilmington’s trial witnesses contended that consideration of the McLean Report\\n\\n“would not have been helpful because it was prepared with a different purpose in mind\\n\\n— the valuation of a single share” for stock options, rather than the valuation of a\\n\\ncontrolling interest for sale. Id. at 634–35. But the district court, relying on the\\n\\nuncontradicted testimony of a “highly credible” neutral expert, found that the two reports\\n\\nused “essentially the same methodology” despite being prepared for different purposes.\\n\\nId. at 635. Using that same methodology, the 2013 McLean Report estimated the per\\n\\nshare value of Constellis stock as $1,838.11, while SRR estimated its median per share\\n\\nvalue as $4,235. Id. at 619.\\n\\n Yet the SRR Report, which guided Wilmington as it evaluated the ESOP\\n\\ntransaction, did not even mention the McLean Report. And, although trial testimony\\n\\nestablished that at least one Wilmington official knew of the McLean Report, no one\\n\\nfrom Wilmington ever asked about it or questioned the vast discrepancy between two\\n\\nvaluations of the same company performed mere months apart. Id. at 634–35. The\\n\\ndistrict court concluded that a prudent fiduciary in Wilmington’s position would have\\n\\ninquired as to SRR’s omission. This was particularly so given that Constellis officers\\n\\ntestified that the company’s business prospects had not dramatically changed in the\\n\\nperiod between the two reports, and the SRR Report had referenced a different\\n\\n“valuation” older than McLean’s. 6\\n\\n\\n 6\\n Specifically, the SRR Report noted that in 2012 — a year before the McLean\\nReport’s publication — a private equity firm offered to buy Constellis for between $340\\nand $350 million. But rather than explain that the private equity firm then lowered its\\n(Continued)\\n 17\\n\\f Relying on trial evidence, the district court concluded that even a cursory review\\n\\nof the McLean Report would have raised questions as to whether the share valuation in\\n\\nthe SRR Report was too optimistic. The court did not find that the McLean Report\\n\\nnecessarily offered a more accurate picture of Constellis’s true value, but simply that a\\n\\nreasonably prudent fiduciary would have asked more questions. The court found that the\\n\\nanswers to these questions were “precisely the kinds of information that Wilmington, as\\n\\ntrustee, should have sought and evaluated” when considering the valuation of Constellis\\n\\nstock. Id. at 636. We see no reason to conclude otherwise.\\n\\n 2.\\n\\n The second major fault identified by the district court concerned Wilmington’s\\n\\nfailure to adequately probe the reliability of financial projections prepared by Constellis\\n\\nmanagement and used by SRR. Id. at 636–38. The court found that “the record show[ed]\\n\\nthat there were several red flags indicating that these projections were inflated, which\\n\\nWilmington either ignored or downplayed.” Id. at 636. Wilmington offers both general\\n\\nand specific challenges to this finding.\\n\\n First, Wilmington argues that Constellis management’s financial projections were,\\n\\nin fact, reliable and so required no probing. In support of this view, Wilmington contends\\n\\nthat because the McLean Report also utilized management’s financial projections to\\n\\n\\n\\n\\noffer to $275 million, see Brundle I, 241 F. Supp. 3d at 614–15, the report simply stated\\nthat the deal fell through due to the buyer’s “inability to secure sufficient financing.”\\n\\n 18\\n\\farrive at its own valuation of Constellis — a valuation the court treated as relevant — the\\n\\ncourt should have found the projections that the SRR Report used were also reliable.\\n\\n But although both McLean and SRR relied on financial projections prepared by\\n\\nConstellis management, they did not rely on the same financial projections. Id. at 638.\\n\\nThe projections that Constellis provided to SRR forecasted revenue over a much longer\\n\\ntime period, id. at 637–38, making them less accurate and less reliable. Further,\\n\\nConstellis management specifically prepared this set of projections for the purposes of\\n\\nSRR’s valuation in connection with the ESOP sale. This created a risk that Constellis\\n\\nmanagement might inflate its projections in response to incentives unique to the ESOP\\n\\nsale. Id. at 636. In light of these distinctions, the district court’s differing assessments of\\n\\nthe two reports’ comparative reliability were not inherently contradictory.\\n\\n At a more granular level, Wilmington maintains that each of the red flags that the\\n\\ndistrict court identified in Constellis’s financial projections are “non-existent.”\\n\\nWilmington Opening Br. 33–34, 38–39. Wilmington asserts largely factual, and\\n\\nuniversally unpersuasive, arguments in support of this view.\\n\\n Wilmington challenges the district court’s conclusion that Wilmington should\\n\\nhave been more critical of Constellis management’s financial projections because\\n\\nmanagement had a financial incentive to inflate the purchase price. The court found that\\n\\nthis initial red flag should have alerted Wilmington to probe the SRR valuation of\\n\\nConstellis. The district court’s finding on this issue primarily rested on the prospect of\\n\\nmanagement receiving 5% of the purchase price in cash bonuses — a factual\\n\\ndetermination well supported by the record. See Brundle I, 241 F. Supp. 3d at 636.\\n\\n 19\\n\\f The district court also identified as a red flag an ongoing government investigation\\n\\ninto accounting and record-keeping errors by Constellis, which the court concluded\\n\\n“should have raised questions about the reliability of Constellis’[s] . . . projections.” Id.\\n\\nAgain, contrary to Wilmington’s suggestion, we see no basis for holding this finding\\n\\nclearly erroneous. A government investigation into errors of this nature surely creates a\\n\\nquestion as to the reliability of a company’s financial projections, which a reasonably\\n\\nprudent fiduciary representing the buyers of the company should probe further. Cf.\\n\\nKeach v. U.S. Tr. Co., 419 F.3d 626, 633–37 (7th Cir. 2005) (finding ESOP trustee met\\n\\nfiduciary duty when it “analyzed exhaustively [the company’s] financials, had conducted\\n\\nindependent valuation analyses and had challenged the financial forecasts made by [the\\n\\ncompany’s] management as too optimistic”).\\n\\n Still another red flag to which Wilmington, in the district court’s view, did “not\\n\\nadequately respond was the riskiness of Constellis’[s] contract concentration.” Brundle I,\\n\\n241 F. Supp. 3d at 637. The district court believed that this risk called for Wilmington to\\n\\napply further scrutiny to the company’s financial projections. The court found, and\\n\\nWilmington does not dispute, that at the time of the ESOP sale, about 70% of Constellis’s\\n\\nrevenue depended on just two government contracts. Id. at 637. Yet Wilmington\\n\\nadopted a valuation that assumed Constellis stock posed significantly less risk than the\\n\\nstock market as a whole. Again relying on the trial testimony of a “neutral” and “highly\\n\\ncredible” third party expert, the court explained its conclusion that Constellis’s industry\\n\\npeers — namely, government contractors — are certainly “no less risky than the market\\n\\nas a whole.” Brundle II, 258 F. Supp. 3d at 663. And again, the record offers ample\\n\\n 20\\n\\fsupport for this finding. See Brundle I, 241 F. Supp. 3d at 637; Brundle II, 258 F. Supp.\\n\\n3d at 662–63. 7\\n\\n Wilmington also maintains that the district court unfairly characterized\\n\\nConstellis’s “multiple sets of projections” as a red flag. Wilmington claims that the\\n\\ndistrict court ignored the fact that SRR advised Wilmington that the market and\\n\\nConstellis had changed throughout 2013. But the court adequately addressed this\\n\\nargument, see Brundle I, 241 F. Supp. 3d at 635–36, and we defer to its factual finding\\n\\nthat the changes in the market and Constellis’s business prospects throughout 2013 did\\n\\nnot justify multiple sets of projections.\\n\\n Last, Wilmington contends that we should reverse the district court due to its\\n\\ninitially erroneous understanding of the warranties Wilmington obtained to indemnify the\\n\\nESOP against the ongoing government investigation. At first, the court incorrectly found\\n\\n 7\\n The court acknowledged that it originally had misunderstood the definition of the\\nrisk factor, called “beta,” that SRR used in its report. SRR chose a beta of 0.7, indicating\\nthat Constellis stock was less risky than the average stock (set at a beta of 1.0). The court\\nhad understood beta to measure the risk of Constellis stock relative to its industry peers,\\nbut beta actually measures the risk of a company’s stock — or in the case of a privately\\nheld company like Constellis, the risk of a company’s publicly traded industry peers —\\nrelative to the stock market as a whole. Brundle II, 258 F. Supp. 3d at 658.\\n Upon consideration of Wilmington’s Rule 59 motion, the court stood by its\\noriginal conclusion that Wilmington had inappropriately chosen a beta indicating that\\nConstellis was less risky than other stocks. The court concluded that a neutral beta of 1.0\\nwas more appropriate, noting that “[e]ven if government contracting business [in which\\nConstellis participates] does not fluctuate in correlation with the market, that does not\\nmean that government contracting is necessarily more stable.” Id. at 663. The court\\nnoted that a Wilmington trial witness had acknowledged that “the government contracting\\nindustry” is at times “less stable than the market as a whole.” Id. The court further relied\\non the “most credible” neutral expert’s testimony that the public companies used by SRR\\nto measure beta were “not a good match for Constellis.” Id. We see no clear error in\\nthese findings.\\n\\n 21\\n\\fthat only Constellis had indemnified the ESOP, thus creating an illusory form of\\n\\nindemnification. But in denying Wilmington’s Rule 59 motion, the court candidly\\n\\naddressed that error and acknowledged that, in fact, both Constellis and the Sellers had\\n\\nindemnified the ESOP. Brundle II, 258 F. Supp. 3d at 656. Nonetheless, the court found\\n\\nthat its “corrected understanding [did] not alter [its] conclusions about . . . Wilmington’s\\n\\ninadequate investigation into the soundness of Constellis’[s] financial projections.” Id.\\n\\nThe court explained that, “[e]ven omitting its erroneous view of the Sellers’ . . .\\n\\nwarranties,” Wilmington failed to rebut the many red flags discussed above, each of\\n\\nwhich independently called for more robust due diligence by Wilmington. Id. at 656–57.\\n\\nFor the reasons we have explained above, we find no clear error in any of these findings\\n\\nand so reject this final argument from Wilmington as to Constellis management’s\\n\\nfinancial projections.\\n\\n 3.\\n\\n The district court found that Wilmington’s third major failure in ensuring that its\\n\\nreliance on the SRR valuation was reasonably justified occurred when it “did not\\n\\ninvestigate the appropriateness of applying a 10% control premium” to Constellis stock\\n\\nand “fail[ed] to discount the [valuation] for lack of control.” Brundle I, 241 F. Supp. 3d\\n\\nat 638.\\n\\n Purchasers will generally pay more for “rights associated with control of the\\n\\nenterprise.” Estate of Godley v. Comm’r, 286 F.3d 210, 214 (4th Cir. 2002). We have\\n\\ndefined “control” as “an interest which allows the shareholder to unilaterally direct\\n\\ncorporate action, select management, decide the amount of distribution, rearrange the\\n\\n 22\\n\\fcorporation’s capital structure, and decide whether to liquidate, merge, or sell assets.” Id.\\n\\nat 215 (internal quotation marks omitted).\\n\\n The district court recognized that the ESOP had “powers beyond those of an\\n\\nordinary shareholder.” Brundle I, 241 F. Supp. 3d at 627 n.23. But the court nonetheless\\n\\nfound that the “ESOP essentially had no power to control Constellis” as a result of the\\n\\ntransaction’s unique structure. Id. at 638–39. Accordingly, the court concluded that\\n\\nWilmington erred in failing to investigate the SRR valuation, which not only failed to\\n\\ndiscount the stock for lack of control, but even added a 10% control premium to the value\\n\\nof the Constellis stock. The record supports both findings.\\n\\n The Sellers retained the power to appoint a majority of the Constellis board, a key\\n\\nindicator of control. See id. at 626. Further, the ESOP governing plan document and the\\n\\nESOP trust agreement each required Wilmington to vote its shares as the Constellis\\n\\nboard (not the ESOP) directed. See id. at 626–27. Wilmington maintains that the ESOP\\n\\ncould independently exercise its voting powers because the plan documents included a\\n\\nclause nullifying any provision that violated ERISA. But Constellis’s general counsel\\n\\ntestified at trial that the ESOP could only contravene the plan documents and exercise its\\n\\nindependent voting authority by filing a lawsuit — the same limited relief available to a\\n\\nminority shareholder. The district court thus concluded that Wilmington breached its\\n\\nfiduciary obligation in failing to question SRR’s failure to discount for lack of control.\\n\\nSee id. at 639. Given the record evidence that the ESOP’s unique ownership structure\\n\\nwas intentionally designed to maintain the Sellers’ control over Constellis even after\\n\\nselling their shares, the district court’s conclusion hardly constitutes clear error.\\n\\n 23\\n\\f Wilmington next contends that even if the ESOP lacked control, a 10% control\\n\\npremium was justified by the fact that the ESOP owned 100% of Constellis shares and\\n\\nobtained “elements of control.” Id. at 647. Wilmington argues that SRR reasonably\\n\\napplied a “modest” 10% control premium given that market control premiums are often\\n\\nbetween 35–40%. But in light of the limited rights provided to the ESOP, we cannot\\n\\nconclude that the district court erred in finding that Wilmington should have done more\\n\\nto challenge the use of any control premium. The SRR Report “devoted just one sentence\\n\\nto articulating its decision,” yet Wilmington never asked SRR about its decision to apply\\n\\na control premium. Id. at 639. For an assumption that carried such weighty\\n\\nconsequences, we cannot say that the district court clearly erred in finding that a\\n\\nreasonably prudent fiduciary would have probed the issue further.\\n\\n 4.\\n\\n The final major fault that the district court identified in Wilmington’s reliance on\\n\\nthe SRR Report was Wilmington’s failure to probe why SRR consistently rounded the\\n\\nvaluation of Constellis stock upwards. This repeatedly increased the price the ESOP had\\n\\nto pay for the stock. The district court concluded that because an ESOP fiduciary should\\n\\nbe concerned with achieving the lowest possible price for the ESOP, Wilmington ought\\n\\nto have asked why SRR consistently engaged in the upward rounding to the ESOP’s\\n\\ndetriment. Id. at 639–40.\\n\\n Wilmington devotes only a short footnote in its opening brief to this issue and fails\\n\\nto address it at all in its reply brief. It thus appears to have forfeited an appellate\\n\\nchallenge to the court’s findings on this issue. See Wahi v. Charleston Area Med. Ctr.,\\n\\n 24\\n\\fInc., 562 F.3d 599, 607 (4th Cir. 2009) (finding argument raised only in a footnote in\\n\\nappellant’s opening brief forfeited on appeal). Perhaps this is because the district court’s\\n\\nfinding is self-evidently correct. And, as the district court noted, Brundle I, 241 F. Supp.\\n\\n3d at 640, this conclusion accords with those of other courts. For example, the Sixth\\n\\nCircuit described a similar rounding practice as “extremely disconcerting” and noted that\\n\\nthis conduct, although not dispositive, was illustrative of lackluster due diligence\\n\\ndisplayed throughout the transaction process. Chao, 285 F.3d at 433–34. So too here.\\n\\n B.\\n\\n Apart from Wilmington’s four major failures to scrutinize SRR’s report, the\\n\\ndistrict court also found that Wilmington’s conduct throughout the transaction provided\\n\\nfurther evidence that Wilmington failed to act as a prudent fiduciary solely on behalf of\\n\\nthe ESOP participants. Although the court found that Wilmington’s actions on behalf of\\n\\nthe ESOP did not amount to bad faith, it recognized that “ERISA demand[ed] more to\\n\\nexcuse a fiduciary from liability.” Brundle I, 241 F. Supp. 3d at 643.\\n\\n The district court found that Constellis’s principal motivation for creating the\\n\\nESOP was to further the Sellers’ interests, not the interests of the ESOP participant\\n\\nbuyers. Id. at 616. The sale of Constellis to the ESOP enabled the Sellers to cash out\\n\\ntheir company stock, which they had tried and failed to accomplish several times, and to\\n\\nreap substantial tax savings. Moreover, the ESOP’s unique structure enabled the Sellers\\n\\nto avoid the downside risk of holding equity, yet profit from any upside, while also\\n\\nretaining control over the company. The court found that Wilmington, in its role as the\\n\\n\\n\\n 25\\n\\fESOP’s fiduciary, simply ignored these motivations rather than investigating whether\\n\\nthey affected the ESOP’s legality under ERISA. Id. at 640–42.\\n\\n The district court additionally found that making the Sellers’ interests paramount\\n\\nshortened the transaction timeline and rushed Wilmington’s due diligence process and\\n\\nprice and terms negotiations. To maximize the after-tax benefits to the Sellers, the ESOP\\n\\nsale had to conclude before the end of 2013. Accordingly, Wilmington and its agents\\n\\ncompleted their due diligence, made pricing decisions, conducted negotiations, and\\n\\nlaunched a tender offer in less than two months. Id. at 621–25. Wilmington employees\\n\\nmet to discuss the transaction only three times and met with Constellis management just\\n\\nonce. Id. at 642. All meetings lasted less than 90 minutes and several of Wilmington’s\\n\\nteam members were absent from each. Id. And the district court found that Wilmington\\n\\nviolated its own policy by repeatedly taking less than 48 hours between receiving a\\n\\nvaluation report and meeting to discuss it. Id. at 621, 625. The court concluded that this\\n\\ntype of conduct fell well short of the diligence expected of a prudent fiduciary. Id. at\\n\\n643.\\n\\n Finally, the court noted that “Wilmington’s lack of engagement and willingness to\\n\\nnegotiate so favorably with CSG may have been motivated by its significant business\\n\\nrelationship with CSG.” Id. The district court found that Wilmington, CSG, and SRR\\n\\nmaintained extensive and lucrative business relationships and that SRR was willing to\\n\\ndiscuss its valuation strategies with CSG while negotiations were ongoing. Id. The\\n\\nrecord offers ample support for all of these findings.\\n\\n\\n\\n 26\\n\\f C.\\n\\n Wilmington also maintains that the district court erred in finding that the value of\\n\\nStock Appreciation Rights (SARs) issued in connection with the ESOP’s purchase of\\n\\nConstellis should have been deducted from Constellis’s equity value for purposes of\\n\\nSRR’s valuation. SARs are incentives that Constellis would have owed to management\\n\\nhad the company’s value reached a certain price by a particular date. Wilmington argues\\n\\nthe value of the SARs should not have been deducted from Constellis’s estimated value\\n\\nbecause they were inchoate at the time of the sale. The district court disagreed and found\\n\\nthat, because Constellis intended for the SARs to be issued, their value should have been\\n\\ndeducted from Constellis’s equity value. Id. at 648.\\n\\n Wilmington rehashes the same argument on appeal but fails to identify any\\n\\nevidence that demonstrates the district court clearly erred in this factual determination.\\n\\nBecause we discern no such evidence, we reject this claim.\\n\\n D.\\n\\n In support of its final attack on the district court’s liability findings, Wilmington\\n\\nrelies on the ESOP’s subsequent sale of Constellis stock to ACADEMI LLC.\\n\\n In early February 2014, less than two months after the ESOP transaction,\\n\\nACADEMI, a major competitor in the private security market, began talks with\\n\\nConstellis management to acquire the company. Id. at 628. Initially, ACADEMI offered\\n\\nto purchase Constellis at an enterprise value of $283.3 million, in a transaction that would\\n\\nresult in $10 million in cash going to the ESOP. Seeking a better offer on the ESOP’s\\n\\nbehalf, Wilmington entered into negotiations with Constellis, the Sellers, and\\n\\n 27\\n\\fACADEMI. Id. at 629. Wilmington’s efforts proved successful: the final transaction,\\n\\nwhich closed on July 25, 2014, effectuated a sale of all the Constellis stock to ACADEMI\\n\\nat an implied enterprise value of $288.3 million. Id. at 631. The final transaction paid\\n\\n$20 million in cash to the ESOP — double the initial $10 million offer — as a result of\\n\\nthe Sellers’ agreeing to write off $33 million of the ESOP’s debt. Id. at 629.\\n\\n Wilmington argues that the ACADEMI sale proves that the ESOP did not overpay\\n\\nfor Constellis seven months earlier. Relying on the first prong of DOL’s proposed\\n\\nadequate-consideration regulations, Wilmington maintains that the ESOP paid “fair\\n\\nmarket value” for the Constellis stock because ACADEMI’s purchase of Constellis stock\\n\\nimplied an enterprise value of $288.3 million, which was within SRR’s estimated range\\n\\nof $275 to $330 million. Wilmington contends this purchase price is of particular\\n\\nsignificance because in the intervening time Constellis assertedly suffered several\\n\\nbusiness setbacks that decreased its enterprise value. 8\\n\\n This argument is unpersuasive for several reasons. The proposed DOL regulations\\n\\nupon which Wilmington relies provide that a trustee can prove consideration is\\n\\n“adequate” if it reflects the stock’s “fair market value” and is “the product of a\\n\\ndetermination made by the fiduciary in good faith.” Proposed Regulation Relating to the\\n\\n\\n 8\\n The district court carefully considered and described these setbacks in detail. See\\nBrundle I, 241 F. Supp. 3d at 627–28. Briefly, the State Department made a formal\\ndemand for payment of $62.2 million as part of its audit of Constellis’s accounting and\\nrecord-keeping practices; Constellis was forced to reduce projected revenue from a\\ncontract in Iraq by more than $100 million and push the remaining revenue further into\\nthe future; its projected revenue from a contract in Kuwait decreased by tens of millions\\nof dollars; and it lost a $338 million contract in Germany it had expected to win. Id.\\n\\n 28\\n\\fDefinition of Adequate Consideration, 53 Fed. Reg. at 17,633. Of course, because the\\n\\nDOL never enacted the proposed regulations, they are not binding. And, as we have\\n\\nexplained, courts look to the conduct of the trustee and whether it met its fiduciary\\n\\nobligations, not to whether the trustee arrived at a “fair” value. But even if we were to\\n\\nadopt the DOL’s proposed regulations, a trustee must satisfy both parts of the test to\\n\\nbenefit from the adequate consideration exception. See id. Assuming arguendo that the\\n\\npurchase was for “fair market value,” we find no error in the district court’s findings that\\n\\nWilmington failed to prove that the share price was also “the product of a determination\\n\\nmade by the fiduciary in good faith.”\\n\\n Furthermore, even if proving the ESOP paid “fair market value” sufficed to meet\\n\\nthe requirements of § 1108(e), the facts of the ACADEMI sale do not prove that the\\n\\nESOP paid only “fair market value” here. In fact, the district court found that the\\n\\nopposite was true. The court found that because ACADEMI, a private security company\\n\\nlike Constellis, would benefit from synergies resulting from its purchase of Constellis, it\\n\\nwould have been willing to pay significantly more for Constellis than the ESOP. Thus,\\n\\nthat ACADEMI actually paid less for Constellis stock suggested a significantly lower fair\\n\\nmarket value for the stock at the time of the ESOP purchase. Of course, Wilmington’s\\n\\nexperts disagreed with this synergies analysis, but the district court found the testimony\\n\\nof other experts on this point more persuasive. Brundle I, 241 F. Supp. 3d at 640. The\\n\\nrecord provides no basis to reject this finding. See Hendricks v. Cent. Reserve Life Ins.\\n\\nCo., 39 F.3d 507, 513 (4th Cir. 1994) (“An appellate court should be especially reluctant\\n\\n\\n\\n 29\\n\\fto set aside a finding based on the trial court’s evaluation of conflicting expert\\n\\ntestimony.”).\\n\\n In sum, the district court found that the ACADEMI sale did not constitute a\\n\\nmeaningful comparator. Discounting the additional synergy value, the $33 million debt\\n\\nwrite-off by the Sellers, and an expected tax refund from the sale, the court found the\\n\\nACADEMI purchase suggested that Constellis’s fair market value was closer to $200\\n\\nmillion — almost $100 million less than the enterprise value implied by the ESOP\\n\\ntransaction. Thus, the court found, the ACADEMI sale could not support Wilmington’s\\n\\nargument that the ESOP paid no more than adequate consideration for Constellis.\\n\\nBrundle I, 241 F. Supp. 3d at 640. We see no clear error in this conclusion.\\n\\n Additionally, we note that, despite paying more for Constellis stock, the ESOP did\\n\\nnot obtain nearly the level of control that ACADEMI acquired. While the ESOP\\n\\nobtained only some elements of control, ACADEMI acquired absolute and uncontested\\n\\ncontrol. Had the district court applied the “standard” 35–40% control premium\\n\\nWilmington’s experts suggested was reasonable, Constellis’s fair market value would fall\\n\\nsomewhere between $145 million and $150 million, almost half the value of the stock\\n\\npurchased by the ESOP only months earlier.\\n\\n\\n\\n III.\\n\\n Having rejected all of Wilmington’s challenges to the district court’s findings as to\\n\\nits liability, we turn to the court’s damages award. The district court concluded that\\n\\nWilmington’s fiduciary failures inflated the price the ESOP paid for Constellis stock by\\n\\n 30\\n\\f$29,773,250. “We review factual findings relating to the calculation of damages for clear\\n\\nerror.” Simms v. United States, 839 F.3d 364, 368 (4th Cir. 2016).\\n\\n A.\\n\\n To calculate the loss to an ESOP and compensate it for a fiduciary’s ERISA\\n\\nviolation, a court typically subtracts the stock’s fair market value, as determined by the\\n\\ncourt, from the inflated price paid by the ESOP. See Bruister, 823 F.3d at 265 (collecting\\n\\ncases). The district court precisely followed this approach. The court used as a baseline\\n\\nthe comprehensive damages estimate provided by Brundle’s expert — the only expert to\\n\\noffer one. 9 The court then considered the flaws in this valuation raised by Wilmington\\n\\nand made “appropriate adjustments based on the evidence adduced at trial and the\\n\\nrelative credibility of the experts.” Brundle I, 241 F. Supp. 3d at 645.\\n\\n Brundle’s expert estimated Wilmington’s lack of due diligence had caused the\\n\\nESOP to overpay for the Constellis stock by almost $103,862,000. But the district court\\n\\ndid not accept this figure. Instead, it independently analyzed each of Wilmington’s\\n\\npurported failings, considered the relevant trial testimony, and then awarded $29,773,250\\n\\n— or less than a third of the expert’s estimation — as damages. Id. at 645–49. The\\n\\nfollowing chart summarizes the district court’s damages findings:\\n\\n Error Difference between fair market value and\\n inflated price paid by ESOP (Damages)\\n Reliance on Management’s $4,325,000\\n Growth Projections\\n Use of .07 Beta $2,936,000\\n\\n 9\\n The Fifth Circuit held, in another ESOP case involving this same expert, that a\\ntrial court “was entitled to credit” his valuation methodology. Bruister, 823 F.3d at 267.\\n\\n 31\\n\\f Inclusion of Control Premium $8,186,000\\n Failure to Include Lack of $9,715,250\\n Control Discount\\n Stock Appreciation Rights $1,611,000\\n Rounding $3,000,000\\n Total Damages $29,773,250\\n\\n Wilmington did not provide the district court with an alternative damages\\n\\ncalculation or offer any evidence that the court could use to devise its own. At oral\\n\\nargument before us, Wilmington conceded as much. Accordingly, it has forfeited its\\n\\nchallenge to the methodology used by the district court when calculating the damages\\n\\naward. See Exxon Shipping Co. v. Baker, 554 U.S. 471, 487 n.6 (2008) (“[W]aiver and\\n\\nforfeiture rules . . . ensure that parties can determine when an issue is out of the case, and\\n\\nthat litigation remains, to the extent possible, an orderly progression.”).\\n\\n Moreover, Wilmington’s principal basis for urging reversal of the damages award\\n\\nconsists of a repetition of its challenge to the district court’s liability findings. Given our\\n\\naffirmance of all the district court’s liability findings — that Wilmington failed to\\n\\nadequately investigate and probe SRR as to the omission of the McLean Report, the use\\n\\nof Constellis management’s growth projections, the 0.7 beta, the 10% control premium,\\n\\nimproper rounding up, and SARs — that challenge fails.\\n\\n B.\\n\\n Wilmington additionally contends that the district court erred in declining to offset\\n\\nits damages calculation by the $20 million in cash that the ESOP received as a result of\\n\\nthe ACADEMI sale. According to Wilmington, “the district court’s failure to” do so\\n\\n“resulted in a clear windfall for the ESOP.” Wilmington Opening Br. at 53. As the\\n\\n 32\\n\\fdistrict court ably explained, see Brundle II, 258 F. Supp. 3d at 660–62, this claim is\\n\\nmeritless.\\n\\n ERISA expressly requires a fiduciary to “make good to [an ESOP] any losses”\\n\\nresulting from a given breach of duty. 29 U.S.C. § 1109(a); cf. Restatement (Second) of\\n\\nTrusts § 205 cmt. e (“If the trustee is authorized to purchase property for the trust, but in\\n\\nbreach of trust he pays more than he should pay, he is chargeable with the amount he paid\\n\\nin excess of its value.”). Thus, in cases involving overpayment for ESOP assets, courts\\n\\ngenerally compute restitution damages exactly as the district court did here: by deducting\\n\\nthe fair market value of the stock from the amount the ESOP actually paid.\\n\\n Wilmington insists that the ESOP’s subsequent and unrelated sale of the stock to\\n\\nACADEMI requires a different result. This misapprehends the nature of the breach. If\\n\\nWilmington had breached its duty by purchasing Constellis stock at all, then a damages\\n\\naward consisting of the purchase payments offset by any subsequent profits would indeed\\n\\nreturn the participants to the pre-purchase status quo.\\n\\n But Wilmington breached here by overpaying for the Constellis stock. Principles\\n\\nof restitution therefore entitle the ESOP and its participants to compensation for the loss\\n\\nfrom the overpayment. Any subsequent gains involving the stock, which the ESOP\\n\\nwould have obtained regardless of the overpayment, have no bearing on that loss. For\\n\\nthis very reason, courts have uniformly rejected analogous offsets to damage awards in\\n\\noverpayment cases. See, e.g., Bruister, 823 F.3d at 270–71 (rejecting offset to account\\n\\nfor unpaid or forgiven ESOP debt and noting that “[e]very court to consider this\\n\\nquestion” agreed); Henry v. U.S. Trust Co. of Cal., N.A., 569 F.3d 96, 98–100 (2d Cir.\\n\\n 33\\n\\f2009) (“Henry V”) (“If an investor pays $100 for 20 shares of stock and later sells those\\n\\nshares back to the original seller for $25, the result is not that the investor paid only $75\\n\\nfor the shares.”).\\n\\n Even so, Wilmington asserts that the events in this case resulted in “pure gain” to\\n\\nthe ESOP, justifying a deviation from this rule. It claims the ESOP “made $20 million\\n\\nfor the nominal cost of carrying $200 million in non-recourse debt for a few months,”\\n\\nbecause “[j]ust seven months” after the prohibited transaction, “the ESOP exchanged its\\n\\ndebt-burdened shares to ACADEMI for $20 million in cash.” Wilmington Opening Br.\\n\\nat 55–56. We disagree. As a preliminary matter, the burden imposed in additional debt\\n\\nfrom a $30 million overpayment is far from “nominal,” even for “just” seven months.\\n\\nSee Henry V, 569 F.3d at 99 n.4 (explaining “the obvious fact that the assumption of\\n\\nindebtedness has immediate legal and economic consequences even before the borrower\\n\\nbegins to repay the debt”).\\n\\n Moreover, if Wilmington seeks to portray the ACADEMI sale as an “exchange” in\\n\\nwhich the ESOP’s pre-sale debt had no effect on its post-sale assets, this is both illogical\\n\\nand untrue. Had the ESOP not initially overpaid for the stock by $30 million, it would\\n\\nhave shouldered tens of millions of dollars less in debt; in turn, it would presumably have\\n\\nbeen tens of millions of dollars better off after being compensated for the stock in the\\n\\nACADEMI sale. Put differently, although the ESOP benefited despite the breach, it\\n\\nwould have benefited at least as much — but ended in a far better position — without the\\n\\nbreach. In fact, had the ESOP initially paid a fair (lower) value for the Constellis stock\\n\\n\\n\\n 34\\n\\fand therefore carried less debt, it would have entered the ACADEMI negotiations in a\\n\\nstronger bargaining position and may have profited further still.\\n\\n Wilmington rejects this conclusion, stressing that the Sellers also agreed to write\\n\\noff more than $30 million of the ESOP’s debt, which it describes as an “effective[]\\n\\nreduc[tion]” of the 2013 purchase price. Wilmington Opening Br. at 56. But once again,\\n\\nthis independent act has no bearing on the ESOP’s loss.\\n\\n Wilmington unpersuasively contends that Henry III supports its argument. That\\n\\ncase addressed very different facts. There, the Second Circuit held that — where sellers\\n\\nfully and voluntarily repaid an ESOP after the IRS found overpayment, but before a court\\n\\nentered a damages judgment — a duplicative recovery for the same overpayment might\\n\\n“result in a windfall.” Henry III, 445 F.3d at 624. Wilmington does not even argue that\\n\\nthe Sellers’ write-off here was meant to remedy the ESOP’s overpayment. Nor could it:\\n\\nunlike the midstream repayment in Henry, the write-off here occurred more than a year\\n\\nprior to the initiation of any legal proceedings alleging Wilmington breached its fiduciary\\n\\nduties. As Wilmington concedes, the write-off was part of a negotiated agreement to\\n\\nclose the ACADEMI sale, a deal wholly unrelated to the issues raised here. Again, it is\\n\\nreasonable to assume that the ESOP would have negotiated equally favorable (if not more\\n\\nfavorable) terms had it paid a fair value in the first instance and thus entered the\\n\\nACADEMI discussions with substantially less debt.\\n\\n In sum, we find no error in the district court’s damages award.\\n\\n\\n\\n\\n 35\\n\\f IV.\\n\\n Finally, we examine the district court’s award of attorneys’ fees. The court\\n\\nawarded Brundle’s counsel $1,819,631.11 in statutory fees and an additional $1.5 million\\n\\nin fees from the ESOP’s damages judgment. No party has presented a substantive\\n\\nchallenge regarding the award of attorneys’ fees under the fee shifting statute. 10 Brundle\\n\\nchallenges the $1.5 million in additional fees (payable from the damages awarded to the\\n\\nESOP) as too small; Wilmington and Constellis, as fiduciaries for the ESOP, challenge\\n\\nthe award as legally improper. We review that award for abuse of discretion, mindful\\n\\nthat our review “is sharply circumscribed, and a fee award must not be overturned unless\\n\\nit is clearly wrong.” Berry v. Schulman, 807 F.3d 600, 617 (4th Cir. 2015) (internal\\n\\nquotation marks omitted).\\n\\n A.\\n\\n We first consider Brundle’s claim that the district court abused its discretion by\\n\\nnot awarding his counsel, Bailey & Glasser, LLP (B&G), a total of $9.9 million in fees\\n\\nunder the firm’s one-third contingent fee agreement with Brundle himself. The district\\n\\ncourt initially suggested that this arrangement was indeed controlling. See Brundle II,\\n\\n258 F. Supp. 3d at 671–72. But the court held its fee decision in abeyance to consider the\\n\\n\\n 10\\n Strangely, although Brundle does not challenge the statutory fee award, he does\\nsummarily contend that he is entitled to $643,584.50 in expenses (the amount he\\nrequested when seeking statutory fees in the district court). The district court denied his\\nrequest for expenses, explaining that it was insufficiently documented. See Brundle II,\\n258 F. Supp. 3d at 669. Before us, Brundle provides neither documentation nor\\nargument. Accordingly, to the extent he even appeals the denial of expenses, we affirm\\nthe district court.\\n\\n 36\\n\\fviews of plan participants and ultimately based its award on equity rather than contract.\\n\\nWe can hardly find an abuse of discretion given that Brundle has no right to have the\\n\\nESOP fund his own fee agreement with B&G.\\n\\n Brundle contends that 29 U.S.C. § 1132(a)(2) — which empowers ESOP\\n\\nparticipants and beneficiaries to bring suit on behalf of an ESOP — additionally\\n\\nauthorizes him to enter into a legal services contract that binds the ESOP. Brundle\\n\\nmusters no caselaw to support his interpretation of the statute, and for good reason.\\n\\nWhile § 1132(a)(2) provides Brundle the right to sue on behalf of the ESOP, neither it\\n\\nnor any other statute authorizes him to unilaterally bind the ESOP to a contract or fee\\n\\nagreement. For this very reason, the vast majority of suits on behalf of ERISA plans take\\n\\nthe form of class actions, in which counsel can seek fees only after a class has been\\n\\ncertified and class members have been given the opportunity to object or opt out. Though\\n\\nB&G has a valid contingent fee agreement with Brundle, see Venegas v. Mitchell, 495\\n\\nU.S. 82 (1990), it does not have a fee agreement with the ESOP.\\n\\n As a result, only equity provides any possible basis for a fee award in addition to\\n\\nthe statutory fees awarded.\\n\\n B.\\n\\n After the district court received the views of some plan participants, it issued a\\n\\nfinal judgment awarding B&G $1.5 million in “addition[]” to the $1.8 million in statutory\\n\\n\\n\\n\\n 37\\n\\ffees — not as a contractual right, but as “a partial common fund award.” 11 Wilmington\\n\\nand Constellis assert that a trio of ERISA provisions precluded the court from awarding\\n\\nany common fund recovery. Unlike most challenges to fee awards, we review de novo\\n\\nquestions regarding a court’s legal authority. See, e.g., Country Vintner of N.C., LLC v. E\\n\\n& J. Gallo Winery, Inc., 718 F.3d 249, 254 (4th Cir. 2013).\\n\\n First, Wilmington and Constellis contend that any common fund award here would\\n\\nviolate ERISA’s “anti-alienation” and “exclusive benefit” provisions. See 29 U.S.C.\\n\\n§ 1056(d)(1) (providing that benefits under retirement plans cannot be “assigned or\\n\\nalienated”); id. § 1103(c)(1) (directing all “assets of a plan” to be “held for the exclusive\\n\\npurposes of providing benefits to participants in the plan and their beneficiaries and\\n\\ndefraying reasonable expenses of administering the plan”). But the district court properly\\n\\nrejected this argument, concluding that because the plan administrator did not yet possess\\n\\nthe damages award — in other words, the court still had jurisdiction over the funds and\\n\\nhad not distributed them to the ESOP — it could not be considered a plan asset. Brundle\\n\\nII, 258 F. Supp. 3d at 670. Of course, if the ESOP had received payment of the award,\\n\\nthose funds would have been subject to ERISA’s duties and protections. See Wilmington\\n\\n\\n 11\\n The district court made clear, and the parties do not dispute, that “[i]n granting\\nboth fee-shifting and contingent fee awards, . . . the contingent fee award must be offset\\nby the amount awarded under the fee-shifting provision.” Brundle II, 258 F. Supp. 3d at\\n672 & n.19. On appeal, Brundle seeks a total of approximately $9.9 million in fees plus\\nabout $650,000 in purported expenses, which (when offset by the $1.8 million in\\nstatutory fees paid by Wilmington) would entitle B&G to a net of approximately $8.8\\nmillion from the common fund. The district court instead awarded Brundle a net of only\\n$1.5 million in fees from the common fund, which it noted was in “addition[]” to the $1.8\\nmillion statutory fee-shifting award, for a total of $3.3 million in fees.\\n\\n 38\\n\\fShipping Co. v. New England Life Ins. Co., 496 F.3d 326, 333 (4th Cir. 2007). But where\\n\\na fund is still under the jurisdiction of the district court, the court may award fees from\\n\\nthat fund without running afoul of ERISA’s anti-alienation or exclusive benefit\\n\\nrequirements. See Kickham Hanley P.C. v. Kodak Ret. Income Plan, 558 F.3d 204, 213\\n\\n(2d Cir. 2009); Lynn v. CSX Transp., Inc., 84 F.3d 970, 975 (7th Cir. 1996).\\n\\n Next, Wilmington and Constellis argue that ERISA’s statutory fee-shifting\\n\\nprovision displaces the common fund doctrine. See 29 U.S.C. § 1132(g)(1) (authorizing\\n\\nprevailing plaintiffs to recover reasonable attorneys’ fees from defendants). They urge us\\n\\nto follow the Seventh Circuit in “limiting the common-fund approach to cases outside the\\n\\nscope of a fee-shifting statute.” Pierce v. Visteon Corp., 791 F.3d 782, 787 (7th Cir.\\n\\n2015); accord Haggart v. Woodley, 809 F.3d 1336, 1358–59 (Fed. Cir. 2016) (largely\\n\\nadopting Pierce rule). 12\\n\\n Several other circuits, however, have disagreed with this approach. See McKeage\\n\\nv. TMBC, LLC, 847 F.3d 992, 1003 (8th Cir. 2017) (“[T]he presence of a fee-shifting\\n\\nstatute precludes a common fund award only when that result is required by the statutory\\n\\nscheme involved.”); In re Bluetooth Headset Prods. Liab. Litig., 654 F.3d 935, 941 (9th\\n\\nCir. 2011) (“The award of attorneys’ fees in a class action settlement is often justified by\\n\\n[a] common fund or statutory fee-shifting[,] . . . and sometimes by both.”); Staton v.\\n\\n\\n 12\\n Pierce is in some tension with prior Seventh Circuit cases holding, in the\\ncontext of settlements, that common fund recoveries are sometimes available even where\\na case was brought under a statute with a fee-shifting provision. See Florin v.\\nNationsbank of Georgia, N.A., 34 F.3d 560, 563–64 (7th Cir. 1994); Skelton v. Gen.\\nMotors Corp., 860 F.2d 250, 252–57 (7th Cir. 1988).\\n\\n 39\\n\\fBoeing Co., 327 F.3d 938, 967–69 (9th Cir. 2003) (permitting common fund recovery\\n\\neven where statutory fees may be available); Cty. of Suffolk v. Long Island Lighting Co.,\\n\\n907 F.2d 1295, 1327 (2d Cir. 1990) (“In our view, fee-shifting statutes are generally not\\n\\nintended to circumscribe the operation of the equitable fund doctrine.”).\\n\\n To determine the proper course here, we consider the roots of the common fund\\n\\ndoctrine. The common fund principle derives from the equitable doctrines of quantum\\n\\nmeruit, Central Railroad & Banking Co. v. Pettus, 113 U.S. 116 (1885), and unjust\\n\\nenrichment, Trustees v. Greenough, 105 U.S. 527, 532 (1881). It allows a court to award\\n\\n“a reasonable attorney’s fee” to “a litigant or a lawyer who recovers a common fund for\\n\\nthe benefit of persons other than himself or his client . . . from the fund as a whole.”\\n\\nBoeing Co. v. Van Gemert, 444 U.S. 472, 478 (1980). The rationale for the doctrine is\\n\\nthat when one benefits from a lawsuit without contributing to its costs, he has been\\n\\nunjustly enriched at the successful litigant’s or lawyer’s expense. Mills v. Elec. Auto-Lite\\n\\nCo., 396 U.S. 375, 392 (1970). Courts remedy this inequity by shifting a proportional\\n\\nshare of reasonable attorneys’ fees onto these unjustly enriched beneficiaries.\\n\\n The Supreme Court has applied the “strong and uniform . . . background rule” of\\n\\nthe common fund doctrine “in a wide range of circumstances as part of [its] inherent\\n\\nauthority.” US Airways, Inc. v. McCutchen, 569 U.S. 88, 104 (2013) (collecting cases).\\n\\nWe agree with Brundle that it applies here. Scores of unnamed ESOP participants\\n\\nbenefited substantially from this lawsuit, while B&G bore the entirety of the costs and\\n\\nrisks. Equity thus demands that the enriched participants pay a proportional share of\\n\\nreasonable attorneys’ fees.\\n\\n 40\\n\\f To be sure, courts often, but not invariably, award common fund fees when a\\n\\nprocedural obstacle, such as the terms of a settlement, bars statutory fees that are\\n\\notherwise available. 13 But it does not follow that all statutory fee provisions necessarily\\n\\ndisplace the doctrine or render it superfluous. To the contrary: although both the\\n\\ncommon fund doctrine and fee-shifting statutes facilitate suit by plaintiffs who may\\n\\notherwise lack the means to hire counsel, they operate in distinct ways and serve distinct\\n\\npurposes.\\n\\n A common fund recovery places the plaintiffs’ cost of litigation on the recovering\\n\\nbeneficiaries of a lawsuit, whereas a fee-shifting statute places this burden on the losing\\n\\nparty. Cf. Venegas, 495 U.S. at 90 (differentiating between “what the losing defendant\\n\\nmust pay” to the plaintiff as attorneys’ fees under a fee-shifting statute and “what the\\n\\nprevailing plaintiff must pay his lawyer”). A fee-shifting statute thus creates an\\n\\nexception to the “American rule” that “the prevailing litigant is ordinarily not entitled to\\n\\ncollect a reasonable attorneys’ fee from the loser.” Alyeska Pipeline Serv. Co. v.\\n\\nWilderness Soc., 421 U.S. 240, 247 (1975). In contrast, the common fund doctrine —\\n\\nthough often similarly described as an exception — better accords with the American rule\\n\\n 13\\n See, e.g., Skelton, 860 F.2d at 256 (affirming common fund award where “the\\nfee-shifting provision [did] not . . . apply to a fee determination in a case settled in a\\ncommon fund”); In re Fine Paper Antitrust Litig., 751 F.2d 562, 582–83 (3d Cir. 1984)\\n(affirming common fund award where settlement released defendants from statutorily\\navailable fees). But see Reyes v. Bakery & Confectionary Union & Indus. Int’l Pension\\nFund, 281 F. Supp. 3d 833, 850 (N.D. Cal. 2017) (“[C]lass counsel may be awarded fees\\nfrom the common fund in addition to any award under ERISA’s fee-shifting statute.”);\\nHumphrey v. United Way of Tex. Gulf Coast, 802 F. Supp. 2d 847, 859 (S.D. Tex. 2011)\\n(“The Court . . . has the power and discretion to award reasonable fees under both\\n[ERISA] and the common fund doctrine.”).\\n\\n 41\\n\\fby holding the beneficiaries of a judgment or settlement responsible for compensating the\\n\\ncounsel who obtained the judgment or settlement for them. See Staton, 327 F.3d at 967.\\n\\n Furthermore, the purpose of the common fund doctrine, unlike a fee-shifting\\n\\nstatute, is to avoid unjust enrichment. Thus, although a statutory fee award against a\\n\\ndefendant generally may not include a contingency enhancement, see City of Burlington\\n\\nv. Dague, 505 U.S. 557, 565–67 (1992), courts routinely impose enhanced common fund\\n\\nawards to compensate counsel for litigation risk at the expense of beneficiaries who did\\n\\nnot shoulder this risk, see, e.g., In re Wash. Pub. Power Supply Sys. Secs. Litig., 19 F.3d\\n\\n1291, 1300 (9th Cir. 1994) (“There is nothing unfair about contingency enhancements in\\n\\ncommon fund cases . . . .”); Florin, 34 F.3d at 564–65 (similarly holding that “the policy\\n\\nconsiderations . . . that militate for forbidding risk multiples in statutory fee-shifting cases\\n\\nhave little force in common fund cases”).\\n\\n From these distinctions, it follows that a “reasonable” fee payable by a defendant\\n\\nto compensate the prevailing plaintiff’s counsel is not necessarily identical to a\\n\\n“reasonable” fee owed by a recovering beneficiary to plaintiff’s counsel, particularly\\n\\nwhere the contingency risk to plaintiff’s counsel is substantial. Cf. Venegas, 495 U.S. at\\n\\n85, 90 (affirming $406,000 contractual fee, paid by prevailing plaintiff to his counsel, as\\n\\nnot “unreasonable” even though “reasonable” statutory fee, paid by losing defendants,\\n\\nwas only $117,000); McKeage, 847 F.3d at 1004 (emphasizing “a distinction between the\\n\\namount a losing party may be required to pay” under fee-shifting provision in settlement\\n\\n“and the amount a class member should equitably be required to pay” under common\\n\\nfund doctrine).\\n\\n 42\\n\\f Consequently, we find unpersuasive the Seventh Circuit’s reasoning in Pierce. In\\n\\nlimiting the common fund doctrine to cases “outside the scope of a fee-shifting statute,”\\n\\nthe Pierce court reasoned first and foremost that “[c]ommon-law doctrines yield to\\n\\nstatutes.” 791 F.3d at 787. But the Supreme Court has instructed that courts must\\n\\n“presum[e] that Congress intended to retain the substance of the common law.”\\n\\nSamantar v. Yousuf, 560 U.S. 305, 320 n.13 (2010). We recognize, of course, that\\n\\nlegislative displacement of the common law does not require “the same sort of evidence\\n\\nof a clear and manifest congressional purpose demanded for preemption of state law.”\\n\\nAm. Elec. Power Co., Inc. v. Connecticut, 564 U.S. 410, 423 (2011) (alterations and\\n\\ninternal quotation marks omitted). Even so, a statute that shifts a reasonable fee onto a\\n\\nlosing defendant does not, without more, “speak[] directly” to congressional intent to\\n\\ndisplace recovery from a common fund. Id. at 424 (internal quotation marks omitted).\\n\\n The Pierce court additionally emphasized that “fee-shifting statutes are designed\\n\\nto ensure that the victims retain full compensation,” 791 F.3d at 787, a concern of\\n\\nindisputable importance. The common fund doctrine, however, balances this critical\\n\\ninterest against the concern of unjust enrichment, which ERISA’s fee-shifting provision\\n\\ndoes not purport to address.\\n\\n Finally, echoing the Pierce court, Wilmington and Constellis stress that B&G was\\n\\nentitled to, and received, a “reasonable” attorneys’ fee under statute. However, as we\\n\\nhave explained, what is “reasonable” as a fee from a losing defendant may well differ\\n\\nfrom what is “reasonable” as a fee from an individual directly benefited by counsel’s\\n\\nefforts. We particularly note that a “reasonable” fee under ERISA’s attorneys’ fee\\n\\n 43\\n\\fprovision (unlike a common fund award) precludes any compensation for contingency\\n\\nrisk. See Dague, 505 U.S. at 565–67. But, we have previously underscored, contingent\\n\\nfees serve an important function in providing under-resourced litigants access to counsel\\n\\nand the courts. In re Abrams & Abrams, P.A., 605 F.3d 238, 245–47 (4th Cir. 2010).\\n\\nConflating statutory attorneys’ fees with common fund recoveries would squarely\\n\\ncontravene this policy.\\n\\n We therefore agree with the Second, Eighth, and Ninth Circuits that a statutory\\n\\nfee-shifting provision (or an award of fees under such a provision) does not, as a matter\\n\\nof law, automatically preclude an award under the common fund doctrine. Accordingly,\\n\\nthe district court retained discretion to award supplemental attorneys’ fees from the\\n\\ncommon fund.\\n\\n C.\\n\\n Having established the district court’s authority to award supplemental fees, we\\n\\nturn to Brundle’s contention that the court abused its discretion in awarding its counsel\\n\\ntoo little from the common fund.\\n\\n Before setting the amount of its common fund award, the district court fashioned\\n\\nan ad hoc process analogous to class settlement procedures under Rule 23. Brundle II,\\n\\n258 F. Supp. 3d at 671–72. The court ordered Brundle’s counsel, B&G, to engage in a\\n\\ngood faith effort to notify the approximately 1,800 former ESOP participants of its\\n\\nproposed contingency fee award. After B&G did so, the court received 59 letters\\n\\nobjecting to a one-third contingency award. As a result of the objections, the court\\n\\ndecided to award B&G only $1.5 million as a supplemental fee payable from the\\n\\n 44\\n\\fdamages award, rather than granting counsel a full one-third ($9.9 million) of the ESOP’s\\n\\ntotal damages recovery.\\n\\n In reviewing the district court’s award, we note that Brundle had available a\\n\\nprocedural mechanism designed to carefully balance the interests of counsel, plaintiffs,\\n\\nand other similarly situated beneficiaries from the start — namely, class certification\\n\\npursuant to Rule 23. To be fair, Brundle and another plaintiff, Halldorson, did initially\\n\\nseek class certification, which the district court denied. But Brundle opted not to timely\\n\\nappeal this denial. And although Halldorson initially sought our review, he later\\n\\nwithdrew his appeal. See supra n.4.\\n\\n Had Brundle pursued class certification and prevailed, B&G could have secured\\n\\nattorneys’ fees from the class as a whole. Although a properly certified class might not\\n\\nhave agreed to the same one-third contingency fee that Brundle did, the district court\\n\\nmight well have awarded a fee significantly higher than the firm’s ultimate recovery\\n\\nhere. 14\\n\\n Brundle, represented by B&G, instead opted to forego Rule 23’s procedural\\n\\nstrictures — thus avoiding “the standards set for the protection of absent class members.”\\n\\nAmchem Prods., Inc. v. Windsor, 521 U.S. 591, 621 (1997). In light of this choice, the\\n\\ndistrict court’s decision to limit the common fund award was not inequitable, as\\n\\nillustrated by the objections from some of the ESOP’s participants. Nearly 60 of the\\n\\n 14\\n See, e.g., Savani v. URS Prof’l Sols. LLC, 121 F. Supp. 3d 564, 574–75 (D.S.C.\\n2015) (approving fee award of 39.57% from common fund award in ERISA settlement\\nand collecting cases); In re Marsh ERISA Litig., 265 F.R.D. 128, 149 (S.D.N.Y. 2010)\\n(approving fee award of 33.33% from common fund award).\\n\\n 45\\n\\f1,800 participants objected to the proposed common fund award, explaining that they had\\n\\nnever been informed of the case status, never agreed to B&G’s representation, and never\\n\\nauthorized the fund to pay a one-third fee. These process concerns would have been\\n\\navoided upfront had Brundle persisted in his pursuit of class certification. But because he\\n\\nand his counsel abandoned Rule 23’s class-protective procedures, equity cuts against\\n\\nawarding B&G the full one-third contingency fee.\\n\\n The district court properly weighed B&G’s efforts on behalf of the ESOP —\\n\\nincluding contingency risk — against the objections from ESOP participants to determine\\n\\na proper common fund award. Because we cannot say this balancing was clearly wrong,\\n\\nsee Berry, 807 F.3d at 617, we affirm the court’s fee award in full.\\n\\n\\n\\n V.\\n\\n For the foregoing reasons, the judgment of the district court is in all respects\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 46\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4380191/\", \"author_raw\": \"DIANA GRIBBON MOTZ, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"GREGORY"},"judge2":{"kind":"string","value":"MOTZ"},"judge3":{"kind":"string","value":"FLOYD"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"GREGORY\": \", Chief\", \"MOTZ\": \", Circuit\", \"FLOYD\": \", Circuit\"}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4602938/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Tim Brundle v. Wilmington Trust, N.A.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-03-22\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 17-1873\n\n\nTIM P. BRUNDLE, on behalf of the Constellis Employee Stock Ownership Plan,\n\n Plaintiff - Appellee,\n\n and\n\nANDREW HALLDORSON, on behalf of the Constellis Employee Stock\nOwnership Plan, and on behalf of a class of all other persons similarly situated,\n\n Plaintiff,\n\n v.\n\nWILMINGTON TRUST, N.A., as successor to Wilmington Trust Retirement and\nInstitutional Services Company,\n\n Defendant - Appellant.\n\n-------------------------------------------\n\nAMERICAN SOCIETY OF APPRAISERS,\n\n Amicus Supporting Appellant,\n\nSECRETARY OF THE UNITED STATES DEPARTMENT OF LABOR,\n\n Amicus Supporting Appellee.\n\n\n No. 17-2224\n\n\nTIM P. BRUNDLE, on behalf of the Constellis Employee Stock Ownership Plan,\n\f Plaintiff - Appellant,\n\n and\n\nANDREW HALLDORSON, on behalf of the Constellis Employee Stock\nOwnership Plan, and on behalf of a class of all other persons similarly situated,\n\n Plaintiff,\n\n v.\n\nWILMINGTON TRUST, N.A., as successor to Wilmington Trust Retirement and\nInstitutional Services Company,\n\n Defendant - Appellee.\n\n-------------------------------------------\n\nSECRETARY OF THE UNITED STATES DEPARTMENT OF LABOR,\n\n Amicus Supporting Appellant,\n\nAMERICAN SOCIETY OF APPRAISERS,\n\n Amicus Supporting Appellee.\n\n\n No. 17-2323\n\n\nTIM P. BRUNDLE, on behalf of the Constellis Employee Stock Ownership Plan,\n\n Plaintiff - Appellee,\n\n and\n\nANDREW HALLDORSON, on behalf of the Constellis Employee Stock\nOwnership Plan, and on behalf of a class of all other persons similarly situated,\n\n Plaintiff,\n\nCONSTELLIS GROUP, INC.,\n\n\n 2\n\f Party-in-Interest,\n\n v.\n\nWILMINGTON TRUST, N.A., as successor to Wilmington Trust Retirement and\nInstitutional Services Company,\n\n Defendant - Appellant.\n\n-------------------------------------------\n\nAMERICAN SOCIETY OF APPRAISERS,\n\n Amicus Supporting Appellant,\n\nSECRETARY OF THE UNITED STATES DEPARTMENT OF LABOR,\n\n Amicus Supporting Appellee.\n\n\n No. 17-2324\n\n\nTIM P. BRUNDLE, on behalf of the Constellis Employee Stock Ownership Plan,\n\n Plaintiff - Appellee,\n\n and\n\nANDREW HALLDORSON, on behalf of the Constellis Employee Stock\nOwnership Plan, and on behalf of a class of all other persons similarly situated,\n\n Plaintiff,\n\n v.\n\nCONSTELLIS GROUP, INC.,\n\n Party-in-Interest - Appellant,\n\n and\n\n\n\n 3\n\fWILMINGTON TRUST, N.A., as successor to Wilmington Trust Retirement and\nInstitutional Services Company,\n\n Defendant.\n\n\n No. 18-1029\n\n\nTIM P. BRUNDLE, on behalf of the Constellis Employee Stock Ownership Plan,\n\n Plaintiff - Appellant,\n\n and\n\nANDREW HALLDORSON, on behalf of the Constellis Employee Stock\nOwnership Plan, and on behalf of a class of all other persons similarly situated,\n\n Plaintiff,\n\n v.\n\nWILMINGTON TRUST, N.A., as successor to Wilmington Trust Retirement and\nInstitutional Services Company,\n\n Defendant - Appellee,\n\nCONSTELLIS GROUP, INC.,\n\n Party-in-Interest.\n\n\nAppeals from the United States District Court for the Eastern District of Virginia, at\nAlexandria. Leonie M. Brinkema, District Judge. (1:15-cv-01494-LMB-IDD)\n\n\nArgued: December 11, 2018 Decided: March 21, 2019\n Amended: March 22, 2019\n\n\nBefore GREGORY, Chief Judge, and MOTZ and FLOYD, Circuit Judges.\n\n\n\n 4\n\fAffirmed by published opinion. Judge Motz wrote the opinion, in which Chief Judge\nGregory and Judge Floyd joined.\n\n\nARGUED: Carter Glasgow Phillips, SIDLEY AUSTIN LLP, Washington, D.C., for\nAppellant/Cross-Appellee Wilmington Trust, N.A. Gregory Y. Porter, BAILEY &\nGLASSER LLP, Washington, D.C., for Appellee/Cross-Appellant. Robin Springberg\nParry, UNITED STATES DEPARTMENT OF LABOR, Washington, D.C., for Amicus\nSecretary of Labor. ON BRIEF: James P. McElligott, Jr., Summer L. Speight,\nRichmond, Virginia, Stephen W. Robinson, MCGUIRE WOODS LLP, Tysons, Virginia;\nJacqueline G. Cooper, Kurt A. Johnson, SIDLEY AUSTIN LLP, Washington, D.C., for\nAppellant/Cross-Appellee Wilmington Trust, N.A. Edward Lee Isler, Micah E. Ticatch,\nISLER DARE, P.C., Vienna, Virginia, for Appellant Constellis Group, Inc. Tillman J.\nBreckenridge, Ryan T. Jenny, BAILEY & GLASSER LLP, Washington, D.C., for\nAppellee/Cross-Appellant. J. Christian Nemeth, Chicago, Illinois, Sophia A. Luby,\nWashington, D.C.; Eliot T. Burriss, Erin Turley, Calli Turner, MCDERMOTT WILL &\nEMERY LLP, Dallas, Texas, for Amicus American Society of Appraisers. Kate S.\nO’Scannlain, Solicitor of Labor, G. William Scott, Associate Solicitor for Plan Benefits\nSecurity, Thomas Tso, Counsel for Appellate and Special Litigation, UNITED STATES\nDEPARTMENT OF LABOR, Washington, D.C., for Amicus Secretary of Labor.\n\n\n\n\n 5\n\fDIANA GRIBBON MOTZ, Circuit Judge:\n\n After owners of a closely held corporation sold the company to its Employee\n\nStock Ownership Plan (“ESOP”), a participant in the ESOP brought this action. The\n\nparticipant contended that the trustee chosen for the ESOP by the corporation breached\n\nits fiduciary duties to the ESOP and overpaid for the stock — improperly enriching the\n\ncorporation’s owners at the expense of its employees.\n\n Following a multi-day bench trial, the district court issued detailed findings of fact\n\nconcluding that the trustee had indeed breached its fiduciary duties, causing the ESOP to\n\noverpay for the corporation’s stock by $29,773,250. The court entered judgment for the\n\nESOP in that amount and awarded attorneys’ fees to the participant’s counsel. These\n\nappeals and cross-appeals followed. As explained within, we affirm the careful findings\n\nof the district court.\n\n\n\n I.\n\n To facilitate understanding of the issues here, we begin with the governing legal\n\nprinciples and background facts that gave rise to this suit. The parties do not challenge\n\nthese principles or facts. All are more fully set forth in the comprehensive district court\n\nopinions, upon which we rely throughout. See Brundle v. Wilmington Tr. N.A., 241\n\nF. Supp. 3d 610 (E.D. Va. 2017) (“Brundle I”); Brundle v. Wilmington Tr. N.A., 258\n\nF. Supp. 3d 647 (E.D. Va. 2017) (“Brundle II”).\n\n\n\n\n 6\n\f A.\n\n The Employee Retirement Income Security Act of 1974 (ERISA) allows an\n\nemployer to create an ESOP, an employee pension plan that invests primarily in the\n\nemployer’s stock. The employer makes contributions to the plan that are used to\n\npurchase stock in the employer’s company. Because — and only because — an ESOP\n\ncontribution qualifies as employee compensation, an employer can deduct the total value\n\nof its ESOP contribution from its income tax liability as an ordinary business expense.\n\n26 U.S.C. § 404; 26 C.F.R. § 1.404(a)–1(b). 1 In this way, an ESOP benefits both\n\nemployees and employers by providing deferred compensation to the former and a\n\nvaluable tax deduction to the latter.\n\n ERISA imposes duties and obligations on all pension plan fiduciaries, including\n\nthose of ESOPs. These duties “ensure that employees will not be left empty-handed once\n\nemployers have guaranteed them certain benefits.” Lockheed Corp. v. Spink, 517 U.S.\n\n882, 887 (1996). One such provision prohibits the fiduciary of any ERISA plan from\n\ncausing a “sale or exchange . . . of any property between the plan and a party in interest.”\n\n29 U.S.C. § 1106(a)(1)(A). Absent a statutory exception, this provision would ban\n\nESOPs because their creation necessarily requires the ESOP to purchase stock from its\n\nsponsoring employer, which is a party in interest. Congress, however, has carved out an\n\n\n\n 1\n An employer’s contributions to an ESOP thus constitute a valuable form of\ndeferred compensation, rather than a gift to employees. See, e.g., Reich v. Hall Holding\nCo., 990 F. Supp. 955, 961 (N.D. Ohio 1998), aff’d sub nom. Chao v. Hall Holding Co.,\n285 F.3d 415 (6th Cir. 2002). Wilmington wisely does not suggest otherwise.\n\n 7\n\fexception to this prohibition to permit the creation of an ESOP if the stock purchase\n\nmeets certain conditions. See 29 U.S.C. § 1108(e).\n\n To protect employees from losing the value of their earned retirement savings, the\n\nexception to the ERISA ban on party-in-interest transactions requires that an ESOP pay\n\nno more than “adequate consideration” for the employer’s stock. Id. § 1108(e)(1). If an\n\nemployer’s “stock was not worth what the ESOP paid for it,” then the ESOP paid more\n\nthan adequate consideration and “the ESOP and its participants suffered a loss under\n\nERISA.” See Reich, 990 F. Supp. at 961.\n\n ERISA does not define what constitutes “adequate consideration” under the\n\n§ 1108(e) exception; the Department of Labor (DOL) has proposed, but never enacted,\n\nregulations doing so. 2 Although courts look to these regulations for guidance, the focus\n\nof the adequate-consideration inquiry rests on the conduct of a fiduciary, as judged by\n\nERISA’s “prudent man” standard of care. See Perez v. Bruister, 823 F.3d 250, 263 (5th\n\nCir. 2016); Henry III, 445 F.3d at 619; Chao, 285 F.3d at 437; Howard v. Shay, 100 F.3d\n\n1484, 1489 (9th Cir. 1996).\n\n Under this standard, “ESOP fiduciaries are subject to the duty of prudence just as\n\nother ERISA fiduciaries are.” Fifth Third Bancorp v. Dudenhoeffer, 134 S. Ct. 2459,\n\n 2\n These proposed regulations, to which courts look for guidance, provide that\n“adequate” consideration must (1) reflect the stock’s “fair market value,” and (2) be “the\nproduct of a determination made by the fiduciary in good faith.” Proposed Regulation\nRelating to the Definition of Adequate Consideration, 53 Fed. Reg. 17,632, 17,633\n(proposed May 17, 1988) (to be codified at 29 C.F.R. pt. 2510). “[I]n practice, the ‘fair\nmarket value’ inquiry overlaps considerably with the ‘good faith’ inquiry.’” Henry v.\nChamplain Enters., Inc., 445 F.3d 610, 618–19 (2d Cir. 2006) (Sotomayor, J.) (“Henry\nIII”) (collecting cases).\n\n 8\n\f2467 (2014). Thus an ESOP fiduciary, like any other ERISA fiduciary, must “discharge\n\nhis duties . . . with the care, skill, prudence, and diligence under the circumstances then\n\nprevailing that a prudent man acting in a like capacity and familiar with such matters\n\nwould use in the conduct of an enterprise of a like character and with like aims.” 29\n\nU.S.C. § 1104(a)(1)(B).\n\n Although these fiduciary duties “draw much of their content from the common law\n\nof trusts . . . ERISA’s standards and procedural protections partly reflect a congressional\n\ndetermination that the common law of trusts did not offer completely satisfactory\n\nprotection.” Tatum v. RJR Pension Inv. Comm., 761 F.3d 346, 357 (4th Cir. 2014)\n\n(internal quotation marks omitted). Courts apply the “prudent man rule . . . bearing in\n\nmind the special nature and purpose of employee benefit plans.” Id. (internal quotation\n\nmarks and alterations omitted). For this reason, “[t]he fiduciary obligations of the\n\ntrustees to the participants and beneficiaries [of an ERISA] plan are . . . the highest\n\nknown to the law.” Id. at 356 (alterations in original) (quoting Donovan v. Bierwith, 680\n\nF.2d 263, 272 n.8 (2d Cir. 1982)).\n\n Because an ESOP fiduciary that raises an affirmative defense under the § 1108(e)\n\nexception seeks to avoid ERISA liability for an otherwise prohibited transaction, the\n\nfiduciary bears the burden of proving by a preponderance of the evidence that the sale\n\nwas for adequate consideration. See Elmore v. Cone Mills Corp., 23 F.3d 855, 864 (4th\n\nCir. 1994) (en banc). “This burden is a heavy one.” Shay, 100 F.3d at 1488.\n\n B.\n\n With these principles in mind, we turn to the facts of this case.\n\n 9\n\f Since its inception, Constellis Group, Inc., the closely held parent company of a\n\ngroup of private security subsidiaries, has offered some form of deferred compensation to\n\nits employees, who are primarily retired members of the U.S. Armed Forces. Brundle I,\n\n241 F. Supp. 3d at 614. After initially offering a stock option program, Constellis\n\nreplaced that program with a profit-sharing plan in 2010. Id. In mid-2013, looking for an\n\n“exit strategy” after having twice tried and failed to effectuate a sale of the company, the\n\nowners of Constellis (hereinafter “the Sellers”) 3 began exploring the possibility of\n\ncreating an ESOP to purchase Constellis. Id. at 615.\n\n To that end, Constellis retained CSG International, an investment banking firm.\n\nCSG reported that sale of Constellis to an ESOP would not only enable the Sellers to\n\nliquidate their shares but would save them 23.8% in federal capital gains taxes. Id.\n\nAlthough noting that an ESOP would also benefit employees, CSG emphasized that\n\nselling Constellis to an ESOP provided the best option to optimize the Sellers’ after-tax\n\ncash return. See, e.g., id. at 616 (noting that CSG reported to the Sellers that, having\n\n“looked at every possible scenario,” it had not seen “any possible alternative that\n\nproduce[d] more after tax cash” than the proposed ESOP (internal quotation marks\n\nomitted)).\n\n CSG suggested that Constellis create what several trial witnesses characterized as\n\na “unique” ESOP structure to effectuate the sale. This unique structure would permit the\n\nSellers to retain de facto control of Constellis, even after the ESOP purchased all of the\n\n 3\n Four individuals owned 77% of Constellis stock at the time of the sale at issue\nhere. See Brundle I, 241 F. Supp. 3d at 615.\n\n 10\n\fcompany stock. Rather than sell 100% of their ownership interest to the ESOP, as is the\n\nusual practice, the Sellers would sell 90% of their shares to the ESOP and then exchange\n\nthe remaining 10% for “equity-like” warrants. These warrants would entitle the Sellers to\n\nbuy back equity in Constellis from the ESOP at a designated price and guarantee the\n\nSellers a majority on the board of directors. Id. at 626.\n\n To fund the ESOP’s purchase, Constellis would contribute 24% of the purchase\n\nprice and the ESOP would borrow the remainder from Constellis and the Sellers\n\nthemselves. Id. at 625. In late September 2013, Constellis decided to move forward with\n\nCSG’s proposal to create this unique ESOP. Id. To maximize the Sellers’ tax savings,\n\nConstellis had to complete the sale by the end of the calendar year. Id. at 622.\n\n On the recommendation of CSG, Constellis engaged Wilmington Trust, N.A., to\n\nserve as trustee for the ESOP. Id. at 616. In its role as trustee, Wilmington hired Stout\n\nRisius Ross (SRR) to be the financial advisor on the ESOP’s purchase of Constellis. Id.\n\nat 617. CSG, Wilmington, and SRR maintained significant long-term business\n\nrelationships, having worked together on more than twenty ESOP deals. Id. at 643\n\n(calling “the ESOP world . . . a very incestuous community”) (internal quotation marks\n\nomitted); id. at 617.\n\n On November 12, 2013, SRR submitted a draft valuation of Constellis stock to\n\nWilmington (the “SRR Report”). The SRR Report concluded that the fair market value\n\nfor a single share of Constellis stock lay between $3,865 and $4,600 — resulting in a\n\nrounded median price per share of $4,235. This placed the company’s worth, or its\n\n“enterprise value,” within a range of $275 to $330 million. Id. at 620–21. On November\n\n 11\n\f14, Wilmington met with analysts from SRR to discuss its report and valuation. At the\n\nmeeting’s conclusion, Wilmington set out to negotiate the ESOP’s purchase of Constellis\n\nwith authorization to offer a share price of $3,900 to $4,235. Id. at 622.\n\n The next day, Wilmington submitted an opening bid on behalf of the ESOP for\n\n$3,900 per share. Id. at 642. CSG, on behalf of Constellis, countered with $4,350 and\n\nsuggested to Wilmington that the ESOP and Constellis agree on a price first and then\n\nadjust the terms of the agreement at a later date. Wilmington agreed and raised its own\n\nbid to $4,100. CSG then countered with $4,250. By the end of the day, Wilmington and\n\nCSG had settled on a share price of $4,235 — the very top of Wilmington’s authorized\n\nnegotiation range. The negotiations lasted little more than five hours.\n\n The ESOP issued a tender offer for the shares on November 18 with a closing date\n\nof December 20. The parties finalized the term sheet on November 22. Between the\n\nconclusion of negotiations and the closing date for the transaction, SRR revised its\n\nvaluation of the draft enterprise range downward from $275–$330 million to $275–$325\n\nmillion, but the per share purchase price remained $4,235. On December 19, after\n\nmeeting with SRR for half an hour to discuss SRR’s valuation, Wilmington approved the\n\npurchase. Id. at 624. On December 20, the ESOP’s purchase of Constellis closed for a\n\nper share price of $4,235. Id. at 625.\n\n Subsequently, Tim P. Brundle, a former Constellis employee and ESOP\n\nparticipant, brought this action contending that Wilmington caused the ESOP to enter\n\n\n\n\n 12\n\finto a transaction prohibited under ERISA § 1106. 4 Brundle alleged that the $4,235 per\n\nshare paid by the ESOP for Constellis was too high and resulted in the ESOP overpaying\n\nthe Sellers for the stock. The district court initially held that the 2013 purchase of\n\nConstellis by the ESOP constituted a prohibited transaction under § 1106(a)(1). Brundle\n\nv. Wilmington Tr., N.A., 2016 WL 6542718, at *12 (E.D. Va. Nov. 3, 2016). Wilmington\n\nconceded as much before the district court but raised the adequate-consideration\n\naffirmative defense available under § 1108(e)(1). Id.\n\n Following a bench trial, the district court issued meticulous factual findings and\n\nconcluded on the basis of those findings that Wilmington had not established the\n\n§ 1108(e) affirmative defense. Rather, the court found that Wilmington had violated its\n\nfiduciary duty to the ESOP. The district court concluded that Wilmington’s fiduciary\n\nfailures resulted in the ESOP overpaying for the Constellis stock by $29,773,250, and so\n\nawarded that amount to the ESOP as damages. Brundle I, 241 F. Supp. 3d at 613.\n\n Brundle then moved for attorneys’ fees. The court first ordered Wilmington to\n\npay attorneys’ fees pursuant to ERISA’s fee-shifting provision, 29 U.S.C. § 1132(g)(1),\n\nin the amount of $1,819,631.11. Brundle II, 258 F. Supp. 3d at 663–69. It subsequently\n\nawarded an additional $1.5 million in fees from the damages award.\n\n 4\n Andrew Halldorson, another former Constellis employee and an ESOP\nparticipant, filed the initial complaint against Wilmington. Halldorson later amended his\ncomplaint to add Brundle as a named plaintiff. Both Halldorson and Brundle moved for\nclass certification, which the district court denied. Following a motion for summary\njudgment by Wilmington, the district court dismissed Halldorson because of a release he\nsigned barring his suit against Wilmington. Halldorson appealed both his dismissal and\nthe denial of class certification but later withdrew his appeal of the class certification\nissue. Brundle did not timely appeal the denial of class certification.\n\n 13\n\f On appeal, Wilmington challenges the court’s liability and damages\n\ndeterminations and its award of $1.5 million in non-statutory attorneys’ fees. Brundle\n\ncross-appeals, challenging as inadequate the same portion of the attorneys’ fees award.\n\n\n\n II.\n\n Wilmington initially and principally contends that the district court erred in\n\nconcluding that it violated ERISA. Following a bench trial, we review a district court’s\n\nfactual findings for clear error and its legal conclusions de novo. Nat’l Fed’n of the Blind\n\nv. Lamone, 813 F.3d 494, 502 (4th Cir. 2016).\n\n At the outset of both its principal brief and its oral argument, Wilmington\n\nemphasized that there is no claim in this case that it acted in bad faith. But of course, an\n\nESOP participant seeking recovery from its fiduciary need not prove that the fiduciary\n\nacted in bad faith. Rather, an ESOP fiduciary is liable to the plan participants if it\n\nbreached its fiduciary duties, i.e., failed to act “solely in the interest of the participants,”\n\nwith the care, skill, prudence, and diligence used by a “prudent man acting in a like\n\ncapacity.” 29 U.S.C. § 1104(a) (emphasis added). Thus our focus is not on\n\nWilmington’s motives (good or bad) but on whether it acted “solely in the interest” of the\n\nplan participants, id., and “engaged in a reasoned decisionmaking process, consistent\n\nwith that of a prudent man in like capacity,” DiFelice v. U.S. Airways, Inc., 497 F.3d 410,\n\n420 (4th Cir. 2007) (internal quotation marks omitted); accord Tatum, 761 F.3d at 356.\n\nAs the Fifth Circuit has put it, “a pure heart and an empty head are not enough.”\n\nDonovan v. Cunningham, 716 F.2d 1455, 1467 (5th Cir. 1983).\n\n 14\n\f A.\n\n The district court found that because Wilmington failed to prove by a\n\npreponderance of the evidence that the ESOP’s purchase of Constellis was for adequate\n\nconsideration — and no more than adequate consideration — the transaction failed to\n\nqualify for the § 1108(e) affirmative defense. 5 In challenging this holding, Wilmington\n\nheavily relies on the valuation of Constellis stock submitted by its advisor, SRR.\n\n Expert advice, like an advisor’s independent valuation, can of course serve as\n\nevidence of prudence in the discharge of an ESOP trustee’s duties under § 1108(e). See\n\nBussian v. RJR Nabisco, Inc., 223 F.3d 286, 300–01 (5th Cir. 2000). But such advice “is\n\nnot a magic wand that fiduciaries may simply wave over a transaction to ensure that their\n\nresponsibilities are fulfilled.” Cunningham, 716 F.2d at 1474. Rather, a plan trustee\n\nmust at least show that it (1) “investigate[d] the expert’s qualifications,” (2) “provide[d]\n\nthe expert with complete and accurate information,” and (3) “[made] certain that reliance\n\non the expert’s advice was reasonably justified under the circumstances.” Shay, 100 F.3d\n\nat 1489. Because ERISA demands a high level of scrutiny from fiduciaries, a trustee\n\nmust prove that it considered these factors “and any others relevant under the particular\n\n\n 5\n For this defense to apply, in addition to being for adequate consideration, (1) the\nsale or exchange must be of “qualifying employer securities,” (2) the trustee cannot\ncharge a commission, and (3) the plan must qualify as “an eligible individual account\nplan.” 29 U.S.C. § 1108(e).\n All parties agree that the transaction here was for “qualifying employer securities.”\nThey further agree that Wilmington did not charge a commission, and they do not dispute\nthe district court’s finding that Wilmington’s fees were reasonable. See Brundle I, 241 F.\nSupp. 3d at 617. The parties do contest, however, whether the ESOP qualifies as an\n“eligible plan.” The district court did not reach this issue, nor do we.\n\n 15\n\fcircumstances it faced at the time of the decision,” and took care to avoid any identified\n\nconflicts of interest. See Bruister, 823 F.3d at 263 (internal quotation marks omitted).\n\n The district court properly recognized that the above legal principles guided its\n\ninquiry. The court then issued extensive factual findings in support of its conclusion that\n\nWilmington had “not demonstrated that its reliance on SRR’s [valuation] report was\n\n‘reasonably justified’ in light of all the circumstances because [Wilmington] ha[d] not\n\nshown that it thoroughly probed the gaps and internal inconsistencies in that report.”\n\nBrundle I, 241 F. Supp. 3d at 634.\n\n The court found Wilmington’s decision-making process inadequate in four major\n\nrespects. Id. It explained that “[a]lthough these failings independently” might not be\n\ndispositive, cumulatively they demonstrated that “Wilmington failed to meet its duty”\n\nunder ERISA, id., which, of course, includes the obligation to act “solely in the interest”\n\nof plan participants, 29 U.S.C. § 1104(a). Wilmington challenges the district court’s\n\nexhaustive findings of fact and conclusions of law as to each of the four designated\n\nfailures.\n\n 1.\n\n First, Wilmington maintains the district court erred in finding fault with\n\nWilmington’s failure to investigate SRR’s omission from its report of another, much\n\nlower, valuation of Constellis stock. That valuation, termed the “McLean Report” by the\n\nparties, had been completed just months earlier by the McLean Group, an investment\n\nbank that had regularly provided annual share valuations for Constellis. Brundle I, 241 F.\n\nSupp. 3d at 619, 634–35.\n\n 16\n\f Wilmington’s trial witnesses contended that consideration of the McLean Report\n\n“would not have been helpful because it was prepared with a different purpose in mind\n\n— the valuation of a single share” for stock options, rather than the valuation of a\n\ncontrolling interest for sale. Id. at 634–35. But the district court, relying on the\n\nuncontradicted testimony of a “highly credible” neutral expert, found that the two reports\n\nused “essentially the same methodology” despite being prepared for different purposes.\n\nId. at 635. Using that same methodology, the 2013 McLean Report estimated the per\n\nshare value of Constellis stock as $1,838.11, while SRR estimated its median per share\n\nvalue as $4,235. Id. at 619.\n\n Yet the SRR Report, which guided Wilmington as it evaluated the ESOP\n\ntransaction, did not even mention the McLean Report. And, although trial testimony\n\nestablished that at least one Wilmington official knew of the McLean Report, no one\n\nfrom Wilmington ever asked about it or questioned the vast discrepancy between two\n\nvaluations of the same company performed mere months apart. Id. at 634–35. The\n\ndistrict court concluded that a prudent fiduciary in Wilmington’s position would have\n\ninquired as to SRR’s omission. This was particularly so given that Constellis officers\n\ntestified that the company’s business prospects had not dramatically changed in the\n\nperiod between the two reports, and the SRR Report had referenced a different\n\n“valuation” older than McLean’s. 6\n\n\n 6\n Specifically, the SRR Report noted that in 2012 — a year before the McLean\nReport’s publication — a private equity firm offered to buy Constellis for between $340\nand $350 million. But rather than explain that the private equity firm then lowered its\n(Continued)\n 17\n\f Relying on trial evidence, the district court concluded that even a cursory review\n\nof the McLean Report would have raised questions as to whether the share valuation in\n\nthe SRR Report was too optimistic. The court did not find that the McLean Report\n\nnecessarily offered a more accurate picture of Constellis’s true value, but simply that a\n\nreasonably prudent fiduciary would have asked more questions. The court found that the\n\nanswers to these questions were “precisely the kinds of information that Wilmington, as\n\ntrustee, should have sought and evaluated” when considering the valuation of Constellis\n\nstock. Id. at 636. We see no reason to conclude otherwise.\n\n 2.\n\n The second major fault identified by the district court concerned Wilmington’s\n\nfailure to adequately probe the reliability of financial projections prepared by Constellis\n\nmanagement and used by SRR. Id. at 636–38. The court found that “the record show[ed]\n\nthat there were several red flags indicating that these projections were inflated, which\n\nWilmington either ignored or downplayed.” Id. at 636. Wilmington offers both general\n\nand specific challenges to this finding.\n\n First, Wilmington argues that Constellis management’s financial projections were,\n\nin fact, reliable and so required no probing. In support of this view, Wilmington contends\n\nthat because the McLean Report also utilized management’s financial projections to\n\n\n\n\noffer to $275 million, see Brundle I, 241 F. Supp. 3d at 614–15, the report simply stated\nthat the deal fell through due to the buyer’s “inability to secure sufficient financing.”\n\n 18\n\farrive at its own valuation of Constellis — a valuation the court treated as relevant — the\n\ncourt should have found the projections that the SRR Report used were also reliable.\n\n But although both McLean and SRR relied on financial projections prepared by\n\nConstellis management, they did not rely on the same financial projections. Id. at 638.\n\nThe projections that Constellis provided to SRR forecasted revenue over a much longer\n\ntime period, id. at 637–38, making them less accurate and less reliable. Further,\n\nConstellis management specifically prepared this set of projections for the purposes of\n\nSRR’s valuation in connection with the ESOP sale. This created a risk that Constellis\n\nmanagement might inflate its projections in response to incentives unique to the ESOP\n\nsale. Id. at 636. In light of these distinctions, the district court’s differing assessments of\n\nthe two reports’ comparative reliability were not inherently contradictory.\n\n At a more granular level, Wilmington maintains that each of the red flags that the\n\ndistrict court identified in Constellis’s financial projections are “non-existent.”\n\nWilmington Opening Br. 33–34, 38–39. Wilmington asserts largely factual, and\n\nuniversally unpersuasive, arguments in support of this view.\n\n Wilmington challenges the district court’s conclusion that Wilmington should\n\nhave been more critical of Constellis management’s financial projections because\n\nmanagement had a financial incentive to inflate the purchase price. The court found that\n\nthis initial red flag should have alerted Wilmington to probe the SRR valuation of\n\nConstellis. The district court’s finding on this issue primarily rested on the prospect of\n\nmanagement receiving 5% of the purchase price in cash bonuses — a factual\n\ndetermination well supported by the record. See Brundle I, 241 F. Supp. 3d at 636.\n\n 19\n\f The district court also identified as a red flag an ongoing government investigation\n\ninto accounting and record-keeping errors by Constellis, which the court concluded\n\n“should have raised questions about the reliability of Constellis’[s] . . . projections.” Id.\n\nAgain, contrary to Wilmington’s suggestion, we see no basis for holding this finding\n\nclearly erroneous. A government investigation into errors of this nature surely creates a\n\nquestion as to the reliability of a company’s financial projections, which a reasonably\n\nprudent fiduciary representing the buyers of the company should probe further. Cf.\n\nKeach v. U.S. Tr. Co., 419 F.3d 626, 633–37 (7th Cir. 2005) (finding ESOP trustee met\n\nfiduciary duty when it “analyzed exhaustively [the company’s] financials, had conducted\n\nindependent valuation analyses and had challenged the financial forecasts made by [the\n\ncompany’s] management as too optimistic”).\n\n Still another red flag to which Wilmington, in the district court’s view, did “not\n\nadequately respond was the riskiness of Constellis’[s] contract concentration.” Brundle I,\n\n241 F. Supp. 3d at 637. The district court believed that this risk called for Wilmington to\n\napply further scrutiny to the company’s financial projections. The court found, and\n\nWilmington does not dispute, that at the time of the ESOP sale, about 70% of Constellis’s\n\nrevenue depended on just two government contracts. Id. at 637. Yet Wilmington\n\nadopted a valuation that assumed Constellis stock posed significantly less risk than the\n\nstock market as a whole. Again relying on the trial testimony of a “neutral” and “highly\n\ncredible” third party expert, the court explained its conclusion that Constellis’s industry\n\npeers — namely, government contractors — are certainly “no less risky than the market\n\nas a whole.” Brundle II, 258 F. Supp. 3d at 663. And again, the record offers ample\n\n 20\n\fsupport for this finding. See Brundle I, 241 F. Supp. 3d at 637; Brundle II, 258 F. Supp.\n\n3d at 662–63. 7\n\n Wilmington also maintains that the district court unfairly characterized\n\nConstellis’s “multiple sets of projections” as a red flag. Wilmington claims that the\n\ndistrict court ignored the fact that SRR advised Wilmington that the market and\n\nConstellis had changed throughout 2013. But the court adequately addressed this\n\nargument, see Brundle I, 241 F. Supp. 3d at 635–36, and we defer to its factual finding\n\nthat the changes in the market and Constellis’s business prospects throughout 2013 did\n\nnot justify multiple sets of projections.\n\n Last, Wilmington contends that we should reverse the district court due to its\n\ninitially erroneous understanding of the warranties Wilmington obtained to indemnify the\n\nESOP against the ongoing government investigation. At first, the court incorrectly found\n\n 7\n The court acknowledged that it originally had misunderstood the definition of the\nrisk factor, called “beta,” that SRR used in its report. SRR chose a beta of 0.7, indicating\nthat Constellis stock was less risky than the average stock (set at a beta of 1.0). The court\nhad understood beta to measure the risk of Constellis stock relative to its industry peers,\nbut beta actually measures the risk of a company’s stock — or in the case of a privately\nheld company like Constellis, the risk of a company’s publicly traded industry peers —\nrelative to the stock market as a whole. Brundle II, 258 F. Supp. 3d at 658.\n Upon consideration of Wilmington’s Rule 59 motion, the court stood by its\noriginal conclusion that Wilmington had inappropriately chosen a beta indicating that\nConstellis was less risky than other stocks. The court concluded that a neutral beta of 1.0\nwas more appropriate, noting that “[e]ven if government contracting business [in which\nConstellis participates] does not fluctuate in correlation with the market, that does not\nmean that government contracting is necessarily more stable.” Id. at 663. The court\nnoted that a Wilmington trial witness had acknowledged that “the government contracting\nindustry” is at times “less stable than the market as a whole.” Id. The court further relied\non the “most credible” neutral expert’s testimony that the public companies used by SRR\nto measure beta were “not a good match for Constellis.” Id. We see no clear error in\nthese findings.\n\n 21\n\fthat only Constellis had indemnified the ESOP, thus creating an illusory form of\n\nindemnification. But in denying Wilmington’s Rule 59 motion, the court candidly\n\naddressed that error and acknowledged that, in fact, both Constellis and the Sellers had\n\nindemnified the ESOP. Brundle II, 258 F. Supp. 3d at 656. Nonetheless, the court found\n\nthat its “corrected understanding [did] not alter [its] conclusions about . . . Wilmington’s\n\ninadequate investigation into the soundness of Constellis’[s] financial projections.” Id.\n\nThe court explained that, “[e]ven omitting its erroneous view of the Sellers’ . . .\n\nwarranties,” Wilmington failed to rebut the many red flags discussed above, each of\n\nwhich independently called for more robust due diligence by Wilmington. Id. at 656–57.\n\nFor the reasons we have explained above, we find no clear error in any of these findings\n\nand so reject this final argument from Wilmington as to Constellis management’s\n\nfinancial projections.\n\n 3.\n\n The district court found that Wilmington’s third major failure in ensuring that its\n\nreliance on the SRR valuation was reasonably justified occurred when it “did not\n\ninvestigate the appropriateness of applying a 10% control premium” to Constellis stock\n\nand “fail[ed] to discount the [valuation] for lack of control.” Brundle I, 241 F. Supp. 3d\n\nat 638.\n\n Purchasers will generally pay more for “rights associated with control of the\n\nenterprise.” Estate of Godley v. Comm’r, 286 F.3d 210, 214 (4th Cir. 2002). We have\n\ndefined “control” as “an interest which allows the shareholder to unilaterally direct\n\ncorporate action, select management, decide the amount of distribution, rearrange the\n\n 22\n\fcorporation’s capital structure, and decide whether to liquidate, merge, or sell assets.” Id.\n\nat 215 (internal quotation marks omitted).\n\n The district court recognized that the ESOP had “powers beyond those of an\n\nordinary shareholder.” Brundle I, 241 F. Supp. 3d at 627 n.23. But the court nonetheless\n\nfound that the “ESOP essentially had no power to control Constellis” as a result of the\n\ntransaction’s unique structure. Id. at 638–39. Accordingly, the court concluded that\n\nWilmington erred in failing to investigate the SRR valuation, which not only failed to\n\ndiscount the stock for lack of control, but even added a 10% control premium to the value\n\nof the Constellis stock. The record supports both findings.\n\n The Sellers retained the power to appoint a majority of the Constellis board, a key\n\nindicator of control. See id. at 626. Further, the ESOP governing plan document and the\n\nESOP trust agreement each required Wilmington to vote its shares as the Constellis\n\nboard (not the ESOP) directed. See id. at 626–27. Wilmington maintains that the ESOP\n\ncould independently exercise its voting powers because the plan documents included a\n\nclause nullifying any provision that violated ERISA. But Constellis’s general counsel\n\ntestified at trial that the ESOP could only contravene the plan documents and exercise its\n\nindependent voting authority by filing a lawsuit — the same limited relief available to a\n\nminority shareholder. The district court thus concluded that Wilmington breached its\n\nfiduciary obligation in failing to question SRR’s failure to discount for lack of control.\n\nSee id. at 639. Given the record evidence that the ESOP’s unique ownership structure\n\nwas intentionally designed to maintain the Sellers’ control over Constellis even after\n\nselling their shares, the district court’s conclusion hardly constitutes clear error.\n\n 23\n\f Wilmington next contends that even if the ESOP lacked control, a 10% control\n\npremium was justified by the fact that the ESOP owned 100% of Constellis shares and\n\nobtained “elements of control.” Id. at 647. Wilmington argues that SRR reasonably\n\napplied a “modest” 10% control premium given that market control premiums are often\n\nbetween 35–40%. But in light of the limited rights provided to the ESOP, we cannot\n\nconclude that the district court erred in finding that Wilmington should have done more\n\nto challenge the use of any control premium. The SRR Report “devoted just one sentence\n\nto articulating its decision,” yet Wilmington never asked SRR about its decision to apply\n\na control premium. Id. at 639. For an assumption that carried such weighty\n\nconsequences, we cannot say that the district court clearly erred in finding that a\n\nreasonably prudent fiduciary would have probed the issue further.\n\n 4.\n\n The final major fault that the district court identified in Wilmington’s reliance on\n\nthe SRR Report was Wilmington’s failure to probe why SRR consistently rounded the\n\nvaluation of Constellis stock upwards. This repeatedly increased the price the ESOP had\n\nto pay for the stock. The district court concluded that because an ESOP fiduciary should\n\nbe concerned with achieving the lowest possible price for the ESOP, Wilmington ought\n\nto have asked why SRR consistently engaged in the upward rounding to the ESOP’s\n\ndetriment. Id. at 639–40.\n\n Wilmington devotes only a short footnote in its opening brief to this issue and fails\n\nto address it at all in its reply brief. It thus appears to have forfeited an appellate\n\nchallenge to the court’s findings on this issue. See Wahi v. Charleston Area Med. Ctr.,\n\n 24\n\fInc., 562 F.3d 599, 607 (4th Cir. 2009) (finding argument raised only in a footnote in\n\nappellant’s opening brief forfeited on appeal). Perhaps this is because the district court’s\n\nfinding is self-evidently correct. And, as the district court noted, Brundle I, 241 F. Supp.\n\n3d at 640, this conclusion accords with those of other courts. For example, the Sixth\n\nCircuit described a similar rounding practice as “extremely disconcerting” and noted that\n\nthis conduct, although not dispositive, was illustrative of lackluster due diligence\n\ndisplayed throughout the transaction process. Chao, 285 F.3d at 433–34. So too here.\n\n B.\n\n Apart from Wilmington’s four major failures to scrutinize SRR’s report, the\n\ndistrict court also found that Wilmington’s conduct throughout the transaction provided\n\nfurther evidence that Wilmington failed to act as a prudent fiduciary solely on behalf of\n\nthe ESOP participants. Although the court found that Wilmington’s actions on behalf of\n\nthe ESOP did not amount to bad faith, it recognized that “ERISA demand[ed] more to\n\nexcuse a fiduciary from liability.” Brundle I, 241 F. Supp. 3d at 643.\n\n The district court found that Constellis’s principal motivation for creating the\n\nESOP was to further the Sellers’ interests, not the interests of the ESOP participant\n\nbuyers. Id. at 616. The sale of Constellis to the ESOP enabled the Sellers to cash out\n\ntheir company stock, which they had tried and failed to accomplish several times, and to\n\nreap substantial tax savings. Moreover, the ESOP’s unique structure enabled the Sellers\n\nto avoid the downside risk of holding equity, yet profit from any upside, while also\n\nretaining control over the company. The court found that Wilmington, in its role as the\n\n\n\n 25\n\fESOP’s fiduciary, simply ignored these motivations rather than investigating whether\n\nthey affected the ESOP’s legality under ERISA. Id. at 640–42.\n\n The district court additionally found that making the Sellers’ interests paramount\n\nshortened the transaction timeline and rushed Wilmington’s due diligence process and\n\nprice and terms negotiations. To maximize the after-tax benefits to the Sellers, the ESOP\n\nsale had to conclude before the end of 2013. Accordingly, Wilmington and its agents\n\ncompleted their due diligence, made pricing decisions, conducted negotiations, and\n\nlaunched a tender offer in less than two months. Id. at 621–25. Wilmington employees\n\nmet to discuss the transaction only three times and met with Constellis management just\n\nonce. Id. at 642. All meetings lasted less than 90 minutes and several of Wilmington’s\n\nteam members were absent from each. Id. And the district court found that Wilmington\n\nviolated its own policy by repeatedly taking less than 48 hours between receiving a\n\nvaluation report and meeting to discuss it. Id. at 621, 625. The court concluded that this\n\ntype of conduct fell well short of the diligence expected of a prudent fiduciary. Id. at\n\n643.\n\n Finally, the court noted that “Wilmington’s lack of engagement and willingness to\n\nnegotiate so favorably with CSG may have been motivated by its significant business\n\nrelationship with CSG.” Id. The district court found that Wilmington, CSG, and SRR\n\nmaintained extensive and lucrative business relationships and that SRR was willing to\n\ndiscuss its valuation strategies with CSG while negotiations were ongoing. Id. The\n\nrecord offers ample support for all of these findings.\n\n\n\n 26\n\f C.\n\n Wilmington also maintains that the district court erred in finding that the value of\n\nStock Appreciation Rights (SARs) issued in connection with the ESOP’s purchase of\n\nConstellis should have been deducted from Constellis’s equity value for purposes of\n\nSRR’s valuation. SARs are incentives that Constellis would have owed to management\n\nhad the company’s value reached a certain price by a particular date. Wilmington argues\n\nthe value of the SARs should not have been deducted from Constellis’s estimated value\n\nbecause they were inchoate at the time of the sale. The district court disagreed and found\n\nthat, because Constellis intended for the SARs to be issued, their value should have been\n\ndeducted from Constellis’s equity value. Id. at 648.\n\n Wilmington rehashes the same argument on appeal but fails to identify any\n\nevidence that demonstrates the district court clearly erred in this factual determination.\n\nBecause we discern no such evidence, we reject this claim.\n\n D.\n\n In support of its final attack on the district court’s liability findings, Wilmington\n\nrelies on the ESOP’s subsequent sale of Constellis stock to ACADEMI LLC.\n\n In early February 2014, less than two months after the ESOP transaction,\n\nACADEMI, a major competitor in the private security market, began talks with\n\nConstellis management to acquire the company. Id. at 628. Initially, ACADEMI offered\n\nto purchase Constellis at an enterprise value of $283.3 million, in a transaction that would\n\nresult in $10 million in cash going to the ESOP. Seeking a better offer on the ESOP’s\n\nbehalf, Wilmington entered into negotiations with Constellis, the Sellers, and\n\n 27\n\fACADEMI. Id. at 629. Wilmington’s efforts proved successful: the final transaction,\n\nwhich closed on July 25, 2014, effectuated a sale of all the Constellis stock to ACADEMI\n\nat an implied enterprise value of $288.3 million. Id. at 631. The final transaction paid\n\n$20 million in cash to the ESOP — double the initial $10 million offer — as a result of\n\nthe Sellers’ agreeing to write off $33 million of the ESOP’s debt. Id. at 629.\n\n Wilmington argues that the ACADEMI sale proves that the ESOP did not overpay\n\nfor Constellis seven months earlier. Relying on the first prong of DOL’s proposed\n\nadequate-consideration regulations, Wilmington maintains that the ESOP paid “fair\n\nmarket value” for the Constellis stock because ACADEMI’s purchase of Constellis stock\n\nimplied an enterprise value of $288.3 million, which was within SRR’s estimated range\n\nof $275 to $330 million. Wilmington contends this purchase price is of particular\n\nsignificance because in the intervening time Constellis assertedly suffered several\n\nbusiness setbacks that decreased its enterprise value. 8\n\n This argument is unpersuasive for several reasons. The proposed DOL regulations\n\nupon which Wilmington relies provide that a trustee can prove consideration is\n\n“adequate” if it reflects the stock’s “fair market value” and is “the product of a\n\ndetermination made by the fiduciary in good faith.” Proposed Regulation Relating to the\n\n\n 8\n The district court carefully considered and described these setbacks in detail. See\nBrundle I, 241 F. Supp. 3d at 627–28. Briefly, the State Department made a formal\ndemand for payment of $62.2 million as part of its audit of Constellis’s accounting and\nrecord-keeping practices; Constellis was forced to reduce projected revenue from a\ncontract in Iraq by more than $100 million and push the remaining revenue further into\nthe future; its projected revenue from a contract in Kuwait decreased by tens of millions\nof dollars; and it lost a $338 million contract in Germany it had expected to win. Id.\n\n 28\n\fDefinition of Adequate Consideration, 53 Fed. Reg. at 17,633. Of course, because the\n\nDOL never enacted the proposed regulations, they are not binding. And, as we have\n\nexplained, courts look to the conduct of the trustee and whether it met its fiduciary\n\nobligations, not to whether the trustee arrived at a “fair” value. But even if we were to\n\nadopt the DOL’s proposed regulations, a trustee must satisfy both parts of the test to\n\nbenefit from the adequate consideration exception. See id. Assuming arguendo that the\n\npurchase was for “fair market value,” we find no error in the district court’s findings that\n\nWilmington failed to prove that the share price was also “the product of a determination\n\nmade by the fiduciary in good faith.”\n\n Furthermore, even if proving the ESOP paid “fair market value” sufficed to meet\n\nthe requirements of § 1108(e), the facts of the ACADEMI sale do not prove that the\n\nESOP paid only “fair market value” here. In fact, the district court found that the\n\nopposite was true. The court found that because ACADEMI, a private security company\n\nlike Constellis, would benefit from synergies resulting from its purchase of Constellis, it\n\nwould have been willing to pay significantly more for Constellis than the ESOP. Thus,\n\nthat ACADEMI actually paid less for Constellis stock suggested a significantly lower fair\n\nmarket value for the stock at the time of the ESOP purchase. Of course, Wilmington’s\n\nexperts disagreed with this synergies analysis, but the district court found the testimony\n\nof other experts on this point more persuasive. Brundle I, 241 F. Supp. 3d at 640. The\n\nrecord provides no basis to reject this finding. See Hendricks v. Cent. Reserve Life Ins.\n\nCo., 39 F.3d 507, 513 (4th Cir. 1994) (“An appellate court should be especially reluctant\n\n\n\n 29\n\fto set aside a finding based on the trial court’s evaluation of conflicting expert\n\ntestimony.”).\n\n In sum, the district court found that the ACADEMI sale did not constitute a\n\nmeaningful comparator. Discounting the additional synergy value, the $33 million debt\n\nwrite-off by the Sellers, and an expected tax refund from the sale, the court found the\n\nACADEMI purchase suggested that Constellis’s fair market value was closer to $200\n\nmillion — almost $100 million less than the enterprise value implied by the ESOP\n\ntransaction. Thus, the court found, the ACADEMI sale could not support Wilmington’s\n\nargument that the ESOP paid no more than adequate consideration for Constellis.\n\nBrundle I, 241 F. Supp. 3d at 640. We see no clear error in this conclusion.\n\n Additionally, we note that, despite paying more for Constellis stock, the ESOP did\n\nnot obtain nearly the level of control that ACADEMI acquired. While the ESOP\n\nobtained only some elements of control, ACADEMI acquired absolute and uncontested\n\ncontrol. Had the district court applied the “standard” 35–40% control premium\n\nWilmington’s experts suggested was reasonable, Constellis’s fair market value would fall\n\nsomewhere between $145 million and $150 million, almost half the value of the stock\n\npurchased by the ESOP only months earlier.\n\n\n\n III.\n\n Having rejected all of Wilmington’s challenges to the district court’s findings as to\n\nits liability, we turn to the court’s damages award. The district court concluded that\n\nWilmington’s fiduciary failures inflated the price the ESOP paid for Constellis stock by\n\n 30\n\f$29,773,250. “We review factual findings relating to the calculation of damages for clear\n\nerror.” Simms v. United States, 839 F.3d 364, 368 (4th Cir. 2016).\n\n A.\n\n To calculate the loss to an ESOP and compensate it for a fiduciary’s ERISA\n\nviolation, a court typically subtracts the stock’s fair market value, as determined by the\n\ncourt, from the inflated price paid by the ESOP. See Bruister, 823 F.3d at 265 (collecting\n\ncases). The district court precisely followed this approach. The court used as a baseline\n\nthe comprehensive damages estimate provided by Brundle’s expert — the only expert to\n\noffer one. 9 The court then considered the flaws in this valuation raised by Wilmington\n\nand made “appropriate adjustments based on the evidence adduced at trial and the\n\nrelative credibility of the experts.” Brundle I, 241 F. Supp. 3d at 645.\n\n Brundle’s expert estimated Wilmington’s lack of due diligence had caused the\n\nESOP to overpay for the Constellis stock by almost $103,862,000. But the district court\n\ndid not accept this figure. Instead, it independently analyzed each of Wilmington’s\n\npurported failings, considered the relevant trial testimony, and then awarded $29,773,250\n\n— or less than a third of the expert’s estimation — as damages. Id. at 645–49. The\n\nfollowing chart summarizes the district court’s damages findings:\n\n Error Difference between fair market value and\n inflated price paid by ESOP (Damages)\n Reliance on Management’s $4,325,000\n Growth Projections\n Use of .07 Beta $2,936,000\n\n 9\n The Fifth Circuit held, in another ESOP case involving this same expert, that a\ntrial court “was entitled to credit” his valuation methodology. Bruister, 823 F.3d at 267.\n\n 31\n\f Inclusion of Control Premium $8,186,000\n Failure to Include Lack of $9,715,250\n Control Discount\n Stock Appreciation Rights $1,611,000\n Rounding $3,000,000\n Total Damages $29,773,250\n\n Wilmington did not provide the district court with an alternative damages\n\ncalculation or offer any evidence that the court could use to devise its own. At oral\n\nargument before us, Wilmington conceded as much. Accordingly, it has forfeited its\n\nchallenge to the methodology used by the district court when calculating the damages\n\naward. See Exxon Shipping Co. v. Baker, 554 U.S. 471, 487 n.6 (2008) (“[W]aiver and\n\nforfeiture rules . . . ensure that parties can determine when an issue is out of the case, and\n\nthat litigation remains, to the extent possible, an orderly progression.”).\n\n Moreover, Wilmington’s principal basis for urging reversal of the damages award\n\nconsists of a repetition of its challenge to the district court’s liability findings. Given our\n\naffirmance of all the district court’s liability findings — that Wilmington failed to\n\nadequately investigate and probe SRR as to the omission of the McLean Report, the use\n\nof Constellis management’s growth projections, the 0.7 beta, the 10% control premium,\n\nimproper rounding up, and SARs — that challenge fails.\n\n B.\n\n Wilmington additionally contends that the district court erred in declining to offset\n\nits damages calculation by the $20 million in cash that the ESOP received as a result of\n\nthe ACADEMI sale. According to Wilmington, “the district court’s failure to” do so\n\n“resulted in a clear windfall for the ESOP.” Wilmington Opening Br. at 53. As the\n\n 32\n\fdistrict court ably explained, see Brundle II, 258 F. Supp. 3d at 660–62, this claim is\n\nmeritless.\n\n ERISA expressly requires a fiduciary to “make good to [an ESOP] any losses”\n\nresulting from a given breach of duty. 29 U.S.C. § 1109(a); cf. Restatement (Second) of\n\nTrusts § 205 cmt. e (“If the trustee is authorized to purchase property for the trust, but in\n\nbreach of trust he pays more than he should pay, he is chargeable with the amount he paid\n\nin excess of its value.”). Thus, in cases involving overpayment for ESOP assets, courts\n\ngenerally compute restitution damages exactly as the district court did here: by deducting\n\nthe fair market value of the stock from the amount the ESOP actually paid.\n\n Wilmington insists that the ESOP’s subsequent and unrelated sale of the stock to\n\nACADEMI requires a different result. This misapprehends the nature of the breach. If\n\nWilmington had breached its duty by purchasing Constellis stock at all, then a damages\n\naward consisting of the purchase payments offset by any subsequent profits would indeed\n\nreturn the participants to the pre-purchase status quo.\n\n But Wilmington breached here by overpaying for the Constellis stock. Principles\n\nof restitution therefore entitle the ESOP and its participants to compensation for the loss\n\nfrom the overpayment. Any subsequent gains involving the stock, which the ESOP\n\nwould have obtained regardless of the overpayment, have no bearing on that loss. For\n\nthis very reason, courts have uniformly rejected analogous offsets to damage awards in\n\noverpayment cases. See, e.g., Bruister, 823 F.3d at 270–71 (rejecting offset to account\n\nfor unpaid or forgiven ESOP debt and noting that “[e]very court to consider this\n\nquestion” agreed); Henry v. U.S. Trust Co. of Cal., N.A., 569 F.3d 96, 98–100 (2d Cir.\n\n 33\n\f2009) (“Henry V”) (“If an investor pays $100 for 20 shares of stock and later sells those\n\nshares back to the original seller for $25, the result is not that the investor paid only $75\n\nfor the shares.”).\n\n Even so, Wilmington asserts that the events in this case resulted in “pure gain” to\n\nthe ESOP, justifying a deviation from this rule. It claims the ESOP “made $20 million\n\nfor the nominal cost of carrying $200 million in non-recourse debt for a few months,”\n\nbecause “[j]ust seven months” after the prohibited transaction, “the ESOP exchanged its\n\ndebt-burdened shares to ACADEMI for $20 million in cash.” Wilmington Opening Br.\n\nat 55–56. We disagree. As a preliminary matter, the burden imposed in additional debt\n\nfrom a $30 million overpayment is far from “nominal,” even for “just” seven months.\n\nSee Henry V, 569 F.3d at 99 n.4 (explaining “the obvious fact that the assumption of\n\nindebtedness has immediate legal and economic consequences even before the borrower\n\nbegins to repay the debt”).\n\n Moreover, if Wilmington seeks to portray the ACADEMI sale as an “exchange” in\n\nwhich the ESOP’s pre-sale debt had no effect on its post-sale assets, this is both illogical\n\nand untrue. Had the ESOP not initially overpaid for the stock by $30 million, it would\n\nhave shouldered tens of millions of dollars less in debt; in turn, it would presumably have\n\nbeen tens of millions of dollars better off after being compensated for the stock in the\n\nACADEMI sale. Put differently, although the ESOP benefited despite the breach, it\n\nwould have benefited at least as much — but ended in a far better position — without the\n\nbreach. In fact, had the ESOP initially paid a fair (lower) value for the Constellis stock\n\n\n\n 34\n\fand therefore carried less debt, it would have entered the ACADEMI negotiations in a\n\nstronger bargaining position and may have profited further still.\n\n Wilmington rejects this conclusion, stressing that the Sellers also agreed to write\n\noff more than $30 million of the ESOP’s debt, which it describes as an “effective[]\n\nreduc[tion]” of the 2013 purchase price. Wilmington Opening Br. at 56. But once again,\n\nthis independent act has no bearing on the ESOP’s loss.\n\n Wilmington unpersuasively contends that Henry III supports its argument. That\n\ncase addressed very different facts. There, the Second Circuit held that — where sellers\n\nfully and voluntarily repaid an ESOP after the IRS found overpayment, but before a court\n\nentered a damages judgment — a duplicative recovery for the same overpayment might\n\n“result in a windfall.” Henry III, 445 F.3d at 624. Wilmington does not even argue that\n\nthe Sellers’ write-off here was meant to remedy the ESOP’s overpayment. Nor could it:\n\nunlike the midstream repayment in Henry, the write-off here occurred more than a year\n\nprior to the initiation of any legal proceedings alleging Wilmington breached its fiduciary\n\nduties. As Wilmington concedes, the write-off was part of a negotiated agreement to\n\nclose the ACADEMI sale, a deal wholly unrelated to the issues raised here. Again, it is\n\nreasonable to assume that the ESOP would have negotiated equally favorable (if not more\n\nfavorable) terms had it paid a fair value in the first instance and thus entered the\n\nACADEMI discussions with substantially less debt.\n\n In sum, we find no error in the district court’s damages award.\n\n\n\n\n 35\n\f IV.\n\n Finally, we examine the district court’s award of attorneys’ fees. The court\n\nawarded Brundle’s counsel $1,819,631.11 in statutory fees and an additional $1.5 million\n\nin fees from the ESOP’s damages judgment. No party has presented a substantive\n\nchallenge regarding the award of attorneys’ fees under the fee shifting statute. 10 Brundle\n\nchallenges the $1.5 million in additional fees (payable from the damages awarded to the\n\nESOP) as too small; Wilmington and Constellis, as fiduciaries for the ESOP, challenge\n\nthe award as legally improper. We review that award for abuse of discretion, mindful\n\nthat our review “is sharply circumscribed, and a fee award must not be overturned unless\n\nit is clearly wrong.” Berry v. Schulman, 807 F.3d 600, 617 (4th Cir. 2015) (internal\n\nquotation marks omitted).\n\n A.\n\n We first consider Brundle’s claim that the district court abused its discretion by\n\nnot awarding his counsel, Bailey & Glasser, LLP (B&G), a total of $9.9 million in fees\n\nunder the firm’s one-third contingent fee agreement with Brundle himself. The district\n\ncourt initially suggested that this arrangement was indeed controlling. See Brundle II,\n\n258 F. Supp. 3d at 671–72. But the court held its fee decision in abeyance to consider the\n\n\n 10\n Strangely, although Brundle does not challenge the statutory fee award, he does\nsummarily contend that he is entitled to $643,584.50 in expenses (the amount he\nrequested when seeking statutory fees in the district court). The district court denied his\nrequest for expenses, explaining that it was insufficiently documented. See Brundle II,\n258 F. Supp. 3d at 669. Before us, Brundle provides neither documentation nor\nargument. Accordingly, to the extent he even appeals the denial of expenses, we affirm\nthe district court.\n\n 36\n\fviews of plan participants and ultimately based its award on equity rather than contract.\n\nWe can hardly find an abuse of discretion given that Brundle has no right to have the\n\nESOP fund his own fee agreement with B&G.\n\n Brundle contends that 29 U.S.C. § 1132(a)(2) — which empowers ESOP\n\nparticipants and beneficiaries to bring suit on behalf of an ESOP — additionally\n\nauthorizes him to enter into a legal services contract that binds the ESOP. Brundle\n\nmusters no caselaw to support his interpretation of the statute, and for good reason.\n\nWhile § 1132(a)(2) provides Brundle the right to sue on behalf of the ESOP, neither it\n\nnor any other statute authorizes him to unilaterally bind the ESOP to a contract or fee\n\nagreement. For this very reason, the vast majority of suits on behalf of ERISA plans take\n\nthe form of class actions, in which counsel can seek fees only after a class has been\n\ncertified and class members have been given the opportunity to object or opt out. Though\n\nB&G has a valid contingent fee agreement with Brundle, see Venegas v. Mitchell, 495\n\nU.S. 82 (1990), it does not have a fee agreement with the ESOP.\n\n As a result, only equity provides any possible basis for a fee award in addition to\n\nthe statutory fees awarded.\n\n B.\n\n After the district court received the views of some plan participants, it issued a\n\nfinal judgment awarding B&G $1.5 million in “addition[]” to the $1.8 million in statutory\n\n\n\n\n 37\n\ffees — not as a contractual right, but as “a partial common fund award.” 11 Wilmington\n\nand Constellis assert that a trio of ERISA provisions precluded the court from awarding\n\nany common fund recovery. Unlike most challenges to fee awards, we review de novo\n\nquestions regarding a court’s legal authority. See, e.g., Country Vintner of N.C., LLC v. E\n\n& J. Gallo Winery, Inc., 718 F.3d 249, 254 (4th Cir. 2013).\n\n First, Wilmington and Constellis contend that any common fund award here would\n\nviolate ERISA’s “anti-alienation” and “exclusive benefit” provisions. See 29 U.S.C.\n\n§ 1056(d)(1) (providing that benefits under retirement plans cannot be “assigned or\n\nalienated”); id. § 1103(c)(1) (directing all “assets of a plan” to be “held for the exclusive\n\npurposes of providing benefits to participants in the plan and their beneficiaries and\n\ndefraying reasonable expenses of administering the plan”). But the district court properly\n\nrejected this argument, concluding that because the plan administrator did not yet possess\n\nthe damages award — in other words, the court still had jurisdiction over the funds and\n\nhad not distributed them to the ESOP — it could not be considered a plan asset. Brundle\n\nII, 258 F. Supp. 3d at 670. Of course, if the ESOP had received payment of the award,\n\nthose funds would have been subject to ERISA’s duties and protections. See Wilmington\n\n\n 11\n The district court made clear, and the parties do not dispute, that “[i]n granting\nboth fee-shifting and contingent fee awards, . . . the contingent fee award must be offset\nby the amount awarded under the fee-shifting provision.” Brundle II, 258 F. Supp. 3d at\n672 & n.19. On appeal, Brundle seeks a total of approximately $9.9 million in fees plus\nabout $650,000 in purported expenses, which (when offset by the $1.8 million in\nstatutory fees paid by Wilmington) would entitle B&G to a net of approximately $8.8\nmillion from the common fund. The district court instead awarded Brundle a net of only\n$1.5 million in fees from the common fund, which it noted was in “addition[]” to the $1.8\nmillion statutory fee-shifting award, for a total of $3.3 million in fees.\n\n 38\n\fShipping Co. v. New England Life Ins. Co., 496 F.3d 326, 333 (4th Cir. 2007). But where\n\na fund is still under the jurisdiction of the district court, the court may award fees from\n\nthat fund without running afoul of ERISA’s anti-alienation or exclusive benefit\n\nrequirements. See Kickham Hanley P.C. v. Kodak Ret. Income Plan, 558 F.3d 204, 213\n\n(2d Cir. 2009); Lynn v. CSX Transp., Inc., 84 F.3d 970, 975 (7th Cir. 1996).\n\n Next, Wilmington and Constellis argue that ERISA’s statutory fee-shifting\n\nprovision displaces the common fund doctrine. See 29 U.S.C. § 1132(g)(1) (authorizing\n\nprevailing plaintiffs to recover reasonable attorneys’ fees from defendants). They urge us\n\nto follow the Seventh Circuit in “limiting the common-fund approach to cases outside the\n\nscope of a fee-shifting statute.” Pierce v. Visteon Corp., 791 F.3d 782, 787 (7th Cir.\n\n2015); accord Haggart v. Woodley, 809 F.3d 1336, 1358–59 (Fed. Cir. 2016) (largely\n\nadopting Pierce rule). 12\n\n Several other circuits, however, have disagreed with this approach. See McKeage\n\nv. TMBC, LLC, 847 F.3d 992, 1003 (8th Cir. 2017) (“[T]he presence of a fee-shifting\n\nstatute precludes a common fund award only when that result is required by the statutory\n\nscheme involved.”); In re Bluetooth Headset Prods. Liab. Litig., 654 F.3d 935, 941 (9th\n\nCir. 2011) (“The award of attorneys’ fees in a class action settlement is often justified by\n\n[a] common fund or statutory fee-shifting[,] . . . and sometimes by both.”); Staton v.\n\n\n 12\n Pierce is in some tension with prior Seventh Circuit cases holding, in the\ncontext of settlements, that common fund recoveries are sometimes available even where\na case was brought under a statute with a fee-shifting provision. See Florin v.\nNationsbank of Georgia, N.A., 34 F.3d 560, 563–64 (7th Cir. 1994); Skelton v. Gen.\nMotors Corp., 860 F.2d 250, 252–57 (7th Cir. 1988).\n\n 39\n\fBoeing Co., 327 F.3d 938, 967–69 (9th Cir. 2003) (permitting common fund recovery\n\neven where statutory fees may be available); Cty. of Suffolk v. Long Island Lighting Co.,\n\n907 F.2d 1295, 1327 (2d Cir. 1990) (“In our view, fee-shifting statutes are generally not\n\nintended to circumscribe the operation of the equitable fund doctrine.”).\n\n To determine the proper course here, we consider the roots of the common fund\n\ndoctrine. The common fund principle derives from the equitable doctrines of quantum\n\nmeruit, Central Railroad & Banking Co. v. Pettus, 113 U.S. 116 (1885), and unjust\n\nenrichment, Trustees v. Greenough, 105 U.S. 527, 532 (1881). It allows a court to award\n\n“a reasonable attorney’s fee” to “a litigant or a lawyer who recovers a common fund for\n\nthe benefit of persons other than himself or his client . . . from the fund as a whole.”\n\nBoeing Co. v. Van Gemert, 444 U.S. 472, 478 (1980). The rationale for the doctrine is\n\nthat when one benefits from a lawsuit without contributing to its costs, he has been\n\nunjustly enriched at the successful litigant’s or lawyer’s expense. Mills v. Elec. Auto-Lite\n\nCo., 396 U.S. 375, 392 (1970). Courts remedy this inequity by shifting a proportional\n\nshare of reasonable attorneys’ fees onto these unjustly enriched beneficiaries.\n\n The Supreme Court has applied the “strong and uniform . . . background rule” of\n\nthe common fund doctrine “in a wide range of circumstances as part of [its] inherent\n\nauthority.” US Airways, Inc. v. McCutchen, 569 U.S. 88, 104 (2013) (collecting cases).\n\nWe agree with Brundle that it applies here. Scores of unnamed ESOP participants\n\nbenefited substantially from this lawsuit, while B&G bore the entirety of the costs and\n\nrisks. Equity thus demands that the enriched participants pay a proportional share of\n\nreasonable attorneys’ fees.\n\n 40\n\f To be sure, courts often, but not invariably, award common fund fees when a\n\nprocedural obstacle, such as the terms of a settlement, bars statutory fees that are\n\notherwise available. 13 But it does not follow that all statutory fee provisions necessarily\n\ndisplace the doctrine or render it superfluous. To the contrary: although both the\n\ncommon fund doctrine and fee-shifting statutes facilitate suit by plaintiffs who may\n\notherwise lack the means to hire counsel, they operate in distinct ways and serve distinct\n\npurposes.\n\n A common fund recovery places the plaintiffs’ cost of litigation on the recovering\n\nbeneficiaries of a lawsuit, whereas a fee-shifting statute places this burden on the losing\n\nparty. Cf. Venegas, 495 U.S. at 90 (differentiating between “what the losing defendant\n\nmust pay” to the plaintiff as attorneys’ fees under a fee-shifting statute and “what the\n\nprevailing plaintiff must pay his lawyer”). A fee-shifting statute thus creates an\n\nexception to the “American rule” that “the prevailing litigant is ordinarily not entitled to\n\ncollect a reasonable attorneys’ fee from the loser.” Alyeska Pipeline Serv. Co. v.\n\nWilderness Soc., 421 U.S. 240, 247 (1975). In contrast, the common fund doctrine —\n\nthough often similarly described as an exception — better accords with the American rule\n\n 13\n See, e.g., Skelton, 860 F.2d at 256 (affirming common fund award where “the\nfee-shifting provision [did] not . . . apply to a fee determination in a case settled in a\ncommon fund”); In re Fine Paper Antitrust Litig., 751 F.2d 562, 582–83 (3d Cir. 1984)\n(affirming common fund award where settlement released defendants from statutorily\navailable fees). But see Reyes v. Bakery & Confectionary Union & Indus. Int’l Pension\nFund, 281 F. Supp. 3d 833, 850 (N.D. Cal. 2017) (“[C]lass counsel may be awarded fees\nfrom the common fund in addition to any award under ERISA’s fee-shifting statute.”);\nHumphrey v. United Way of Tex. Gulf Coast, 802 F. Supp. 2d 847, 859 (S.D. Tex. 2011)\n(“The Court . . . has the power and discretion to award reasonable fees under both\n[ERISA] and the common fund doctrine.”).\n\n 41\n\fby holding the beneficiaries of a judgment or settlement responsible for compensating the\n\ncounsel who obtained the judgment or settlement for them. See Staton, 327 F.3d at 967.\n\n Furthermore, the purpose of the common fund doctrine, unlike a fee-shifting\n\nstatute, is to avoid unjust enrichment. Thus, although a statutory fee award against a\n\ndefendant generally may not include a contingency enhancement, see City of Burlington\n\nv. Dague, 505 U.S. 557, 565–67 (1992), courts routinely impose enhanced common fund\n\nawards to compensate counsel for litigation risk at the expense of beneficiaries who did\n\nnot shoulder this risk, see, e.g., In re Wash. Pub. Power Supply Sys. Secs. Litig., 19 F.3d\n\n1291, 1300 (9th Cir. 1994) (“There is nothing unfair about contingency enhancements in\n\ncommon fund cases . . . .”); Florin, 34 F.3d at 564–65 (similarly holding that “the policy\n\nconsiderations . . . that militate for forbidding risk multiples in statutory fee-shifting cases\n\nhave little force in common fund cases”).\n\n From these distinctions, it follows that a “reasonable” fee payable by a defendant\n\nto compensate the prevailing plaintiff’s counsel is not necessarily identical to a\n\n“reasonable” fee owed by a recovering beneficiary to plaintiff’s counsel, particularly\n\nwhere the contingency risk to plaintiff’s counsel is substantial. Cf. Venegas, 495 U.S. at\n\n85, 90 (affirming $406,000 contractual fee, paid by prevailing plaintiff to his counsel, as\n\nnot “unreasonable” even though “reasonable” statutory fee, paid by losing defendants,\n\nwas only $117,000); McKeage, 847 F.3d at 1004 (emphasizing “a distinction between the\n\namount a losing party may be required to pay” under fee-shifting provision in settlement\n\n“and the amount a class member should equitably be required to pay” under common\n\nfund doctrine).\n\n 42\n\f Consequently, we find unpersuasive the Seventh Circuit’s reasoning in Pierce. In\n\nlimiting the common fund doctrine to cases “outside the scope of a fee-shifting statute,”\n\nthe Pierce court reasoned first and foremost that “[c]ommon-law doctrines yield to\n\nstatutes.” 791 F.3d at 787. But the Supreme Court has instructed that courts must\n\n“presum[e] that Congress intended to retain the substance of the common law.”\n\nSamantar v. Yousuf, 560 U.S. 305, 320 n.13 (2010). We recognize, of course, that\n\nlegislative displacement of the common law does not require “the same sort of evidence\n\nof a clear and manifest congressional purpose demanded for preemption of state law.”\n\nAm. Elec. Power Co., Inc. v. Connecticut, 564 U.S. 410, 423 (2011) (alterations and\n\ninternal quotation marks omitted). Even so, a statute that shifts a reasonable fee onto a\n\nlosing defendant does not, without more, “speak[] directly” to congressional intent to\n\ndisplace recovery from a common fund. Id. at 424 (internal quotation marks omitted).\n\n The Pierce court additionally emphasized that “fee-shifting statutes are designed\n\nto ensure that the victims retain full compensation,” 791 F.3d at 787, a concern of\n\nindisputable importance. The common fund doctrine, however, balances this critical\n\ninterest against the concern of unjust enrichment, which ERISA’s fee-shifting provision\n\ndoes not purport to address.\n\n Finally, echoing the Pierce court, Wilmington and Constellis stress that B&G was\n\nentitled to, and received, a “reasonable” attorneys’ fee under statute. However, as we\n\nhave explained, what is “reasonable” as a fee from a losing defendant may well differ\n\nfrom what is “reasonable” as a fee from an individual directly benefited by counsel’s\n\nefforts. We particularly note that a “reasonable” fee under ERISA’s attorneys’ fee\n\n 43\n\fprovision (unlike a common fund award) precludes any compensation for contingency\n\nrisk. See Dague, 505 U.S. at 565–67. But, we have previously underscored, contingent\n\nfees serve an important function in providing under-resourced litigants access to counsel\n\nand the courts. In re Abrams & Abrams, P.A., 605 F.3d 238, 245–47 (4th Cir. 2010).\n\nConflating statutory attorneys’ fees with common fund recoveries would squarely\n\ncontravene this policy.\n\n We therefore agree with the Second, Eighth, and Ninth Circuits that a statutory\n\nfee-shifting provision (or an award of fees under such a provision) does not, as a matter\n\nof law, automatically preclude an award under the common fund doctrine. Accordingly,\n\nthe district court retained discretion to award supplemental attorneys’ fees from the\n\ncommon fund.\n\n C.\n\n Having established the district court’s authority to award supplemental fees, we\n\nturn to Brundle’s contention that the court abused its discretion in awarding its counsel\n\ntoo little from the common fund.\n\n Before setting the amount of its common fund award, the district court fashioned\n\nan ad hoc process analogous to class settlement procedures under Rule 23. Brundle II,\n\n258 F. Supp. 3d at 671–72. The court ordered Brundle’s counsel, B&G, to engage in a\n\ngood faith effort to notify the approximately 1,800 former ESOP participants of its\n\nproposed contingency fee award. After B&G did so, the court received 59 letters\n\nobjecting to a one-third contingency award. As a result of the objections, the court\n\ndecided to award B&G only $1.5 million as a supplemental fee payable from the\n\n 44\n\fdamages award, rather than granting counsel a full one-third ($9.9 million) of the ESOP’s\n\ntotal damages recovery.\n\n In reviewing the district court’s award, we note that Brundle had available a\n\nprocedural mechanism designed to carefully balance the interests of counsel, plaintiffs,\n\nand other similarly situated beneficiaries from the start — namely, class certification\n\npursuant to Rule 23. To be fair, Brundle and another plaintiff, Halldorson, did initially\n\nseek class certification, which the district court denied. But Brundle opted not to timely\n\nappeal this denial. And although Halldorson initially sought our review, he later\n\nwithdrew his appeal. See supra n.4.\n\n Had Brundle pursued class certification and prevailed, B&G could have secured\n\nattorneys’ fees from the class as a whole. Although a properly certified class might not\n\nhave agreed to the same one-third contingency fee that Brundle did, the district court\n\nmight well have awarded a fee significantly higher than the firm’s ultimate recovery\n\nhere. 14\n\n Brundle, represented by B&G, instead opted to forego Rule 23’s procedural\n\nstrictures — thus avoiding “the standards set for the protection of absent class members.”\n\nAmchem Prods., Inc. v. Windsor, 521 U.S. 591, 621 (1997). In light of this choice, the\n\ndistrict court’s decision to limit the common fund award was not inequitable, as\n\nillustrated by the objections from some of the ESOP’s participants. Nearly 60 of the\n\n 14\n See, e.g., Savani v. URS Prof’l Sols. LLC, 121 F. Supp. 3d 564, 574–75 (D.S.C.\n2015) (approving fee award of 39.57% from common fund award in ERISA settlement\nand collecting cases); In re Marsh ERISA Litig., 265 F.R.D. 128, 149 (S.D.N.Y. 2010)\n(approving fee award of 33.33% from common fund award).\n\n 45\n\f1,800 participants objected to the proposed common fund award, explaining that they had\n\nnever been informed of the case status, never agreed to B&G’s representation, and never\n\nauthorized the fund to pay a one-third fee. These process concerns would have been\n\navoided upfront had Brundle persisted in his pursuit of class certification. But because he\n\nand his counsel abandoned Rule 23’s class-protective procedures, equity cuts against\n\nawarding B&G the full one-third contingency fee.\n\n The district court properly weighed B&G’s efforts on behalf of the ESOP —\n\nincluding contingency risk — against the objections from ESOP participants to determine\n\na proper common fund award. Because we cannot say this balancing was clearly wrong,\n\nsee Berry, 807 F.3d at 617, we affirm the court’s fee award in full.\n\n\n\n V.\n\n For the foregoing reasons, the judgment of the district court is in all respects\n\n AFFIRMED.\n\n\n\n\n 46\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Tim Brundle v. Wilmington Trust, N.A.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-03-22\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 17-1873\\n\\n\\nTIM P. BRUNDLE, on behalf of the Constellis Employee Stock Ownership Plan,\\n\\n Plaintiff - Appellee,\\n\\n and\\n\\nANDREW HALLDORSON, on behalf of the Constellis Employee Stock\\nOwnership Plan, and on behalf of a class of all other persons similarly situated,\\n\\n Plaintiff,\\n\\n v.\\n\\nWILMINGTON TRUST, N.A., as successor to Wilmington Trust Retirement and\\nInstitutional Services Company,\\n\\n Defendant - Appellant.\\n\\n-------------------------------------------\\n\\nAMERICAN SOCIETY OF APPRAISERS,\\n\\n Amicus Supporting Appellant,\\n\\nSECRETARY OF THE UNITED STATES DEPARTMENT OF LABOR,\\n\\n Amicus Supporting Appellee.\\n\\n\\n No. 17-2224\\n\\n\\nTIM P. BRUNDLE, on behalf of the Constellis Employee Stock Ownership Plan,\\n\\f Plaintiff - Appellant,\\n\\n and\\n\\nANDREW HALLDORSON, on behalf of the Constellis Employee Stock\\nOwnership Plan, and on behalf of a class of all other persons similarly situated,\\n\\n Plaintiff,\\n\\n v.\\n\\nWILMINGTON TRUST, N.A., as successor to Wilmington Trust Retirement and\\nInstitutional Services Company,\\n\\n Defendant - Appellee.\\n\\n-------------------------------------------\\n\\nSECRETARY OF THE UNITED STATES DEPARTMENT OF LABOR,\\n\\n Amicus Supporting Appellant,\\n\\nAMERICAN SOCIETY OF APPRAISERS,\\n\\n Amicus Supporting Appellee.\\n\\n\\n No. 17-2323\\n\\n\\nTIM P. BRUNDLE, on behalf of the Constellis Employee Stock Ownership Plan,\\n\\n Plaintiff - Appellee,\\n\\n and\\n\\nANDREW HALLDORSON, on behalf of the Constellis Employee Stock\\nOwnership Plan, and on behalf of a class of all other persons similarly situated,\\n\\n Plaintiff,\\n\\nCONSTELLIS GROUP, INC.,\\n\\n\\n 2\\n\\f Party-in-Interest,\\n\\n v.\\n\\nWILMINGTON TRUST, N.A., as successor to Wilmington Trust Retirement and\\nInstitutional Services Company,\\n\\n Defendant - Appellant.\\n\\n-------------------------------------------\\n\\nAMERICAN SOCIETY OF APPRAISERS,\\n\\n Amicus Supporting Appellant,\\n\\nSECRETARY OF THE UNITED STATES DEPARTMENT OF LABOR,\\n\\n Amicus Supporting Appellee.\\n\\n\\n No. 17-2324\\n\\n\\nTIM P. BRUNDLE, on behalf of the Constellis Employee Stock Ownership Plan,\\n\\n Plaintiff - Appellee,\\n\\n and\\n\\nANDREW HALLDORSON, on behalf of the Constellis Employee Stock\\nOwnership Plan, and on behalf of a class of all other persons similarly situated,\\n\\n Plaintiff,\\n\\n v.\\n\\nCONSTELLIS GROUP, INC.,\\n\\n Party-in-Interest - Appellant,\\n\\n and\\n\\n\\n\\n 3\\n\\fWILMINGTON TRUST, N.A., as successor to Wilmington Trust Retirement and\\nInstitutional Services Company,\\n\\n Defendant.\\n\\n\\n No. 18-1029\\n\\n\\nTIM P. BRUNDLE, on behalf of the Constellis Employee Stock Ownership Plan,\\n\\n Plaintiff - Appellant,\\n\\n and\\n\\nANDREW HALLDORSON, on behalf of the Constellis Employee Stock\\nOwnership Plan, and on behalf of a class of all other persons similarly situated,\\n\\n Plaintiff,\\n\\n v.\\n\\nWILMINGTON TRUST, N.A., as successor to Wilmington Trust Retirement and\\nInstitutional Services Company,\\n\\n Defendant - Appellee,\\n\\nCONSTELLIS GROUP, INC.,\\n\\n Party-in-Interest.\\n\\n\\nAppeals from the United States District Court for the Eastern District of Virginia, at\\nAlexandria. Leonie M. Brinkema, District Judge. (1:15-cv-01494-LMB-IDD)\\n\\n\\nArgued: December 11, 2018 Decided: March 21, 2019\\n Amended: March 22, 2019\\n\\n\\nBefore GREGORY, Chief Judge, and MOTZ and FLOYD, Circuit Judges.\\n\\n\\n\\n 4\\n\\fAffirmed by published opinion. Judge Motz wrote the opinion, in which Chief Judge\\nGregory and Judge Floyd joined.\\n\\n\\nARGUED: Carter Glasgow Phillips, SIDLEY AUSTIN LLP, Washington, D.C., for\\nAppellant/Cross-Appellee Wilmington Trust, N.A. Gregory Y. Porter, BAILEY &\\nGLASSER LLP, Washington, D.C., for Appellee/Cross-Appellant. Robin Springberg\\nParry, UNITED STATES DEPARTMENT OF LABOR, Washington, D.C., for Amicus\\nSecretary of Labor. ON BRIEF: James P. McElligott, Jr., Summer L. Speight,\\nRichmond, Virginia, Stephen W. Robinson, MCGUIRE WOODS LLP, Tysons, Virginia;\\nJacqueline G. Cooper, Kurt A. Johnson, SIDLEY AUSTIN LLP, Washington, D.C., for\\nAppellant/Cross-Appellee Wilmington Trust, N.A. Edward Lee Isler, Micah E. Ticatch,\\nISLER DARE, P.C., Vienna, Virginia, for Appellant Constellis Group, Inc. Tillman J.\\nBreckenridge, Ryan T. Jenny, BAILEY & GLASSER LLP, Washington, D.C., for\\nAppellee/Cross-Appellant. J. Christian Nemeth, Chicago, Illinois, Sophia A. Luby,\\nWashington, D.C.; Eliot T. Burriss, Erin Turley, Calli Turner, MCDERMOTT WILL &\\nEMERY LLP, Dallas, Texas, for Amicus American Society of Appraisers. Kate S.\\nO’Scannlain, Solicitor of Labor, G. William Scott, Associate Solicitor for Plan Benefits\\nSecurity, Thomas Tso, Counsel for Appellate and Special Litigation, UNITED STATES\\nDEPARTMENT OF LABOR, Washington, D.C., for Amicus Secretary of Labor.\\n\\n\\n\\n\\n 5\\n\\fDIANA GRIBBON MOTZ, Circuit Judge:\\n\\n After owners of a closely held corporation sold the company to its Employee\\n\\nStock Ownership Plan (“ESOP”), a participant in the ESOP brought this action. The\\n\\nparticipant contended that the trustee chosen for the ESOP by the corporation breached\\n\\nits fiduciary duties to the ESOP and overpaid for the stock — improperly enriching the\\n\\ncorporation’s owners at the expense of its employees.\\n\\n Following a multi-day bench trial, the district court issued detailed findings of fact\\n\\nconcluding that the trustee had indeed breached its fiduciary duties, causing the ESOP to\\n\\noverpay for the corporation’s stock by $29,773,250. The court entered judgment for the\\n\\nESOP in that amount and awarded attorneys’ fees to the participant’s counsel. These\\n\\nappeals and cross-appeals followed. As explained within, we affirm the careful findings\\n\\nof the district court.\\n\\n\\n\\n I.\\n\\n To facilitate understanding of the issues here, we begin with the governing legal\\n\\nprinciples and background facts that gave rise to this suit. The parties do not challenge\\n\\nthese principles or facts. All are more fully set forth in the comprehensive district court\\n\\nopinions, upon which we rely throughout. See Brundle v. Wilmington Tr. N.A., 241\\n\\nF. Supp. 3d 610 (E.D. Va. 2017) (“Brundle I”); Brundle v. Wilmington Tr. N.A., 258\\n\\nF. Supp. 3d 647 (E.D. Va. 2017) (“Brundle II”).\\n\\n\\n\\n\\n 6\\n\\f A.\\n\\n The Employee Retirement Income Security Act of 1974 (ERISA) allows an\\n\\nemployer to create an ESOP, an employee pension plan that invests primarily in the\\n\\nemployer’s stock. The employer makes contributions to the plan that are used to\\n\\npurchase stock in the employer’s company. Because — and only because — an ESOP\\n\\ncontribution qualifies as employee compensation, an employer can deduct the total value\\n\\nof its ESOP contribution from its income tax liability as an ordinary business expense.\\n\\n26 U.S.C. § 404; 26 C.F.R. § 1.404(a)–1(b). 1 In this way, an ESOP benefits both\\n\\nemployees and employers by providing deferred compensation to the former and a\\n\\nvaluable tax deduction to the latter.\\n\\n ERISA imposes duties and obligations on all pension plan fiduciaries, including\\n\\nthose of ESOPs. These duties “ensure that employees will not be left empty-handed once\\n\\nemployers have guaranteed them certain benefits.” Lockheed Corp. v. Spink, 517 U.S.\\n\\n882, 887 (1996). One such provision prohibits the fiduciary of any ERISA plan from\\n\\ncausing a “sale or exchange . . . of any property between the plan and a party in interest.”\\n\\n29 U.S.C. § 1106(a)(1)(A). Absent a statutory exception, this provision would ban\\n\\nESOPs because their creation necessarily requires the ESOP to purchase stock from its\\n\\nsponsoring employer, which is a party in interest. Congress, however, has carved out an\\n\\n\\n\\n 1\\n An employer’s contributions to an ESOP thus constitute a valuable form of\\ndeferred compensation, rather than a gift to employees. See, e.g., Reich v. Hall Holding\\nCo., 990 F. Supp. 955, 961 (N.D. Ohio 1998), aff’d sub nom. Chao v. Hall Holding Co.,\\n285 F.3d 415 (6th Cir. 2002). Wilmington wisely does not suggest otherwise.\\n\\n 7\\n\\fexception to this prohibition to permit the creation of an ESOP if the stock purchase\\n\\nmeets certain conditions. See 29 U.S.C. § 1108(e).\\n\\n To protect employees from losing the value of their earned retirement savings, the\\n\\nexception to the ERISA ban on party-in-interest transactions requires that an ESOP pay\\n\\nno more than “adequate consideration” for the employer’s stock. Id. § 1108(e)(1). If an\\n\\nemployer’s “stock was not worth what the ESOP paid for it,” then the ESOP paid more\\n\\nthan adequate consideration and “the ESOP and its participants suffered a loss under\\n\\nERISA.” See Reich, 990 F. Supp. at 961.\\n\\n ERISA does not define what constitutes “adequate consideration” under the\\n\\n§ 1108(e) exception; the Department of Labor (DOL) has proposed, but never enacted,\\n\\nregulations doing so. 2 Although courts look to these regulations for guidance, the focus\\n\\nof the adequate-consideration inquiry rests on the conduct of a fiduciary, as judged by\\n\\nERISA’s “prudent man” standard of care. See Perez v. Bruister, 823 F.3d 250, 263 (5th\\n\\nCir. 2016); Henry III, 445 F.3d at 619; Chao, 285 F.3d at 437; Howard v. Shay, 100 F.3d\\n\\n1484, 1489 (9th Cir. 1996).\\n\\n Under this standard, “ESOP fiduciaries are subject to the duty of prudence just as\\n\\nother ERISA fiduciaries are.” Fifth Third Bancorp v. Dudenhoeffer, 134 S. Ct. 2459,\\n\\n 2\\n These proposed regulations, to which courts look for guidance, provide that\\n“adequate” consideration must (1) reflect the stock’s “fair market value,” and (2) be “the\\nproduct of a determination made by the fiduciary in good faith.” Proposed Regulation\\nRelating to the Definition of Adequate Consideration, 53 Fed. Reg. 17,632, 17,633\\n(proposed May 17, 1988) (to be codified at 29 C.F.R. pt. 2510). “[I]n practice, the ‘fair\\nmarket value’ inquiry overlaps considerably with the ‘good faith’ inquiry.’” Henry v.\\nChamplain Enters., Inc., 445 F.3d 610, 618–19 (2d Cir. 2006) (Sotomayor, J.) (“Henry\\nIII”) (collecting cases).\\n\\n 8\\n\\f2467 (2014). Thus an ESOP fiduciary, like any other ERISA fiduciary, must “discharge\\n\\nhis duties . . . with the care, skill, prudence, and diligence under the circumstances then\\n\\nprevailing that a prudent man acting in a like capacity and familiar with such matters\\n\\nwould use in the conduct of an enterprise of a like character and with like aims.” 29\\n\\nU.S.C. § 1104(a)(1)(B).\\n\\n Although these fiduciary duties “draw much of their content from the common law\\n\\nof trusts . . . ERISA’s standards and procedural protections partly reflect a congressional\\n\\ndetermination that the common law of trusts did not offer completely satisfactory\\n\\nprotection.” Tatum v. RJR Pension Inv. Comm., 761 F.3d 346, 357 (4th Cir. 2014)\\n\\n(internal quotation marks omitted). Courts apply the “prudent man rule . . . bearing in\\n\\nmind the special nature and purpose of employee benefit plans.” Id. (internal quotation\\n\\nmarks and alterations omitted). For this reason, “[t]he fiduciary obligations of the\\n\\ntrustees to the participants and beneficiaries [of an ERISA] plan are . . . the highest\\n\\nknown to the law.” Id. at 356 (alterations in original) (quoting Donovan v. Bierwith, 680\\n\\nF.2d 263, 272 n.8 (2d Cir. 1982)).\\n\\n Because an ESOP fiduciary that raises an affirmative defense under the § 1108(e)\\n\\nexception seeks to avoid ERISA liability for an otherwise prohibited transaction, the\\n\\nfiduciary bears the burden of proving by a preponderance of the evidence that the sale\\n\\nwas for adequate consideration. See Elmore v. Cone Mills Corp., 23 F.3d 855, 864 (4th\\n\\nCir. 1994) (en banc). “This burden is a heavy one.” Shay, 100 F.3d at 1488.\\n\\n B.\\n\\n With these principles in mind, we turn to the facts of this case.\\n\\n 9\\n\\f Since its inception, Constellis Group, Inc., the closely held parent company of a\\n\\ngroup of private security subsidiaries, has offered some form of deferred compensation to\\n\\nits employees, who are primarily retired members of the U.S. Armed Forces. Brundle I,\\n\\n241 F. Supp. 3d at 614. After initially offering a stock option program, Constellis\\n\\nreplaced that program with a profit-sharing plan in 2010. Id. In mid-2013, looking for an\\n\\n“exit strategy” after having twice tried and failed to effectuate a sale of the company, the\\n\\nowners of Constellis (hereinafter “the Sellers”) 3 began exploring the possibility of\\n\\ncreating an ESOP to purchase Constellis. Id. at 615.\\n\\n To that end, Constellis retained CSG International, an investment banking firm.\\n\\nCSG reported that sale of Constellis to an ESOP would not only enable the Sellers to\\n\\nliquidate their shares but would save them 23.8% in federal capital gains taxes. Id.\\n\\nAlthough noting that an ESOP would also benefit employees, CSG emphasized that\\n\\nselling Constellis to an ESOP provided the best option to optimize the Sellers’ after-tax\\n\\ncash return. See, e.g., id. at 616 (noting that CSG reported to the Sellers that, having\\n\\n“looked at every possible scenario,” it had not seen “any possible alternative that\\n\\nproduce[d] more after tax cash” than the proposed ESOP (internal quotation marks\\n\\nomitted)).\\n\\n CSG suggested that Constellis create what several trial witnesses characterized as\\n\\na “unique” ESOP structure to effectuate the sale. This unique structure would permit the\\n\\nSellers to retain de facto control of Constellis, even after the ESOP purchased all of the\\n\\n 3\\n Four individuals owned 77% of Constellis stock at the time of the sale at issue\\nhere. See Brundle I, 241 F. Supp. 3d at 615.\\n\\n 10\\n\\fcompany stock. Rather than sell 100% of their ownership interest to the ESOP, as is the\\n\\nusual practice, the Sellers would sell 90% of their shares to the ESOP and then exchange\\n\\nthe remaining 10% for “equity-like” warrants. These warrants would entitle the Sellers to\\n\\nbuy back equity in Constellis from the ESOP at a designated price and guarantee the\\n\\nSellers a majority on the board of directors. Id. at 626.\\n\\n To fund the ESOP’s purchase, Constellis would contribute 24% of the purchase\\n\\nprice and the ESOP would borrow the remainder from Constellis and the Sellers\\n\\nthemselves. Id. at 625. In late September 2013, Constellis decided to move forward with\\n\\nCSG’s proposal to create this unique ESOP. Id. To maximize the Sellers’ tax savings,\\n\\nConstellis had to complete the sale by the end of the calendar year. Id. at 622.\\n\\n On the recommendation of CSG, Constellis engaged Wilmington Trust, N.A., to\\n\\nserve as trustee for the ESOP. Id. at 616. In its role as trustee, Wilmington hired Stout\\n\\nRisius Ross (SRR) to be the financial advisor on the ESOP’s purchase of Constellis. Id.\\n\\nat 617. CSG, Wilmington, and SRR maintained significant long-term business\\n\\nrelationships, having worked together on more than twenty ESOP deals. Id. at 643\\n\\n(calling “the ESOP world . . . a very incestuous community”) (internal quotation marks\\n\\nomitted); id. at 617.\\n\\n On November 12, 2013, SRR submitted a draft valuation of Constellis stock to\\n\\nWilmington (the “SRR Report”). The SRR Report concluded that the fair market value\\n\\nfor a single share of Constellis stock lay between $3,865 and $4,600 — resulting in a\\n\\nrounded median price per share of $4,235. This placed the company’s worth, or its\\n\\n“enterprise value,” within a range of $275 to $330 million. Id. at 620–21. On November\\n\\n 11\\n\\f14, Wilmington met with analysts from SRR to discuss its report and valuation. At the\\n\\nmeeting’s conclusion, Wilmington set out to negotiate the ESOP’s purchase of Constellis\\n\\nwith authorization to offer a share price of $3,900 to $4,235. Id. at 622.\\n\\n The next day, Wilmington submitted an opening bid on behalf of the ESOP for\\n\\n$3,900 per share. Id. at 642. CSG, on behalf of Constellis, countered with $4,350 and\\n\\nsuggested to Wilmington that the ESOP and Constellis agree on a price first and then\\n\\nadjust the terms of the agreement at a later date. Wilmington agreed and raised its own\\n\\nbid to $4,100. CSG then countered with $4,250. By the end of the day, Wilmington and\\n\\nCSG had settled on a share price of $4,235 — the very top of Wilmington’s authorized\\n\\nnegotiation range. The negotiations lasted little more than five hours.\\n\\n The ESOP issued a tender offer for the shares on November 18 with a closing date\\n\\nof December 20. The parties finalized the term sheet on November 22. Between the\\n\\nconclusion of negotiations and the closing date for the transaction, SRR revised its\\n\\nvaluation of the draft enterprise range downward from $275–$330 million to $275–$325\\n\\nmillion, but the per share purchase price remained $4,235. On December 19, after\\n\\nmeeting with SRR for half an hour to discuss SRR’s valuation, Wilmington approved the\\n\\npurchase. Id. at 624. On December 20, the ESOP’s purchase of Constellis closed for a\\n\\nper share price of $4,235. Id. at 625.\\n\\n Subsequently, Tim P. Brundle, a former Constellis employee and ESOP\\n\\nparticipant, brought this action contending that Wilmington caused the ESOP to enter\\n\\n\\n\\n\\n 12\\n\\finto a transaction prohibited under ERISA § 1106. 4 Brundle alleged that the $4,235 per\\n\\nshare paid by the ESOP for Constellis was too high and resulted in the ESOP overpaying\\n\\nthe Sellers for the stock. The district court initially held that the 2013 purchase of\\n\\nConstellis by the ESOP constituted a prohibited transaction under § 1106(a)(1). Brundle\\n\\nv. Wilmington Tr., N.A., 2016 WL 6542718, at *12 (E.D. Va. Nov. 3, 2016). Wilmington\\n\\nconceded as much before the district court but raised the adequate-consideration\\n\\naffirmative defense available under § 1108(e)(1). Id.\\n\\n Following a bench trial, the district court issued meticulous factual findings and\\n\\nconcluded on the basis of those findings that Wilmington had not established the\\n\\n§ 1108(e) affirmative defense. Rather, the court found that Wilmington had violated its\\n\\nfiduciary duty to the ESOP. The district court concluded that Wilmington’s fiduciary\\n\\nfailures resulted in the ESOP overpaying for the Constellis stock by $29,773,250, and so\\n\\nawarded that amount to the ESOP as damages. Brundle I, 241 F. Supp. 3d at 613.\\n\\n Brundle then moved for attorneys’ fees. The court first ordered Wilmington to\\n\\npay attorneys’ fees pursuant to ERISA’s fee-shifting provision, 29 U.S.C. § 1132(g)(1),\\n\\nin the amount of $1,819,631.11. Brundle II, 258 F. Supp. 3d at 663–69. It subsequently\\n\\nawarded an additional $1.5 million in fees from the damages award.\\n\\n 4\\n Andrew Halldorson, another former Constellis employee and an ESOP\\nparticipant, filed the initial complaint against Wilmington. Halldorson later amended his\\ncomplaint to add Brundle as a named plaintiff. Both Halldorson and Brundle moved for\\nclass certification, which the district court denied. Following a motion for summary\\njudgment by Wilmington, the district court dismissed Halldorson because of a release he\\nsigned barring his suit against Wilmington. Halldorson appealed both his dismissal and\\nthe denial of class certification but later withdrew his appeal of the class certification\\nissue. Brundle did not timely appeal the denial of class certification.\\n\\n 13\\n\\f On appeal, Wilmington challenges the court’s liability and damages\\n\\ndeterminations and its award of $1.5 million in non-statutory attorneys’ fees. Brundle\\n\\ncross-appeals, challenging as inadequate the same portion of the attorneys’ fees award.\\n\\n\\n\\n II.\\n\\n Wilmington initially and principally contends that the district court erred in\\n\\nconcluding that it violated ERISA. Following a bench trial, we review a district court’s\\n\\nfactual findings for clear error and its legal conclusions de novo. Nat’l Fed’n of the Blind\\n\\nv. Lamone, 813 F.3d 494, 502 (4th Cir. 2016).\\n\\n At the outset of both its principal brief and its oral argument, Wilmington\\n\\nemphasized that there is no claim in this case that it acted in bad faith. But of course, an\\n\\nESOP participant seeking recovery from its fiduciary need not prove that the fiduciary\\n\\nacted in bad faith. Rather, an ESOP fiduciary is liable to the plan participants if it\\n\\nbreached its fiduciary duties, i.e., failed to act “solely in the interest of the participants,”\\n\\nwith the care, skill, prudence, and diligence used by a “prudent man acting in a like\\n\\ncapacity.” 29 U.S.C. § 1104(a) (emphasis added). Thus our focus is not on\\n\\nWilmington’s motives (good or bad) but on whether it acted “solely in the interest” of the\\n\\nplan participants, id., and “engaged in a reasoned decisionmaking process, consistent\\n\\nwith that of a prudent man in like capacity,” DiFelice v. U.S. Airways, Inc., 497 F.3d 410,\\n\\n420 (4th Cir. 2007) (internal quotation marks omitted); accord Tatum, 761 F.3d at 356.\\n\\nAs the Fifth Circuit has put it, “a pure heart and an empty head are not enough.”\\n\\nDonovan v. Cunningham, 716 F.2d 1455, 1467 (5th Cir. 1983).\\n\\n 14\\n\\f A.\\n\\n The district court found that because Wilmington failed to prove by a\\n\\npreponderance of the evidence that the ESOP’s purchase of Constellis was for adequate\\n\\nconsideration — and no more than adequate consideration — the transaction failed to\\n\\nqualify for the § 1108(e) affirmative defense. 5 In challenging this holding, Wilmington\\n\\nheavily relies on the valuation of Constellis stock submitted by its advisor, SRR.\\n\\n Expert advice, like an advisor’s independent valuation, can of course serve as\\n\\nevidence of prudence in the discharge of an ESOP trustee’s duties under § 1108(e). See\\n\\nBussian v. RJR Nabisco, Inc., 223 F.3d 286, 300–01 (5th Cir. 2000). But such advice “is\\n\\nnot a magic wand that fiduciaries may simply wave over a transaction to ensure that their\\n\\nresponsibilities are fulfilled.” Cunningham, 716 F.2d at 1474. Rather, a plan trustee\\n\\nmust at least show that it (1) “investigate[d] the expert’s qualifications,” (2) “provide[d]\\n\\nthe expert with complete and accurate information,” and (3) “[made] certain that reliance\\n\\non the expert’s advice was reasonably justified under the circumstances.” Shay, 100 F.3d\\n\\nat 1489. Because ERISA demands a high level of scrutiny from fiduciaries, a trustee\\n\\nmust prove that it considered these factors “and any others relevant under the particular\\n\\n\\n 5\\n For this defense to apply, in addition to being for adequate consideration, (1) the\\nsale or exchange must be of “qualifying employer securities,” (2) the trustee cannot\\ncharge a commission, and (3) the plan must qualify as “an eligible individual account\\nplan.” 29 U.S.C. § 1108(e).\\n All parties agree that the transaction here was for “qualifying employer securities.”\\nThey further agree that Wilmington did not charge a commission, and they do not dispute\\nthe district court’s finding that Wilmington’s fees were reasonable. See Brundle I, 241 F.\\nSupp. 3d at 617. The parties do contest, however, whether the ESOP qualifies as an\\n“eligible plan.” The district court did not reach this issue, nor do we.\\n\\n 15\\n\\fcircumstances it faced at the time of the decision,” and took care to avoid any identified\\n\\nconflicts of interest. See Bruister, 823 F.3d at 263 (internal quotation marks omitted).\\n\\n The district court properly recognized that the above legal principles guided its\\n\\ninquiry. The court then issued extensive factual findings in support of its conclusion that\\n\\nWilmington had “not demonstrated that its reliance on SRR’s [valuation] report was\\n\\n‘reasonably justified’ in light of all the circumstances because [Wilmington] ha[d] not\\n\\nshown that it thoroughly probed the gaps and internal inconsistencies in that report.”\\n\\nBrundle I, 241 F. Supp. 3d at 634.\\n\\n The court found Wilmington’s decision-making process inadequate in four major\\n\\nrespects. Id. It explained that “[a]lthough these failings independently” might not be\\n\\ndispositive, cumulatively they demonstrated that “Wilmington failed to meet its duty”\\n\\nunder ERISA, id., which, of course, includes the obligation to act “solely in the interest”\\n\\nof plan participants, 29 U.S.C. § 1104(a). Wilmington challenges the district court’s\\n\\nexhaustive findings of fact and conclusions of law as to each of the four designated\\n\\nfailures.\\n\\n 1.\\n\\n First, Wilmington maintains the district court erred in finding fault with\\n\\nWilmington’s failure to investigate SRR’s omission from its report of another, much\\n\\nlower, valuation of Constellis stock. That valuation, termed the “McLean Report” by the\\n\\nparties, had been completed just months earlier by the McLean Group, an investment\\n\\nbank that had regularly provided annual share valuations for Constellis. Brundle I, 241 F.\\n\\nSupp. 3d at 619, 634–35.\\n\\n 16\\n\\f Wilmington’s trial witnesses contended that consideration of the McLean Report\\n\\n“would not have been helpful because it was prepared with a different purpose in mind\\n\\n— the valuation of a single share” for stock options, rather than the valuation of a\\n\\ncontrolling interest for sale. Id. at 634–35. But the district court, relying on the\\n\\nuncontradicted testimony of a “highly credible” neutral expert, found that the two reports\\n\\nused “essentially the same methodology” despite being prepared for different purposes.\\n\\nId. at 635. Using that same methodology, the 2013 McLean Report estimated the per\\n\\nshare value of Constellis stock as $1,838.11, while SRR estimated its median per share\\n\\nvalue as $4,235. Id. at 619.\\n\\n Yet the SRR Report, which guided Wilmington as it evaluated the ESOP\\n\\ntransaction, did not even mention the McLean Report. And, although trial testimony\\n\\nestablished that at least one Wilmington official knew of the McLean Report, no one\\n\\nfrom Wilmington ever asked about it or questioned the vast discrepancy between two\\n\\nvaluations of the same company performed mere months apart. Id. at 634–35. The\\n\\ndistrict court concluded that a prudent fiduciary in Wilmington’s position would have\\n\\ninquired as to SRR’s omission. This was particularly so given that Constellis officers\\n\\ntestified that the company’s business prospects had not dramatically changed in the\\n\\nperiod between the two reports, and the SRR Report had referenced a different\\n\\n“valuation” older than McLean’s. 6\\n\\n\\n 6\\n Specifically, the SRR Report noted that in 2012 — a year before the McLean\\nReport’s publication — a private equity firm offered to buy Constellis for between $340\\nand $350 million. But rather than explain that the private equity firm then lowered its\\n(Continued)\\n 17\\n\\f Relying on trial evidence, the district court concluded that even a cursory review\\n\\nof the McLean Report would have raised questions as to whether the share valuation in\\n\\nthe SRR Report was too optimistic. The court did not find that the McLean Report\\n\\nnecessarily offered a more accurate picture of Constellis’s true value, but simply that a\\n\\nreasonably prudent fiduciary would have asked more questions. The court found that the\\n\\nanswers to these questions were “precisely the kinds of information that Wilmington, as\\n\\ntrustee, should have sought and evaluated” when considering the valuation of Constellis\\n\\nstock. Id. at 636. We see no reason to conclude otherwise.\\n\\n 2.\\n\\n The second major fault identified by the district court concerned Wilmington’s\\n\\nfailure to adequately probe the reliability of financial projections prepared by Constellis\\n\\nmanagement and used by SRR. Id. at 636–38. The court found that “the record show[ed]\\n\\nthat there were several red flags indicating that these projections were inflated, which\\n\\nWilmington either ignored or downplayed.” Id. at 636. Wilmington offers both general\\n\\nand specific challenges to this finding.\\n\\n First, Wilmington argues that Constellis management’s financial projections were,\\n\\nin fact, reliable and so required no probing. In support of this view, Wilmington contends\\n\\nthat because the McLean Report also utilized management’s financial projections to\\n\\n\\n\\n\\noffer to $275 million, see Brundle I, 241 F. Supp. 3d at 614–15, the report simply stated\\nthat the deal fell through due to the buyer’s “inability to secure sufficient financing.”\\n\\n 18\\n\\farrive at its own valuation of Constellis — a valuation the court treated as relevant — the\\n\\ncourt should have found the projections that the SRR Report used were also reliable.\\n\\n But although both McLean and SRR relied on financial projections prepared by\\n\\nConstellis management, they did not rely on the same financial projections. Id. at 638.\\n\\nThe projections that Constellis provided to SRR forecasted revenue over a much longer\\n\\ntime period, id. at 637–38, making them less accurate and less reliable. Further,\\n\\nConstellis management specifically prepared this set of projections for the purposes of\\n\\nSRR’s valuation in connection with the ESOP sale. This created a risk that Constellis\\n\\nmanagement might inflate its projections in response to incentives unique to the ESOP\\n\\nsale. Id. at 636. In light of these distinctions, the district court’s differing assessments of\\n\\nthe two reports’ comparative reliability were not inherently contradictory.\\n\\n At a more granular level, Wilmington maintains that each of the red flags that the\\n\\ndistrict court identified in Constellis’s financial projections are “non-existent.”\\n\\nWilmington Opening Br. 33–34, 38–39. Wilmington asserts largely factual, and\\n\\nuniversally unpersuasive, arguments in support of this view.\\n\\n Wilmington challenges the district court’s conclusion that Wilmington should\\n\\nhave been more critical of Constellis management’s financial projections because\\n\\nmanagement had a financial incentive to inflate the purchase price. The court found that\\n\\nthis initial red flag should have alerted Wilmington to probe the SRR valuation of\\n\\nConstellis. The district court’s finding on this issue primarily rested on the prospect of\\n\\nmanagement receiving 5% of the purchase price in cash bonuses — a factual\\n\\ndetermination well supported by the record. See Brundle I, 241 F. Supp. 3d at 636.\\n\\n 19\\n\\f The district court also identified as a red flag an ongoing government investigation\\n\\ninto accounting and record-keeping errors by Constellis, which the court concluded\\n\\n“should have raised questions about the reliability of Constellis’[s] . . . projections.” Id.\\n\\nAgain, contrary to Wilmington’s suggestion, we see no basis for holding this finding\\n\\nclearly erroneous. A government investigation into errors of this nature surely creates a\\n\\nquestion as to the reliability of a company’s financial projections, which a reasonably\\n\\nprudent fiduciary representing the buyers of the company should probe further. Cf.\\n\\nKeach v. U.S. Tr. Co., 419 F.3d 626, 633–37 (7th Cir. 2005) (finding ESOP trustee met\\n\\nfiduciary duty when it “analyzed exhaustively [the company’s] financials, had conducted\\n\\nindependent valuation analyses and had challenged the financial forecasts made by [the\\n\\ncompany’s] management as too optimistic”).\\n\\n Still another red flag to which Wilmington, in the district court’s view, did “not\\n\\nadequately respond was the riskiness of Constellis’[s] contract concentration.” Brundle I,\\n\\n241 F. Supp. 3d at 637. The district court believed that this risk called for Wilmington to\\n\\napply further scrutiny to the company’s financial projections. The court found, and\\n\\nWilmington does not dispute, that at the time of the ESOP sale, about 70% of Constellis’s\\n\\nrevenue depended on just two government contracts. Id. at 637. Yet Wilmington\\n\\nadopted a valuation that assumed Constellis stock posed significantly less risk than the\\n\\nstock market as a whole. Again relying on the trial testimony of a “neutral” and “highly\\n\\ncredible” third party expert, the court explained its conclusion that Constellis’s industry\\n\\npeers — namely, government contractors — are certainly “no less risky than the market\\n\\nas a whole.” Brundle II, 258 F. Supp. 3d at 663. And again, the record offers ample\\n\\n 20\\n\\fsupport for this finding. See Brundle I, 241 F. Supp. 3d at 637; Brundle II, 258 F. Supp.\\n\\n3d at 662–63. 7\\n\\n Wilmington also maintains that the district court unfairly characterized\\n\\nConstellis’s “multiple sets of projections” as a red flag. Wilmington claims that the\\n\\ndistrict court ignored the fact that SRR advised Wilmington that the market and\\n\\nConstellis had changed throughout 2013. But the court adequately addressed this\\n\\nargument, see Brundle I, 241 F. Supp. 3d at 635–36, and we defer to its factual finding\\n\\nthat the changes in the market and Constellis’s business prospects throughout 2013 did\\n\\nnot justify multiple sets of projections.\\n\\n Last, Wilmington contends that we should reverse the district court due to its\\n\\ninitially erroneous understanding of the warranties Wilmington obtained to indemnify the\\n\\nESOP against the ongoing government investigation. At first, the court incorrectly found\\n\\n 7\\n The court acknowledged that it originally had misunderstood the definition of the\\nrisk factor, called “beta,” that SRR used in its report. SRR chose a beta of 0.7, indicating\\nthat Constellis stock was less risky than the average stock (set at a beta of 1.0). The court\\nhad understood beta to measure the risk of Constellis stock relative to its industry peers,\\nbut beta actually measures the risk of a company’s stock — or in the case of a privately\\nheld company like Constellis, the risk of a company’s publicly traded industry peers —\\nrelative to the stock market as a whole. Brundle II, 258 F. Supp. 3d at 658.\\n Upon consideration of Wilmington’s Rule 59 motion, the court stood by its\\noriginal conclusion that Wilmington had inappropriately chosen a beta indicating that\\nConstellis was less risky than other stocks. The court concluded that a neutral beta of 1.0\\nwas more appropriate, noting that “[e]ven if government contracting business [in which\\nConstellis participates] does not fluctuate in correlation with the market, that does not\\nmean that government contracting is necessarily more stable.” Id. at 663. The court\\nnoted that a Wilmington trial witness had acknowledged that “the government contracting\\nindustry” is at times “less stable than the market as a whole.” Id. The court further relied\\non the “most credible” neutral expert’s testimony that the public companies used by SRR\\nto measure beta were “not a good match for Constellis.” Id. We see no clear error in\\nthese findings.\\n\\n 21\\n\\fthat only Constellis had indemnified the ESOP, thus creating an illusory form of\\n\\nindemnification. But in denying Wilmington’s Rule 59 motion, the court candidly\\n\\naddressed that error and acknowledged that, in fact, both Constellis and the Sellers had\\n\\nindemnified the ESOP. Brundle II, 258 F. Supp. 3d at 656. Nonetheless, the court found\\n\\nthat its “corrected understanding [did] not alter [its] conclusions about . . . Wilmington’s\\n\\ninadequate investigation into the soundness of Constellis’[s] financial projections.” Id.\\n\\nThe court explained that, “[e]ven omitting its erroneous view of the Sellers’ . . .\\n\\nwarranties,” Wilmington failed to rebut the many red flags discussed above, each of\\n\\nwhich independently called for more robust due diligence by Wilmington. Id. at 656–57.\\n\\nFor the reasons we have explained above, we find no clear error in any of these findings\\n\\nand so reject this final argument from Wilmington as to Constellis management’s\\n\\nfinancial projections.\\n\\n 3.\\n\\n The district court found that Wilmington’s third major failure in ensuring that its\\n\\nreliance on the SRR valuation was reasonably justified occurred when it “did not\\n\\ninvestigate the appropriateness of applying a 10% control premium” to Constellis stock\\n\\nand “fail[ed] to discount the [valuation] for lack of control.” Brundle I, 241 F. Supp. 3d\\n\\nat 638.\\n\\n Purchasers will generally pay more for “rights associated with control of the\\n\\nenterprise.” Estate of Godley v. Comm’r, 286 F.3d 210, 214 (4th Cir. 2002). We have\\n\\ndefined “control” as “an interest which allows the shareholder to unilaterally direct\\n\\ncorporate action, select management, decide the amount of distribution, rearrange the\\n\\n 22\\n\\fcorporation’s capital structure, and decide whether to liquidate, merge, or sell assets.” Id.\\n\\nat 215 (internal quotation marks omitted).\\n\\n The district court recognized that the ESOP had “powers beyond those of an\\n\\nordinary shareholder.” Brundle I, 241 F. Supp. 3d at 627 n.23. But the court nonetheless\\n\\nfound that the “ESOP essentially had no power to control Constellis” as a result of the\\n\\ntransaction’s unique structure. Id. at 638–39. Accordingly, the court concluded that\\n\\nWilmington erred in failing to investigate the SRR valuation, which not only failed to\\n\\ndiscount the stock for lack of control, but even added a 10% control premium to the value\\n\\nof the Constellis stock. The record supports both findings.\\n\\n The Sellers retained the power to appoint a majority of the Constellis board, a key\\n\\nindicator of control. See id. at 626. Further, the ESOP governing plan document and the\\n\\nESOP trust agreement each required Wilmington to vote its shares as the Constellis\\n\\nboard (not the ESOP) directed. See id. at 626–27. Wilmington maintains that the ESOP\\n\\ncould independently exercise its voting powers because the plan documents included a\\n\\nclause nullifying any provision that violated ERISA. But Constellis’s general counsel\\n\\ntestified at trial that the ESOP could only contravene the plan documents and exercise its\\n\\nindependent voting authority by filing a lawsuit — the same limited relief available to a\\n\\nminority shareholder. The district court thus concluded that Wilmington breached its\\n\\nfiduciary obligation in failing to question SRR’s failure to discount for lack of control.\\n\\nSee id. at 639. Given the record evidence that the ESOP’s unique ownership structure\\n\\nwas intentionally designed to maintain the Sellers’ control over Constellis even after\\n\\nselling their shares, the district court’s conclusion hardly constitutes clear error.\\n\\n 23\\n\\f Wilmington next contends that even if the ESOP lacked control, a 10% control\\n\\npremium was justified by the fact that the ESOP owned 100% of Constellis shares and\\n\\nobtained “elements of control.” Id. at 647. Wilmington argues that SRR reasonably\\n\\napplied a “modest” 10% control premium given that market control premiums are often\\n\\nbetween 35–40%. But in light of the limited rights provided to the ESOP, we cannot\\n\\nconclude that the district court erred in finding that Wilmington should have done more\\n\\nto challenge the use of any control premium. The SRR Report “devoted just one sentence\\n\\nto articulating its decision,” yet Wilmington never asked SRR about its decision to apply\\n\\na control premium. Id. at 639. For an assumption that carried such weighty\\n\\nconsequences, we cannot say that the district court clearly erred in finding that a\\n\\nreasonably prudent fiduciary would have probed the issue further.\\n\\n 4.\\n\\n The final major fault that the district court identified in Wilmington’s reliance on\\n\\nthe SRR Report was Wilmington’s failure to probe why SRR consistently rounded the\\n\\nvaluation of Constellis stock upwards. This repeatedly increased the price the ESOP had\\n\\nto pay for the stock. The district court concluded that because an ESOP fiduciary should\\n\\nbe concerned with achieving the lowest possible price for the ESOP, Wilmington ought\\n\\nto have asked why SRR consistently engaged in the upward rounding to the ESOP’s\\n\\ndetriment. Id. at 639–40.\\n\\n Wilmington devotes only a short footnote in its opening brief to this issue and fails\\n\\nto address it at all in its reply brief. It thus appears to have forfeited an appellate\\n\\nchallenge to the court’s findings on this issue. See Wahi v. Charleston Area Med. Ctr.,\\n\\n 24\\n\\fInc., 562 F.3d 599, 607 (4th Cir. 2009) (finding argument raised only in a footnote in\\n\\nappellant’s opening brief forfeited on appeal). Perhaps this is because the district court’s\\n\\nfinding is self-evidently correct. And, as the district court noted, Brundle I, 241 F. Supp.\\n\\n3d at 640, this conclusion accords with those of other courts. For example, the Sixth\\n\\nCircuit described a similar rounding practice as “extremely disconcerting” and noted that\\n\\nthis conduct, although not dispositive, was illustrative of lackluster due diligence\\n\\ndisplayed throughout the transaction process. Chao, 285 F.3d at 433–34. So too here.\\n\\n B.\\n\\n Apart from Wilmington’s four major failures to scrutinize SRR’s report, the\\n\\ndistrict court also found that Wilmington’s conduct throughout the transaction provided\\n\\nfurther evidence that Wilmington failed to act as a prudent fiduciary solely on behalf of\\n\\nthe ESOP participants. Although the court found that Wilmington’s actions on behalf of\\n\\nthe ESOP did not amount to bad faith, it recognized that “ERISA demand[ed] more to\\n\\nexcuse a fiduciary from liability.” Brundle I, 241 F. Supp. 3d at 643.\\n\\n The district court found that Constellis’s principal motivation for creating the\\n\\nESOP was to further the Sellers’ interests, not the interests of the ESOP participant\\n\\nbuyers. Id. at 616. The sale of Constellis to the ESOP enabled the Sellers to cash out\\n\\ntheir company stock, which they had tried and failed to accomplish several times, and to\\n\\nreap substantial tax savings. Moreover, the ESOP’s unique structure enabled the Sellers\\n\\nto avoid the downside risk of holding equity, yet profit from any upside, while also\\n\\nretaining control over the company. The court found that Wilmington, in its role as the\\n\\n\\n\\n 25\\n\\fESOP’s fiduciary, simply ignored these motivations rather than investigating whether\\n\\nthey affected the ESOP’s legality under ERISA. Id. at 640–42.\\n\\n The district court additionally found that making the Sellers’ interests paramount\\n\\nshortened the transaction timeline and rushed Wilmington’s due diligence process and\\n\\nprice and terms negotiations. To maximize the after-tax benefits to the Sellers, the ESOP\\n\\nsale had to conclude before the end of 2013. Accordingly, Wilmington and its agents\\n\\ncompleted their due diligence, made pricing decisions, conducted negotiations, and\\n\\nlaunched a tender offer in less than two months. Id. at 621–25. Wilmington employees\\n\\nmet to discuss the transaction only three times and met with Constellis management just\\n\\nonce. Id. at 642. All meetings lasted less than 90 minutes and several of Wilmington’s\\n\\nteam members were absent from each. Id. And the district court found that Wilmington\\n\\nviolated its own policy by repeatedly taking less than 48 hours between receiving a\\n\\nvaluation report and meeting to discuss it. Id. at 621, 625. The court concluded that this\\n\\ntype of conduct fell well short of the diligence expected of a prudent fiduciary. Id. at\\n\\n643.\\n\\n Finally, the court noted that “Wilmington’s lack of engagement and willingness to\\n\\nnegotiate so favorably with CSG may have been motivated by its significant business\\n\\nrelationship with CSG.” Id. The district court found that Wilmington, CSG, and SRR\\n\\nmaintained extensive and lucrative business relationships and that SRR was willing to\\n\\ndiscuss its valuation strategies with CSG while negotiations were ongoing. Id. The\\n\\nrecord offers ample support for all of these findings.\\n\\n\\n\\n 26\\n\\f C.\\n\\n Wilmington also maintains that the district court erred in finding that the value of\\n\\nStock Appreciation Rights (SARs) issued in connection with the ESOP’s purchase of\\n\\nConstellis should have been deducted from Constellis’s equity value for purposes of\\n\\nSRR’s valuation. SARs are incentives that Constellis would have owed to management\\n\\nhad the company’s value reached a certain price by a particular date. Wilmington argues\\n\\nthe value of the SARs should not have been deducted from Constellis’s estimated value\\n\\nbecause they were inchoate at the time of the sale. The district court disagreed and found\\n\\nthat, because Constellis intended for the SARs to be issued, their value should have been\\n\\ndeducted from Constellis’s equity value. Id. at 648.\\n\\n Wilmington rehashes the same argument on appeal but fails to identify any\\n\\nevidence that demonstrates the district court clearly erred in this factual determination.\\n\\nBecause we discern no such evidence, we reject this claim.\\n\\n D.\\n\\n In support of its final attack on the district court’s liability findings, Wilmington\\n\\nrelies on the ESOP’s subsequent sale of Constellis stock to ACADEMI LLC.\\n\\n In early February 2014, less than two months after the ESOP transaction,\\n\\nACADEMI, a major competitor in the private security market, began talks with\\n\\nConstellis management to acquire the company. Id. at 628. Initially, ACADEMI offered\\n\\nto purchase Constellis at an enterprise value of $283.3 million, in a transaction that would\\n\\nresult in $10 million in cash going to the ESOP. Seeking a better offer on the ESOP’s\\n\\nbehalf, Wilmington entered into negotiations with Constellis, the Sellers, and\\n\\n 27\\n\\fACADEMI. Id. at 629. Wilmington’s efforts proved successful: the final transaction,\\n\\nwhich closed on July 25, 2014, effectuated a sale of all the Constellis stock to ACADEMI\\n\\nat an implied enterprise value of $288.3 million. Id. at 631. The final transaction paid\\n\\n$20 million in cash to the ESOP — double the initial $10 million offer — as a result of\\n\\nthe Sellers’ agreeing to write off $33 million of the ESOP’s debt. Id. at 629.\\n\\n Wilmington argues that the ACADEMI sale proves that the ESOP did not overpay\\n\\nfor Constellis seven months earlier. Relying on the first prong of DOL’s proposed\\n\\nadequate-consideration regulations, Wilmington maintains that the ESOP paid “fair\\n\\nmarket value” for the Constellis stock because ACADEMI’s purchase of Constellis stock\\n\\nimplied an enterprise value of $288.3 million, which was within SRR’s estimated range\\n\\nof $275 to $330 million. Wilmington contends this purchase price is of particular\\n\\nsignificance because in the intervening time Constellis assertedly suffered several\\n\\nbusiness setbacks that decreased its enterprise value. 8\\n\\n This argument is unpersuasive for several reasons. The proposed DOL regulations\\n\\nupon which Wilmington relies provide that a trustee can prove consideration is\\n\\n“adequate” if it reflects the stock’s “fair market value” and is “the product of a\\n\\ndetermination made by the fiduciary in good faith.” Proposed Regulation Relating to the\\n\\n\\n 8\\n The district court carefully considered and described these setbacks in detail. See\\nBrundle I, 241 F. Supp. 3d at 627–28. Briefly, the State Department made a formal\\ndemand for payment of $62.2 million as part of its audit of Constellis’s accounting and\\nrecord-keeping practices; Constellis was forced to reduce projected revenue from a\\ncontract in Iraq by more than $100 million and push the remaining revenue further into\\nthe future; its projected revenue from a contract in Kuwait decreased by tens of millions\\nof dollars; and it lost a $338 million contract in Germany it had expected to win. Id.\\n\\n 28\\n\\fDefinition of Adequate Consideration, 53 Fed. Reg. at 17,633. Of course, because the\\n\\nDOL never enacted the proposed regulations, they are not binding. And, as we have\\n\\nexplained, courts look to the conduct of the trustee and whether it met its fiduciary\\n\\nobligations, not to whether the trustee arrived at a “fair” value. But even if we were to\\n\\nadopt the DOL’s proposed regulations, a trustee must satisfy both parts of the test to\\n\\nbenefit from the adequate consideration exception. See id. Assuming arguendo that the\\n\\npurchase was for “fair market value,” we find no error in the district court’s findings that\\n\\nWilmington failed to prove that the share price was also “the product of a determination\\n\\nmade by the fiduciary in good faith.”\\n\\n Furthermore, even if proving the ESOP paid “fair market value” sufficed to meet\\n\\nthe requirements of § 1108(e), the facts of the ACADEMI sale do not prove that the\\n\\nESOP paid only “fair market value” here. In fact, the district court found that the\\n\\nopposite was true. The court found that because ACADEMI, a private security company\\n\\nlike Constellis, would benefit from synergies resulting from its purchase of Constellis, it\\n\\nwould have been willing to pay significantly more for Constellis than the ESOP. Thus,\\n\\nthat ACADEMI actually paid less for Constellis stock suggested a significantly lower fair\\n\\nmarket value for the stock at the time of the ESOP purchase. Of course, Wilmington’s\\n\\nexperts disagreed with this synergies analysis, but the district court found the testimony\\n\\nof other experts on this point more persuasive. Brundle I, 241 F. Supp. 3d at 640. The\\n\\nrecord provides no basis to reject this finding. See Hendricks v. Cent. Reserve Life Ins.\\n\\nCo., 39 F.3d 507, 513 (4th Cir. 1994) (“An appellate court should be especially reluctant\\n\\n\\n\\n 29\\n\\fto set aside a finding based on the trial court’s evaluation of conflicting expert\\n\\ntestimony.”).\\n\\n In sum, the district court found that the ACADEMI sale did not constitute a\\n\\nmeaningful comparator. Discounting the additional synergy value, the $33 million debt\\n\\nwrite-off by the Sellers, and an expected tax refund from the sale, the court found the\\n\\nACADEMI purchase suggested that Constellis’s fair market value was closer to $200\\n\\nmillion — almost $100 million less than the enterprise value implied by the ESOP\\n\\ntransaction. Thus, the court found, the ACADEMI sale could not support Wilmington’s\\n\\nargument that the ESOP paid no more than adequate consideration for Constellis.\\n\\nBrundle I, 241 F. Supp. 3d at 640. We see no clear error in this conclusion.\\n\\n Additionally, we note that, despite paying more for Constellis stock, the ESOP did\\n\\nnot obtain nearly the level of control that ACADEMI acquired. While the ESOP\\n\\nobtained only some elements of control, ACADEMI acquired absolute and uncontested\\n\\ncontrol. Had the district court applied the “standard” 35–40% control premium\\n\\nWilmington’s experts suggested was reasonable, Constellis’s fair market value would fall\\n\\nsomewhere between $145 million and $150 million, almost half the value of the stock\\n\\npurchased by the ESOP only months earlier.\\n\\n\\n\\n III.\\n\\n Having rejected all of Wilmington’s challenges to the district court’s findings as to\\n\\nits liability, we turn to the court’s damages award. The district court concluded that\\n\\nWilmington’s fiduciary failures inflated the price the ESOP paid for Constellis stock by\\n\\n 30\\n\\f$29,773,250. “We review factual findings relating to the calculation of damages for clear\\n\\nerror.” Simms v. United States, 839 F.3d 364, 368 (4th Cir. 2016).\\n\\n A.\\n\\n To calculate the loss to an ESOP and compensate it for a fiduciary’s ERISA\\n\\nviolation, a court typically subtracts the stock’s fair market value, as determined by the\\n\\ncourt, from the inflated price paid by the ESOP. See Bruister, 823 F.3d at 265 (collecting\\n\\ncases). The district court precisely followed this approach. The court used as a baseline\\n\\nthe comprehensive damages estimate provided by Brundle’s expert — the only expert to\\n\\noffer one. 9 The court then considered the flaws in this valuation raised by Wilmington\\n\\nand made “appropriate adjustments based on the evidence adduced at trial and the\\n\\nrelative credibility of the experts.” Brundle I, 241 F. Supp. 3d at 645.\\n\\n Brundle’s expert estimated Wilmington’s lack of due diligence had caused the\\n\\nESOP to overpay for the Constellis stock by almost $103,862,000. But the district court\\n\\ndid not accept this figure. Instead, it independently analyzed each of Wilmington’s\\n\\npurported failings, considered the relevant trial testimony, and then awarded $29,773,250\\n\\n— or less than a third of the expert’s estimation — as damages. Id. at 645–49. The\\n\\nfollowing chart summarizes the district court’s damages findings:\\n\\n Error Difference between fair market value and\\n inflated price paid by ESOP (Damages)\\n Reliance on Management’s $4,325,000\\n Growth Projections\\n Use of .07 Beta $2,936,000\\n\\n 9\\n The Fifth Circuit held, in another ESOP case involving this same expert, that a\\ntrial court “was entitled to credit” his valuation methodology. Bruister, 823 F.3d at 267.\\n\\n 31\\n\\f Inclusion of Control Premium $8,186,000\\n Failure to Include Lack of $9,715,250\\n Control Discount\\n Stock Appreciation Rights $1,611,000\\n Rounding $3,000,000\\n Total Damages $29,773,250\\n\\n Wilmington did not provide the district court with an alternative damages\\n\\ncalculation or offer any evidence that the court could use to devise its own. At oral\\n\\nargument before us, Wilmington conceded as much. Accordingly, it has forfeited its\\n\\nchallenge to the methodology used by the district court when calculating the damages\\n\\naward. See Exxon Shipping Co. v. Baker, 554 U.S. 471, 487 n.6 (2008) (“[W]aiver and\\n\\nforfeiture rules . . . ensure that parties can determine when an issue is out of the case, and\\n\\nthat litigation remains, to the extent possible, an orderly progression.”).\\n\\n Moreover, Wilmington’s principal basis for urging reversal of the damages award\\n\\nconsists of a repetition of its challenge to the district court’s liability findings. Given our\\n\\naffirmance of all the district court’s liability findings — that Wilmington failed to\\n\\nadequately investigate and probe SRR as to the omission of the McLean Report, the use\\n\\nof Constellis management’s growth projections, the 0.7 beta, the 10% control premium,\\n\\nimproper rounding up, and SARs — that challenge fails.\\n\\n B.\\n\\n Wilmington additionally contends that the district court erred in declining to offset\\n\\nits damages calculation by the $20 million in cash that the ESOP received as a result of\\n\\nthe ACADEMI sale. According to Wilmington, “the district court’s failure to” do so\\n\\n“resulted in a clear windfall for the ESOP.” Wilmington Opening Br. at 53. As the\\n\\n 32\\n\\fdistrict court ably explained, see Brundle II, 258 F. Supp. 3d at 660–62, this claim is\\n\\nmeritless.\\n\\n ERISA expressly requires a fiduciary to “make good to [an ESOP] any losses”\\n\\nresulting from a given breach of duty. 29 U.S.C. § 1109(a); cf. Restatement (Second) of\\n\\nTrusts § 205 cmt. e (“If the trustee is authorized to purchase property for the trust, but in\\n\\nbreach of trust he pays more than he should pay, he is chargeable with the amount he paid\\n\\nin excess of its value.”). Thus, in cases involving overpayment for ESOP assets, courts\\n\\ngenerally compute restitution damages exactly as the district court did here: by deducting\\n\\nthe fair market value of the stock from the amount the ESOP actually paid.\\n\\n Wilmington insists that the ESOP’s subsequent and unrelated sale of the stock to\\n\\nACADEMI requires a different result. This misapprehends the nature of the breach. If\\n\\nWilmington had breached its duty by purchasing Constellis stock at all, then a damages\\n\\naward consisting of the purchase payments offset by any subsequent profits would indeed\\n\\nreturn the participants to the pre-purchase status quo.\\n\\n But Wilmington breached here by overpaying for the Constellis stock. Principles\\n\\nof restitution therefore entitle the ESOP and its participants to compensation for the loss\\n\\nfrom the overpayment. Any subsequent gains involving the stock, which the ESOP\\n\\nwould have obtained regardless of the overpayment, have no bearing on that loss. For\\n\\nthis very reason, courts have uniformly rejected analogous offsets to damage awards in\\n\\noverpayment cases. See, e.g., Bruister, 823 F.3d at 270–71 (rejecting offset to account\\n\\nfor unpaid or forgiven ESOP debt and noting that “[e]very court to consider this\\n\\nquestion” agreed); Henry v. U.S. Trust Co. of Cal., N.A., 569 F.3d 96, 98–100 (2d Cir.\\n\\n 33\\n\\f2009) (“Henry V”) (“If an investor pays $100 for 20 shares of stock and later sells those\\n\\nshares back to the original seller for $25, the result is not that the investor paid only $75\\n\\nfor the shares.”).\\n\\n Even so, Wilmington asserts that the events in this case resulted in “pure gain” to\\n\\nthe ESOP, justifying a deviation from this rule. It claims the ESOP “made $20 million\\n\\nfor the nominal cost of carrying $200 million in non-recourse debt for a few months,”\\n\\nbecause “[j]ust seven months” after the prohibited transaction, “the ESOP exchanged its\\n\\ndebt-burdened shares to ACADEMI for $20 million in cash.” Wilmington Opening Br.\\n\\nat 55–56. We disagree. As a preliminary matter, the burden imposed in additional debt\\n\\nfrom a $30 million overpayment is far from “nominal,” even for “just” seven months.\\n\\nSee Henry V, 569 F.3d at 99 n.4 (explaining “the obvious fact that the assumption of\\n\\nindebtedness has immediate legal and economic consequences even before the borrower\\n\\nbegins to repay the debt”).\\n\\n Moreover, if Wilmington seeks to portray the ACADEMI sale as an “exchange” in\\n\\nwhich the ESOP’s pre-sale debt had no effect on its post-sale assets, this is both illogical\\n\\nand untrue. Had the ESOP not initially overpaid for the stock by $30 million, it would\\n\\nhave shouldered tens of millions of dollars less in debt; in turn, it would presumably have\\n\\nbeen tens of millions of dollars better off after being compensated for the stock in the\\n\\nACADEMI sale. Put differently, although the ESOP benefited despite the breach, it\\n\\nwould have benefited at least as much — but ended in a far better position — without the\\n\\nbreach. In fact, had the ESOP initially paid a fair (lower) value for the Constellis stock\\n\\n\\n\\n 34\\n\\fand therefore carried less debt, it would have entered the ACADEMI negotiations in a\\n\\nstronger bargaining position and may have profited further still.\\n\\n Wilmington rejects this conclusion, stressing that the Sellers also agreed to write\\n\\noff more than $30 million of the ESOP’s debt, which it describes as an “effective[]\\n\\nreduc[tion]” of the 2013 purchase price. Wilmington Opening Br. at 56. But once again,\\n\\nthis independent act has no bearing on the ESOP’s loss.\\n\\n Wilmington unpersuasively contends that Henry III supports its argument. That\\n\\ncase addressed very different facts. There, the Second Circuit held that — where sellers\\n\\nfully and voluntarily repaid an ESOP after the IRS found overpayment, but before a court\\n\\nentered a damages judgment — a duplicative recovery for the same overpayment might\\n\\n“result in a windfall.” Henry III, 445 F.3d at 624. Wilmington does not even argue that\\n\\nthe Sellers’ write-off here was meant to remedy the ESOP’s overpayment. Nor could it:\\n\\nunlike the midstream repayment in Henry, the write-off here occurred more than a year\\n\\nprior to the initiation of any legal proceedings alleging Wilmington breached its fiduciary\\n\\nduties. As Wilmington concedes, the write-off was part of a negotiated agreement to\\n\\nclose the ACADEMI sale, a deal wholly unrelated to the issues raised here. Again, it is\\n\\nreasonable to assume that the ESOP would have negotiated equally favorable (if not more\\n\\nfavorable) terms had it paid a fair value in the first instance and thus entered the\\n\\nACADEMI discussions with substantially less debt.\\n\\n In sum, we find no error in the district court’s damages award.\\n\\n\\n\\n\\n 35\\n\\f IV.\\n\\n Finally, we examine the district court’s award of attorneys’ fees. The court\\n\\nawarded Brundle’s counsel $1,819,631.11 in statutory fees and an additional $1.5 million\\n\\nin fees from the ESOP’s damages judgment. No party has presented a substantive\\n\\nchallenge regarding the award of attorneys’ fees under the fee shifting statute. 10 Brundle\\n\\nchallenges the $1.5 million in additional fees (payable from the damages awarded to the\\n\\nESOP) as too small; Wilmington and Constellis, as fiduciaries for the ESOP, challenge\\n\\nthe award as legally improper. We review that award for abuse of discretion, mindful\\n\\nthat our review “is sharply circumscribed, and a fee award must not be overturned unless\\n\\nit is clearly wrong.” Berry v. Schulman, 807 F.3d 600, 617 (4th Cir. 2015) (internal\\n\\nquotation marks omitted).\\n\\n A.\\n\\n We first consider Brundle’s claim that the district court abused its discretion by\\n\\nnot awarding his counsel, Bailey & Glasser, LLP (B&G), a total of $9.9 million in fees\\n\\nunder the firm’s one-third contingent fee agreement with Brundle himself. The district\\n\\ncourt initially suggested that this arrangement was indeed controlling. See Brundle II,\\n\\n258 F. Supp. 3d at 671–72. But the court held its fee decision in abeyance to consider the\\n\\n\\n 10\\n Strangely, although Brundle does not challenge the statutory fee award, he does\\nsummarily contend that he is entitled to $643,584.50 in expenses (the amount he\\nrequested when seeking statutory fees in the district court). The district court denied his\\nrequest for expenses, explaining that it was insufficiently documented. See Brundle II,\\n258 F. Supp. 3d at 669. Before us, Brundle provides neither documentation nor\\nargument. Accordingly, to the extent he even appeals the denial of expenses, we affirm\\nthe district court.\\n\\n 36\\n\\fviews of plan participants and ultimately based its award on equity rather than contract.\\n\\nWe can hardly find an abuse of discretion given that Brundle has no right to have the\\n\\nESOP fund his own fee agreement with B&G.\\n\\n Brundle contends that 29 U.S.C. § 1132(a)(2) — which empowers ESOP\\n\\nparticipants and beneficiaries to bring suit on behalf of an ESOP — additionally\\n\\nauthorizes him to enter into a legal services contract that binds the ESOP. Brundle\\n\\nmusters no caselaw to support his interpretation of the statute, and for good reason.\\n\\nWhile § 1132(a)(2) provides Brundle the right to sue on behalf of the ESOP, neither it\\n\\nnor any other statute authorizes him to unilaterally bind the ESOP to a contract or fee\\n\\nagreement. For this very reason, the vast majority of suits on behalf of ERISA plans take\\n\\nthe form of class actions, in which counsel can seek fees only after a class has been\\n\\ncertified and class members have been given the opportunity to object or opt out. Though\\n\\nB&G has a valid contingent fee agreement with Brundle, see Venegas v. Mitchell, 495\\n\\nU.S. 82 (1990), it does not have a fee agreement with the ESOP.\\n\\n As a result, only equity provides any possible basis for a fee award in addition to\\n\\nthe statutory fees awarded.\\n\\n B.\\n\\n After the district court received the views of some plan participants, it issued a\\n\\nfinal judgment awarding B&G $1.5 million in “addition[]” to the $1.8 million in statutory\\n\\n\\n\\n\\n 37\\n\\ffees — not as a contractual right, but as “a partial common fund award.” 11 Wilmington\\n\\nand Constellis assert that a trio of ERISA provisions precluded the court from awarding\\n\\nany common fund recovery. Unlike most challenges to fee awards, we review de novo\\n\\nquestions regarding a court’s legal authority. See, e.g., Country Vintner of N.C., LLC v. E\\n\\n& J. Gallo Winery, Inc., 718 F.3d 249, 254 (4th Cir. 2013).\\n\\n First, Wilmington and Constellis contend that any common fund award here would\\n\\nviolate ERISA’s “anti-alienation” and “exclusive benefit” provisions. See 29 U.S.C.\\n\\n§ 1056(d)(1) (providing that benefits under retirement plans cannot be “assigned or\\n\\nalienated”); id. § 1103(c)(1) (directing all “assets of a plan” to be “held for the exclusive\\n\\npurposes of providing benefits to participants in the plan and their beneficiaries and\\n\\ndefraying reasonable expenses of administering the plan”). But the district court properly\\n\\nrejected this argument, concluding that because the plan administrator did not yet possess\\n\\nthe damages award — in other words, the court still had jurisdiction over the funds and\\n\\nhad not distributed them to the ESOP — it could not be considered a plan asset. Brundle\\n\\nII, 258 F. Supp. 3d at 670. Of course, if the ESOP had received payment of the award,\\n\\nthose funds would have been subject to ERISA’s duties and protections. See Wilmington\\n\\n\\n 11\\n The district court made clear, and the parties do not dispute, that “[i]n granting\\nboth fee-shifting and contingent fee awards, . . . the contingent fee award must be offset\\nby the amount awarded under the fee-shifting provision.” Brundle II, 258 F. Supp. 3d at\\n672 & n.19. On appeal, Brundle seeks a total of approximately $9.9 million in fees plus\\nabout $650,000 in purported expenses, which (when offset by the $1.8 million in\\nstatutory fees paid by Wilmington) would entitle B&G to a net of approximately $8.8\\nmillion from the common fund. The district court instead awarded Brundle a net of only\\n$1.5 million in fees from the common fund, which it noted was in “addition[]” to the $1.8\\nmillion statutory fee-shifting award, for a total of $3.3 million in fees.\\n\\n 38\\n\\fShipping Co. v. New England Life Ins. Co., 496 F.3d 326, 333 (4th Cir. 2007). But where\\n\\na fund is still under the jurisdiction of the district court, the court may award fees from\\n\\nthat fund without running afoul of ERISA’s anti-alienation or exclusive benefit\\n\\nrequirements. See Kickham Hanley P.C. v. Kodak Ret. Income Plan, 558 F.3d 204, 213\\n\\n(2d Cir. 2009); Lynn v. CSX Transp., Inc., 84 F.3d 970, 975 (7th Cir. 1996).\\n\\n Next, Wilmington and Constellis argue that ERISA’s statutory fee-shifting\\n\\nprovision displaces the common fund doctrine. See 29 U.S.C. § 1132(g)(1) (authorizing\\n\\nprevailing plaintiffs to recover reasonable attorneys’ fees from defendants). They urge us\\n\\nto follow the Seventh Circuit in “limiting the common-fund approach to cases outside the\\n\\nscope of a fee-shifting statute.” Pierce v. Visteon Corp., 791 F.3d 782, 787 (7th Cir.\\n\\n2015); accord Haggart v. Woodley, 809 F.3d 1336, 1358–59 (Fed. Cir. 2016) (largely\\n\\nadopting Pierce rule). 12\\n\\n Several other circuits, however, have disagreed with this approach. See McKeage\\n\\nv. TMBC, LLC, 847 F.3d 992, 1003 (8th Cir. 2017) (“[T]he presence of a fee-shifting\\n\\nstatute precludes a common fund award only when that result is required by the statutory\\n\\nscheme involved.”); In re Bluetooth Headset Prods. Liab. Litig., 654 F.3d 935, 941 (9th\\n\\nCir. 2011) (“The award of attorneys’ fees in a class action settlement is often justified by\\n\\n[a] common fund or statutory fee-shifting[,] . . . and sometimes by both.”); Staton v.\\n\\n\\n 12\\n Pierce is in some tension with prior Seventh Circuit cases holding, in the\\ncontext of settlements, that common fund recoveries are sometimes available even where\\na case was brought under a statute with a fee-shifting provision. See Florin v.\\nNationsbank of Georgia, N.A., 34 F.3d 560, 563–64 (7th Cir. 1994); Skelton v. Gen.\\nMotors Corp., 860 F.2d 250, 252–57 (7th Cir. 1988).\\n\\n 39\\n\\fBoeing Co., 327 F.3d 938, 967–69 (9th Cir. 2003) (permitting common fund recovery\\n\\neven where statutory fees may be available); Cty. of Suffolk v. Long Island Lighting Co.,\\n\\n907 F.2d 1295, 1327 (2d Cir. 1990) (“In our view, fee-shifting statutes are generally not\\n\\nintended to circumscribe the operation of the equitable fund doctrine.”).\\n\\n To determine the proper course here, we consider the roots of the common fund\\n\\ndoctrine. The common fund principle derives from the equitable doctrines of quantum\\n\\nmeruit, Central Railroad & Banking Co. v. Pettus, 113 U.S. 116 (1885), and unjust\\n\\nenrichment, Trustees v. Greenough, 105 U.S. 527, 532 (1881). It allows a court to award\\n\\n“a reasonable attorney’s fee” to “a litigant or a lawyer who recovers a common fund for\\n\\nthe benefit of persons other than himself or his client . . . from the fund as a whole.”\\n\\nBoeing Co. v. Van Gemert, 444 U.S. 472, 478 (1980). The rationale for the doctrine is\\n\\nthat when one benefits from a lawsuit without contributing to its costs, he has been\\n\\nunjustly enriched at the successful litigant’s or lawyer’s expense. Mills v. Elec. Auto-Lite\\n\\nCo., 396 U.S. 375, 392 (1970). Courts remedy this inequity by shifting a proportional\\n\\nshare of reasonable attorneys’ fees onto these unjustly enriched beneficiaries.\\n\\n The Supreme Court has applied the “strong and uniform . . . background rule” of\\n\\nthe common fund doctrine “in a wide range of circumstances as part of [its] inherent\\n\\nauthority.” US Airways, Inc. v. McCutchen, 569 U.S. 88, 104 (2013) (collecting cases).\\n\\nWe agree with Brundle that it applies here. Scores of unnamed ESOP participants\\n\\nbenefited substantially from this lawsuit, while B&G bore the entirety of the costs and\\n\\nrisks. Equity thus demands that the enriched participants pay a proportional share of\\n\\nreasonable attorneys’ fees.\\n\\n 40\\n\\f To be sure, courts often, but not invariably, award common fund fees when a\\n\\nprocedural obstacle, such as the terms of a settlement, bars statutory fees that are\\n\\notherwise available. 13 But it does not follow that all statutory fee provisions necessarily\\n\\ndisplace the doctrine or render it superfluous. To the contrary: although both the\\n\\ncommon fund doctrine and fee-shifting statutes facilitate suit by plaintiffs who may\\n\\notherwise lack the means to hire counsel, they operate in distinct ways and serve distinct\\n\\npurposes.\\n\\n A common fund recovery places the plaintiffs’ cost of litigation on the recovering\\n\\nbeneficiaries of a lawsuit, whereas a fee-shifting statute places this burden on the losing\\n\\nparty. Cf. Venegas, 495 U.S. at 90 (differentiating between “what the losing defendant\\n\\nmust pay” to the plaintiff as attorneys’ fees under a fee-shifting statute and “what the\\n\\nprevailing plaintiff must pay his lawyer”). A fee-shifting statute thus creates an\\n\\nexception to the “American rule” that “the prevailing litigant is ordinarily not entitled to\\n\\ncollect a reasonable attorneys’ fee from the loser.” Alyeska Pipeline Serv. Co. v.\\n\\nWilderness Soc., 421 U.S. 240, 247 (1975). In contrast, the common fund doctrine —\\n\\nthough often similarly described as an exception — better accords with the American rule\\n\\n 13\\n See, e.g., Skelton, 860 F.2d at 256 (affirming common fund award where “the\\nfee-shifting provision [did] not . . . apply to a fee determination in a case settled in a\\ncommon fund”); In re Fine Paper Antitrust Litig., 751 F.2d 562, 582–83 (3d Cir. 1984)\\n(affirming common fund award where settlement released defendants from statutorily\\navailable fees). But see Reyes v. Bakery & Confectionary Union & Indus. Int’l Pension\\nFund, 281 F. Supp. 3d 833, 850 (N.D. Cal. 2017) (“[C]lass counsel may be awarded fees\\nfrom the common fund in addition to any award under ERISA’s fee-shifting statute.”);\\nHumphrey v. United Way of Tex. Gulf Coast, 802 F. Supp. 2d 847, 859 (S.D. Tex. 2011)\\n(“The Court . . . has the power and discretion to award reasonable fees under both\\n[ERISA] and the common fund doctrine.”).\\n\\n 41\\n\\fby holding the beneficiaries of a judgment or settlement responsible for compensating the\\n\\ncounsel who obtained the judgment or settlement for them. See Staton, 327 F.3d at 967.\\n\\n Furthermore, the purpose of the common fund doctrine, unlike a fee-shifting\\n\\nstatute, is to avoid unjust enrichment. Thus, although a statutory fee award against a\\n\\ndefendant generally may not include a contingency enhancement, see City of Burlington\\n\\nv. Dague, 505 U.S. 557, 565–67 (1992), courts routinely impose enhanced common fund\\n\\nawards to compensate counsel for litigation risk at the expense of beneficiaries who did\\n\\nnot shoulder this risk, see, e.g., In re Wash. Pub. Power Supply Sys. Secs. Litig., 19 F.3d\\n\\n1291, 1300 (9th Cir. 1994) (“There is nothing unfair about contingency enhancements in\\n\\ncommon fund cases . . . .”); Florin, 34 F.3d at 564–65 (similarly holding that “the policy\\n\\nconsiderations . . . that militate for forbidding risk multiples in statutory fee-shifting cases\\n\\nhave little force in common fund cases”).\\n\\n From these distinctions, it follows that a “reasonable” fee payable by a defendant\\n\\nto compensate the prevailing plaintiff’s counsel is not necessarily identical to a\\n\\n“reasonable” fee owed by a recovering beneficiary to plaintiff’s counsel, particularly\\n\\nwhere the contingency risk to plaintiff’s counsel is substantial. Cf. Venegas, 495 U.S. at\\n\\n85, 90 (affirming $406,000 contractual fee, paid by prevailing plaintiff to his counsel, as\\n\\nnot “unreasonable” even though “reasonable” statutory fee, paid by losing defendants,\\n\\nwas only $117,000); McKeage, 847 F.3d at 1004 (emphasizing “a distinction between the\\n\\namount a losing party may be required to pay” under fee-shifting provision in settlement\\n\\n“and the amount a class member should equitably be required to pay” under common\\n\\nfund doctrine).\\n\\n 42\\n\\f Consequently, we find unpersuasive the Seventh Circuit’s reasoning in Pierce. In\\n\\nlimiting the common fund doctrine to cases “outside the scope of a fee-shifting statute,”\\n\\nthe Pierce court reasoned first and foremost that “[c]ommon-law doctrines yield to\\n\\nstatutes.” 791 F.3d at 787. But the Supreme Court has instructed that courts must\\n\\n“presum[e] that Congress intended to retain the substance of the common law.”\\n\\nSamantar v. Yousuf, 560 U.S. 305, 320 n.13 (2010). We recognize, of course, that\\n\\nlegislative displacement of the common law does not require “the same sort of evidence\\n\\nof a clear and manifest congressional purpose demanded for preemption of state law.”\\n\\nAm. Elec. Power Co., Inc. v. Connecticut, 564 U.S. 410, 423 (2011) (alterations and\\n\\ninternal quotation marks omitted). Even so, a statute that shifts a reasonable fee onto a\\n\\nlosing defendant does not, without more, “speak[] directly” to congressional intent to\\n\\ndisplace recovery from a common fund. Id. at 424 (internal quotation marks omitted).\\n\\n The Pierce court additionally emphasized that “fee-shifting statutes are designed\\n\\nto ensure that the victims retain full compensation,” 791 F.3d at 787, a concern of\\n\\nindisputable importance. The common fund doctrine, however, balances this critical\\n\\ninterest against the concern of unjust enrichment, which ERISA’s fee-shifting provision\\n\\ndoes not purport to address.\\n\\n Finally, echoing the Pierce court, Wilmington and Constellis stress that B&G was\\n\\nentitled to, and received, a “reasonable” attorneys’ fee under statute. However, as we\\n\\nhave explained, what is “reasonable” as a fee from a losing defendant may well differ\\n\\nfrom what is “reasonable” as a fee from an individual directly benefited by counsel’s\\n\\nefforts. We particularly note that a “reasonable” fee under ERISA’s attorneys’ fee\\n\\n 43\\n\\fprovision (unlike a common fund award) precludes any compensation for contingency\\n\\nrisk. See Dague, 505 U.S. at 565–67. But, we have previously underscored, contingent\\n\\nfees serve an important function in providing under-resourced litigants access to counsel\\n\\nand the courts. In re Abrams & Abrams, P.A., 605 F.3d 238, 245–47 (4th Cir. 2010).\\n\\nConflating statutory attorneys’ fees with common fund recoveries would squarely\\n\\ncontravene this policy.\\n\\n We therefore agree with the Second, Eighth, and Ninth Circuits that a statutory\\n\\nfee-shifting provision (or an award of fees under such a provision) does not, as a matter\\n\\nof law, automatically preclude an award under the common fund doctrine. Accordingly,\\n\\nthe district court retained discretion to award supplemental attorneys’ fees from the\\n\\ncommon fund.\\n\\n C.\\n\\n Having established the district court’s authority to award supplemental fees, we\\n\\nturn to Brundle’s contention that the court abused its discretion in awarding its counsel\\n\\ntoo little from the common fund.\\n\\n Before setting the amount of its common fund award, the district court fashioned\\n\\nan ad hoc process analogous to class settlement procedures under Rule 23. Brundle II,\\n\\n258 F. Supp. 3d at 671–72. The court ordered Brundle’s counsel, B&G, to engage in a\\n\\ngood faith effort to notify the approximately 1,800 former ESOP participants of its\\n\\nproposed contingency fee award. After B&G did so, the court received 59 letters\\n\\nobjecting to a one-third contingency award. As a result of the objections, the court\\n\\ndecided to award B&G only $1.5 million as a supplemental fee payable from the\\n\\n 44\\n\\fdamages award, rather than granting counsel a full one-third ($9.9 million) of the ESOP’s\\n\\ntotal damages recovery.\\n\\n In reviewing the district court’s award, we note that Brundle had available a\\n\\nprocedural mechanism designed to carefully balance the interests of counsel, plaintiffs,\\n\\nand other similarly situated beneficiaries from the start — namely, class certification\\n\\npursuant to Rule 23. To be fair, Brundle and another plaintiff, Halldorson, did initially\\n\\nseek class certification, which the district court denied. But Brundle opted not to timely\\n\\nappeal this denial. And although Halldorson initially sought our review, he later\\n\\nwithdrew his appeal. See supra n.4.\\n\\n Had Brundle pursued class certification and prevailed, B&G could have secured\\n\\nattorneys’ fees from the class as a whole. Although a properly certified class might not\\n\\nhave agreed to the same one-third contingency fee that Brundle did, the district court\\n\\nmight well have awarded a fee significantly higher than the firm’s ultimate recovery\\n\\nhere. 14\\n\\n Brundle, represented by B&G, instead opted to forego Rule 23’s procedural\\n\\nstrictures — thus avoiding “the standards set for the protection of absent class members.”\\n\\nAmchem Prods., Inc. v. Windsor, 521 U.S. 591, 621 (1997). In light of this choice, the\\n\\ndistrict court’s decision to limit the common fund award was not inequitable, as\\n\\nillustrated by the objections from some of the ESOP’s participants. Nearly 60 of the\\n\\n 14\\n See, e.g., Savani v. URS Prof’l Sols. LLC, 121 F. Supp. 3d 564, 574–75 (D.S.C.\\n2015) (approving fee award of 39.57% from common fund award in ERISA settlement\\nand collecting cases); In re Marsh ERISA Litig., 265 F.R.D. 128, 149 (S.D.N.Y. 2010)\\n(approving fee award of 33.33% from common fund award).\\n\\n 45\\n\\f1,800 participants objected to the proposed common fund award, explaining that they had\\n\\nnever been informed of the case status, never agreed to B&G’s representation, and never\\n\\nauthorized the fund to pay a one-third fee. These process concerns would have been\\n\\navoided upfront had Brundle persisted in his pursuit of class certification. But because he\\n\\nand his counsel abandoned Rule 23’s class-protective procedures, equity cuts against\\n\\nawarding B&G the full one-third contingency fee.\\n\\n The district court properly weighed B&G’s efforts on behalf of the ESOP —\\n\\nincluding contingency risk — against the objections from ESOP participants to determine\\n\\na proper common fund award. Because we cannot say this balancing was clearly wrong,\\n\\nsee Berry, 807 F.3d at 617, we affirm the court’s fee award in full.\\n\\n\\n\\n V.\\n\\n For the foregoing reasons, the judgment of the district court is in all respects\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 46\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1065,"cells":{"id":{"kind":"number","value":4602939,"string":"4,602,939"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"Howard Duncan v. William Barr"},"decision_date":{"kind":"string","value":"2019-03-22"},"docket_number":{"kind":"string","value":"17-2423"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before MOTZ, DUNCAN and QUATTLEBAUM, Circuit Judges.\", \"parties\": \"\", \"opinions\": [{\"author\": \"DUNCAN, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 17-2423\\n\\n\\nHOWARD EGBA DUNCAN, JR., a/k/a Duncan Egbaf, a/k/a Howard Duncan,\\n\\n Petitioner,\\n\\nv.\\n\\nWILLIAM P. BARR, Attorney General,\\n\\n Respondent.\\n\\n\\nOn Petition for Review of an Order of the Board of Immigration Appeals.\\n\\n\\nArgued: November 1, 2018 Decided: March 19, 2019\\n Amended: March 22, 2019\\n\\n\\nBefore MOTZ, DUNCAN and QUATTLEBAUM, Circuit Judges.\\n\\n\\nPetition for review granted; remanded for further proceedings by published opinion.\\nJudge Duncan wrote the opinion, in which Judge Motz and Judge Quattlebaum\\nconcurred.\\n\\n\\nARGUED: Michael S. DePrince, PEPPER HAMILTON LLP, Philadelphia,\\nPennsylvania, for Petitioner. Lindsay Donahue, UNITED STATES DEPARTMENT OF\\nJUSTICE, Washington, D.C., for Respondent. ON BRIEF: Anthony Vale, Kate A.\\nMahoney, PEPPER HAMILTON LLP, Philadelphia, Pennsylvania; Michelle N. Mendez,\\nCATHOLIC LEGAL IMMIGRATION NETWORK, INC., Silver Spring, Maryland;\\nHimedes V. Chicas, LAW OFFICES OF JEZIC & MOYSE, LLC, Silver Spring,\\nMaryland, for Petitioner. Chad A. Readler, Acting Assistant Attorney General, Kiley\\nKane, Senior Litigation Counsel, Office of Immigration Litigation, Civil Division,\\n\\fUNITED STATES DEPARTMENT OF JUSTICE, Washington, D.C., for Respondent.\\n\\n\\n\\n\\n 2\\n\\fDUNCAN, Circuit Judge:\\n\\n After submitting an unsuccessful application for a certificate of citizenship with\\n\\nthe United States Citizenship and Immigration Services (the “USCIS”), Howard Egba\\n\\nDuncan, Jr. was placed in removal proceedings. Duncan applied for relief under the\\n\\nUnited Nations Convention against Torture and Other Cruel, Inhuman or Degrading\\n\\nTreatment or Punishment (the “CAT”), 8 C.F.R. § 1208.16(c), and also moved to\\n\\nterminate the proceedings on the basis that he had derived citizenship from his father\\n\\nunder the Child Citizenship Act of 2000 (the “CCA”), 8 U.S.C. §§ 1431–33. The\\n\\nimmigration judge (the “IJ”) determined that Duncan had failed to demonstrate the\\n\\nrequisite governmental acquiescence for relief under the CAT and that he had not derived\\n\\ncitizenship under the CCA because he was not in the “physical custody” of his father\\n\\nduring the requisite time period. The Board of Immigration Appeals (the “BIA”)\\n\\naffirmed on both grounds, finding that the IJ did not clearly err in reaching either\\n\\nconclusion.\\n\\n We are compelled to find that the BIA applied the wrong standard of review as to\\n\\nboth determinations. Consistent with precedent established since the BIA’s decision, we\\n\\nhold that whether the government would acquiesce to torture under the CAT is a mixed\\n\\nquestion of fact and law. Similar analysis persuades us that whether Duncan was in the\\n\\n“physical custody” of his father under the CCA is likewise a mixed question of fact and\\n\\nlaw. While the IJ’s findings of fact are subject to clear error review, the application of\\n\\nthose facts to the relevant legal standards constitute legal judgments subject to de novo\\n\\nreview by the BIA. Accordingly, we grant the petition for review and remand to the BIA.\\n\\n 3\\n\\f I.\\n\\n Duncan is a legal permanent resident of the United States who was born in Nigeria\\n\\nto a Nigerian mother and an American father. When Duncan was six years old, he and\\n\\nhis grandmother moved from Nigeria to the United States to live with Duncan’s father.\\n\\nDuncan lived with his father and grandmother for three months before his father was\\n\\nincarcerated in April 1998. A few months later, Duncan’s grandmother filed a petition to\\n\\nbecome Duncan’s guardian, which was granted later that year. Duncan’s father remained\\n\\nincarcerated until 2011, two years after Duncan’s eighteenth birthday.\\n\\n Throughout his father’s incarceration, Duncan and his father had limited physical\\n\\ncontact with one another; Duncan visited his father approximately once a month and the\\n\\ntwo talked on the phone several times a week. Though Duncan’s father provided some\\n\\nfinancial support to Duncan and remained involved in certain aspects of his upbringing--\\n\\ne.g., deciding where he went to school, what shoes his grandmother could purchase for\\n\\nhim, and whether he would play football--Duncan’s grandmother acted as his primary\\n\\ncaretaker, driving him to and from school and providing him shelter, clothing, and\\n\\nconsistent financial support.\\n\\n Prior to the instant removal proceedings and before his eighteenth birthday,\\n\\nDuncan applied for a certificate of citizenship on July 14, 2009. His application was\\n\\ndenied in March 2010. Duncan appealed the denial of his application, which the\\n\\nAdministrative Appeals Office (the “AAO”) affirmed in February 2015, finding that\\n\\n\\n\\n 4\\n\\fDuncan failed to establish that he was in the “legal custody” or “physical custody” of his\\n\\nfather because he did not reside with his father during the relevant period. 1\\n\\n After Duncan’s appeal was denied, the government initiated removal proceedings\\n\\nagainst him pursuant to 8 U.S.C. § 1227(a)(2) based on his convictions for four crimes\\n\\ncommitted between October 2008 and January 2011. The government charged three\\n\\ngrounds of removability: (1) his conviction of a crime of violence under 18 U.S.C. § 16,\\n\\nwhich was an aggravated felony; (2) his conviction of two crimes involving moral\\n\\nturpitude that did not arise from a single scheme; and (3) his conviction for a firearm\\n\\noffense.\\n\\n Duncan moved to terminate the proceedings on the basis that he was not\\n\\nremovable because he had derived citizenship through his father under the CCA. As a\\n\\ncitizen, he would not be removable from the United States under § 1227(a)(2), which\\n\\nonly applies to aliens. Ojo v. Lynch, 813 F.3d 533, 535 (4th Cir. 2016).\\n\\n Under the CCA, a child born outside the United States automatically becomes a\\n\\ncitizen where (1) the child has at least one parent that is a citizen of the United States,\\n\\neither by birth or naturalization; (2) the child is under eighteen years old; and (3) the child\\n\\nresides in the United States in the legal and physical custody of the citizen parent.\\n\\n8 U.S.C. § 1431(a). Neither party disputed before the IJ that Duncan satisfies the first\\n\\n 1\\n Neither party contends that the AAO’s decision was binding or dispositive as to\\nDuncan’s derivative citizenship claim before the IJ, the BIA, or this court. Instead, as the\\nIJ recognized in its decision, where a respondent is claiming derivative citizenship in\\nremoval proceedings and such claim “has reasonable support, it cannot be rejected\\narbitrarily.” J.A. 180 (quoting Matter of Tijerina-Villarreal, 13 I&N Dec. 327, 331 (BIA\\n1969)).\\n\\n 5\\n\\ftwo requirements. Rather, they disagreed as to whether Duncan was in the “legal\\n\\ncustody” and “physical custody” of his father during the relevant period--from February\\n\\n27, 2001, when the CCA was enacted, to October 17, 2009, when Duncan turned\\n\\neighteen years old--given that his father was incarcerated. See 8 C.F.R. § 320.2\\n\\n(providing that the requirements of the CCA must “have been met after February 26,\\n\\n2001”).\\n\\n Following an evidentiary hearing at which Duncan and his father testified, the IJ\\n\\ndetermined that Duncan had not derived citizenship from his father because he was not in\\n\\nthe “physical custody” of his father during the relevant period. 2 In reaching this\\n\\nconclusion, the IJ reasoned that Duncan was not in the physical care of his father and that\\n\\nhis father did not personally supervise him or make day-to-day decisions over his\\n\\nwelfare. The IJ did not address whether Duncan satisfied the legal custody requirement\\n\\nunder § 1431(a). Consequently, the IJ held that Duncan was removable and denied his\\n\\nsubsequent motion to reconsider.\\n\\n In addition to his derivative citizenship claim, Duncan applied for cancellation of\\n\\nremoval, which the IJ denied. Namely, the IJ found that because Duncan had been\\n\\nconvicted of an aggravated felony, he was disqualified from receiving cancellation of\\n\\nremoval.\\n\\n\\n\\n\\n 2\\n Neither party disputes that the IJ properly identified Maryland--where Duncan\\nresided during the relevant period--as the state whose law governed the physical custody\\ninquiry under the CCA.\\n\\n 6\\n\\f Duncan also applied for relief under the CAT. Under the CAT’s implementing\\n\\nregulations, relief is authorized when an individual demonstrates that it is more likely\\n\\nthan not that “he or she would be tortured if removed to the proposed country of\\n\\nremoval.” 8 C.F.R. § 1208.16(c)(2). To satisfy this standard, a petitioner is required to\\n\\nmake two distinct showings. Turkson v. Holder, 667 F.3d 523, 526 (4th Cir. 2012)\\n\\n(citing 8 C.F.R. § 208.16(c)(2)). First, the petitioner must demonstrate that it is more\\n\\nlikely than not that he will be tortured if removed. Second, the petitioner must show that\\n\\nsuch mistreatment “will occur at the hands of government or with the consent or\\n\\nacquiescence of government.” Id. at 526. While the IJ found Duncan credible, the IJ\\n\\ndenied him CAT relief on the basis that he had not met his burden of proving either that it\\n\\nwas more likely than not that he would be tortured if removed to Nigeria or that such\\n\\ntorture would be by or with the consent or acquiescence of public officials.\\n\\n Duncan appealed the IJ’s removal order to the BIA. In a single-member decision,\\n\\nthe BIA dismissed his appeal. Affirming the IJ’s determination that Duncan is ineligible\\n\\nfor CAT relief, the BIA concluded that the IJ “did not clearly err in finding that the\\n\\ntorture [Duncan] fears would not come at the hands of a public official or with the\\n\\nacquiescence of those officials.” 3 J.A. 353. The BIA also found that the IJ “did not\\n\\nclearly err in finding that [Duncan’s] father did not have physical custody of the\\n\\nrespondent during the relevant time period” and affirmed the IJ’s determination that\\n\\n\\n 3\\n The BIA declined to reach the IJ’s determination that Duncan would not likely\\nbe subject to torture under the CAT.\\n\\n\\n 7\\n\\fDuncan did not derive citizenship from his father under the CCA. J.A. 351. Like the IJ,\\n\\nthe BIA did not address whether Duncan was in the “legal custody” of his father during\\n\\nthe relevant time period. 4 This appeal followed.\\n\\n\\n\\n II.\\n\\n Duncan challenges the BIA’s denial of his request for relief under the CAT and its\\n\\nrejection of his derivative citizenship claim. Specifically, he argues that the BIA applied\\n\\nthe wrong standard of review when it affirmed both of the IJ’s determinations, which the\\n\\nBIA concluded were pure questions of fact and accordingly reviewed for clear error.\\n\\nWhether the BIA has applied the proper standard of review is a question of law for\\n\\npurposes of our jurisdiction under 8 U.S.C. § 1252(a)(2)(D), which we review de novo.\\n\\nUpatcha v. Sessions, 849 F.3d 181, 184 (4th Cir. 2017).\\n\\n For the reasons that follow, we conclude that the BIA incorrectly reviewed the IJ’s\\n\\ndeterminations--government acquiescence under the CAT and “physical custody” under\\n\\nthe CCA--for clear error. We therefore grant Duncan’s petition for review and remand to\\n\\n\\n\\n\\n 4\\n Accordingly, we do not reach the question of whether Duncan was in the “legal\\ncustody” of his father during the relevant time period. On remand, however, depending\\non the BIA’s determinations, it may be necessary for the BIA to address both whether\\nDuncan was in his father’s “physical custody” and “legal custody” pursuant to 8 U.S.C.\\n§ 1431(a).\\n\\n\\n 8\\n\\fthe BIA for application of the correct standard of review. 5 We address Duncan’s claims\\n\\nunder the CAT and the CCA in turn.\\n\\n\\n\\n A.\\n\\n Duncan first argues that the BIA applied the wrong standard of review in\\n\\naffirming the IJ’s determination that he is ineligible for relief under the CAT.\\n\\nSpecifically, he argues that the BIA should have reviewed the IJ’s determination de novo\\n\\nrather than for clear error.\\n\\n We recently addressed this issue in Cruz-Quintanilla v. Whitaker, 914 F.3d 884\\n\\n(4th Cir. 2019), which binds us here. There, we held that the government acquiescence\\n\\ndetermination under the CAT is a mixed question of fact and law and that an IJ’s\\n\\n“determination that the evidence did not meet the relevant standard is a legal judgment\\n\\nsubject to de novo review by the [BIA].” Id. at 885.\\n\\n Here, neither party disputes that the BIA reviewed the IJ’s determination that\\n\\nDuncan did not establish a likelihood of government acquiescence for clear error rather\\n\\nthan de novo. Accordingly, we remand Duncan’s CAT claim so that the BIA may apply\\n\\nthe correct standard of review.\\n\\n\\n\\n\\n 5\\n We therefore do not reach the question of whether one of Duncan’s convictions\\nconstitutes an aggravated felony and, accordingly whether he is eligible for cancellation\\nof removal, in light of the Supreme Court’s ruling in Sessions v. Dimaya, 138 S. Ct. 1204\\n(2018)--a question that the government concedes should be remanded to the BIA to\\nconsider, having declined to reach it previously.\\n\\n 9\\n\\f B.\\n\\n Next, Duncan argues that the BIA applied the wrong standard of review in\\n\\naffirming the IJ’s determination that he has not derived citizenship from his father under\\n\\nthe CCA such that he cannot be removed. Namely, he contends that the BIA erred in\\n\\napplying clear error review to the question of whether he was in the “physical custody” of\\n\\nhis father under the CCA. As this question is a matter of first impression before the\\n\\ncourt, we first address the relevant regulations dictating the BIA’s standards of review of\\n\\nIJ decisions.\\n\\n The BIA’s review of an IJ’s decisions is governed by 8 C.F.R. § 1003.1(d)(3).\\n\\nPrior to 2002, the regulations provided for de novo review by the BIA over all aspects of\\n\\nIJ decisions. Subsequently, however, new regulations established a standard of review\\n\\nunder which the BIA reviews findings of fact for clear error. 8 C.F.R. § 1003.1(d)(3)(i).\\n\\nBut the BIA reviews de novo “all other issues,” id. § 1003.1(d)(3)(ii), “including, in cases\\n\\ninvolving mixed questions of law and fact, the application of the governing legal standard\\n\\nto the facts found by the immigration judge.” Cruz-Quintanilla, 914 F.3d at 889 (internal\\n\\ncitation omitted).\\n\\n Guided by our precedent in similar contexts, we conclude that whether an\\n\\nindividual was in the “physical custody” of a parent under the CCA is a mixed question\\n\\nof fact and law. We first review the analysis in those cases and then turn to the question\\n\\nof the applicability of that analysis to the physical custody determination under the CCA.\\n\\n\\n\\n i.\\n\\n 10\\n\\f Mixed questions of fact and law require a review of two determinations--what the\\n\\nfacts were in a particular case, and the legal conclusions to which those facts lead.\\n\\nTurkson, 667 F.3d at 527. The IJ’s determination of “what happened” is by its nature a\\n\\nfactual finding giving rise to review for clear error by the BIA. See Upatcha, 849 F.3d at\\n\\n185. But applying the relevant legal standard to those facts and deciding whether that\\n\\nstandard was met is a legal judgment subject to de novo review. Id.\\n\\n We have approached similar IJ determinations as a two-step inquiry, requiring the\\n\\nBIA to review an IJ’s factual findings for clear error and its application of the appropriate\\n\\nlegal standard de novo. In Turkson v. Holder, for example, we held that whether a\\n\\npetitioner would be subject to torture within the meaning of the CAT is a mixed question\\n\\nof fact and law. 667 F.3d at 529. The BIA reviews for clear error the IJ’s factual\\n\\nfindings as to what would happen to the petitioner upon removal. But the BIA reviews\\n\\nde novo the IJ’s legal conclusion as to whether this future mistreatment amounts to\\n\\n“torture,” which is “a term of art under the CAT . . . with a specific legal definition.” Id.\\n\\nat 526, 530. Put another way, although the BIA defers to the IJ’s findings of historical\\n\\nfacts and the likelihood that they would occur in the future, the BIA “exercise[s] its\\n\\nindependent judgment to evaluate . . . the legal significance of the facts” as well as “the\\n\\nultimate conclusions to which those facts lead.” Id. at 527. We later held that the same\\n\\nstandard of review applies to the question of whether the government would acquiesce to\\n\\nsuch torture under the CAT, as discussed supra. Cruz-Quintanilla, 914 F.3d at 885.\\n\\n Similarly, in Upatcha we held that whether a petitioner entered into a good faith\\n\\nmarriage under 8 U.S.C. § 1186a(c)(4)(B) is a mixed question of fact and law. 849 F.3d\\n\\n 11\\n\\fat 184; see Massis v. Mukasey, 549 F.3d 631, 636 n.6 (4th Cir. 2008) (explaining that the\\n\\nBIA reviews the IJ’s factual findings of what happened to an individual for clear error,\\n\\nbut reviews de novo the “application of the law to . . . facts--to determine, for example,\\n\\nwhether those facts amount to ‘exceptional and extremely unusual hardship’” (citation\\n\\nomitted). The IJ’s factual determinations--such as the petitioner’s credibility and the\\n\\ndegree to which the couple’s finances were intermingled--are subject to clear error\\n\\nreview. In contrast, the IJ’s ultimate legal judgment--determining whether the\\n\\npetitioner’s marriage satisfies the good faith standard under 8 U.S.C. § 1186a(c)(4)(B)--is\\n\\nsubject to de novo review. Upatcha, 849 F.3d at 185.\\n\\n Applying these same analytical steps, as set out below, we conclude that whether a\\n\\nforeign-born child was in the “physical custody” of her citizen parent under the CCA is a\\n\\nmixed question of fact and law. It requires the IJ first to determine the specific, relevant\\n\\nfacts of the parent-child relationship and then to assess, on the basis of those facts,\\n\\nwhether the parent had “physical custody” over the child as a legal matter. 6\\n\\n\\n\\n ii.\\n\\n The analytical steps that the IJ must take in determining whether a child was in the\\n\\n“physical custody” of her parent under the CCA underscore our conclusion that this\\n\\ndetermination is necessarily a mixed question. Under the CCA, a child born outside of\\n\\n 6\\n We note that the Sixth Circuit has stated, without explaining, that “[t]he IJ’s\\nruling that [the] petitioner . . . did not reside in his citizen father’s physical custody at the\\ntime of his naturalization or at any time thereafter is a factual finding.” Karimijanaki v.\\nHolder, 579 F.3d 710, 721 (6th Cir. 2009).\\n\\n 12\\n\\fthe United States automatically becomes a citizen when, inter alia, the child is residing in\\n\\nthe United States in the “physical custody of the citizen parent.” 8 U.S.C. § 1431(a)(3).\\n\\nCongress has not defined “physical custody” in the CCA or its accompanying\\n\\nregulations. Rather, “it has long been a hallmark of our federalism principles that full\\n\\nauthority over domestic-relations matters resides not in the national government, but in\\n\\nthe several States.” Ojo, 813 F.3d at 540 (citing Ex parte Burrus, 136 U.S. 586, 593–94\\n\\n(1890)).\\n\\n In the absence of a federal definition, and because both the Supreme Court and our\\n\\nown cases look to state law to determine legal relationships in the family context, we turn\\n\\nto state law to determine the meaning of “physical custody” under the CCA. See, e.g., De\\n\\nSylva v. Ballentine, 351 U.S. 570, 580 (1956) (turning to state law to discern whether an\\n\\nillegitimate child is included within the term “children” as used in the Copyright Act,\\n\\nreasoning that “there is no federal law of domestic relations, which is primarily a matter\\n\\nof state concern”). 7\\n\\n “Physical custody” under the CCA therefore presumptively means “physical\\n\\ncustody” as defined under the law of the state in question--in this case, Maryland. Which\\n\\nstate law governs the CCA’s physical custody determination is significant because states\\n\\n\\n 7\\n Indeed, in the absence of a definition of the term “adoption” under the CCA, we\\nhave looked to state law instruments to determine when an individual was adopted for\\npurposes of deriving citizenship under the statute. Ojo, 813 F.3d at 539–41 (“[I]f\\nCongress had intended a modified definition of the term ‘adopted’ for purposes of federal\\nimmigration law and sought to place the interpretation thereof in the hands of an\\nadministrative agency, such as the BIA, Congress would have made that intention\\n‘unmistakably clear.’”) (citing Gregory v. Ashcroft, 501 U.S. 452, 460 (1991)).\\n\\n 13\\n\\fhave appeared to adopt different approaches to determining physical custody, and the\\n\\nsame set of facts may result in different legal outcomes depending upon where they\\n\\noccur.\\n\\n Accordingly, for the limited purpose of illustrating why the CCA’s physical\\n\\ncustody inquiry is necessarily a mixed question of fact and law, we find it helpful to\\n\\ncontrast two states’ approaches--that of Montana and Nevada. However, we clarify that\\n\\nin doing so, we take no position as to whether the physical presence of a parent is\\n\\nnecessary for that parent to have physical custody of her child under either state’s law,\\n\\nnor under the law of Maryland.\\n\\n We begin with the example of the physical custody inquiry under Montana law.\\n\\nMontana recognizes that a parent’s right to custody of her child “is a fundamental,\\n\\nconstitutionally protected right.” Girard v. Williams, 966 P.2d 1155, 1158–59 (Mont.\\n\\n1998). Regarding physical custody in particular, the Montana Supreme Court has held\\n\\nthat such custody “is not limited to having actual, immediate control of the physical\\n\\npresence of the child. Rather, this phrase relates to the custodial rights involved in the\\n\\ncare and control of the child.” Henderson v. Henderson, 568 P.2d 177, 179 (Mont.\\n\\n1977). Indeed, that court has held that a parent who had been incarcerated for five years\\n\\ndid not voluntarily relinquish his right to physical custody “when considered in\\n\\nconjunction with his actions to maintain contact with his children.” Girard, 966 P.2d at\\n\\n1164–65 (holding that nonparents lacked standing to pursue a custodial claim where they\\n\\nfailed to show that the children were not in the physical custody of their parent).\\n\\n\\n\\n 14\\n\\f In contrast, it appears that Nevada requires a parent to reside with a child as a\\n\\ncomponent of physical custody. See Rivero v. Rivero, 216 P.3d 213, 222 (Nev. 2009)\\n\\n(“Physical custody involves the time that a child physically spends in the care of a parent.\\n\\nDuring this time, the child resides with the parent and that parent provides supervision for\\n\\nthe child and makes the day-to-day decisions regarding the child.”).\\n\\n Consequently, the same facts may nonetheless lead an IJ to conclude that a parent\\n\\nhas physical custody over her child under one state’s laws but not another’s. Take, for\\n\\nexample, a child who resides with one parent during the school year and with the other\\n\\nduring the summer vacation months. In Montana, it would appear that both parents retain\\n\\nphysical custody over the child throughout the entire year. In other words, the parent\\n\\nwith whom the child resides during the summer is not divested of her physical custody\\n\\nover the child during the school year, when the child resides with the other parent. See In\\n\\nre Marriage of Susen, 788 P.2d 332, 334 (Mont. 1990) (affirming an award of joint legal\\n\\nand physical custody where the parents live in separate states and the court imposed a\\n\\nsummer and school year schedule). In contrast, in Nevada it appears that only the parent\\n\\nwith whom the child physically resides at the time has custody of the child--meaning that\\n\\nthe parent with whom the child resides in the summer has physical custody only during\\n\\nthe summer. See Bluestein v. Bluestein, 345 P.3d 1044, 1048 (Nev. 2015) (observing that\\n\\nas a general matter, where a child resides with each parent “at least 40 percent of the\\n\\n\\n\\n\\n 15\\n\\ftime, equal to at least 146 days over one calendar year, the parents share[] joint physical\\n\\ncustody”); Rivero, 216 P.3d at 222. 8\\n\\n In sum, we conclude that the physical custody determination under the CCA\\n\\nrequires a bifurcated approach. While the IJ’s findings of fact are subject to clear error\\n\\nreview, the IJ’s application of the facts to the relevant state law in determining whether\\n\\nan individual satisfies the physical custody requirement under § 1431(a) is a legal\\n\\njudgment subject to de novo review by the BIA. Accordingly, we find that the BIA erred\\n\\nin reviewing for clear error the IJ’s legal judgment as to whether, pursuant to Maryland\\n\\nlaw, Duncan satisfied the CCA’s physical custody requirement. Because the BIA applied\\n\\nthe wrong standard of review to this determination, we remand. Should the BIA resolve\\n\\nthe physical custody determination in Duncan’s favor, it must also address whether or not\\n\\nDuncan was in his father’s “legal custody” as the statute so requires for purposes of\\n\\nderivative citizenship. 8 U.S.C. § 1431(a).\\n\\n\\n\\n III.\\n\\n For the foregoing reasons, we grant Duncan’s petition for review and remand the\\n\\ncase to the BIA for further proceedings consistent with this opinion.\\n\\n 8\\n We emphasize that we make no holding regarding the application of Montana or\\nNevada law to the CCA’s physical custody requirement. Indeed, the tensions between\\nstate law defining custodial rights prospectively in context of divorce proceedings on the\\none hand, and the retroactive application of those definitions to evaluate parent-child\\nrelationships for purposes of the CCA on the other, may complicate any attempt to assess\\nphysical custody as a simple factual matter. However, we need not reach those issues\\nhere.\\n\\n\\n 16\\n\\f PETITION FOR REVIEW GRANTED;\\nREMANDED FOR FURTHER PROCEEDINGS\\n\\n\\n\\n\\n 17\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4380192/\", \"author_raw\": \"DUNCAN, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"MOTZ"},"judge2":{"kind":"string","value":"DUNCAN"},"judge3":{"kind":"string","value":"QUATTLEBAUM"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"MOTZ\": \", Circuit\", \"DUNCAN\": \", Circuit\", \"QUATTLEBAUM\": \", Circuit\"}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4602939/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Howard Duncan v. William Barr\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-03-22\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 17-2423\n\n\nHOWARD EGBA DUNCAN, JR., a/k/a Duncan Egbaf, a/k/a Howard Duncan,\n\n Petitioner,\n\nv.\n\nWILLIAM P. BARR, Attorney General,\n\n Respondent.\n\n\nOn Petition for Review of an Order of the Board of Immigration Appeals.\n\n\nArgued: November 1, 2018 Decided: March 19, 2019\n Amended: March 22, 2019\n\n\nBefore MOTZ, DUNCAN and QUATTLEBAUM, Circuit Judges.\n\n\nPetition for review granted; remanded for further proceedings by published opinion.\nJudge Duncan wrote the opinion, in which Judge Motz and Judge Quattlebaum\nconcurred.\n\n\nARGUED: Michael S. DePrince, PEPPER HAMILTON LLP, Philadelphia,\nPennsylvania, for Petitioner. Lindsay Donahue, UNITED STATES DEPARTMENT OF\nJUSTICE, Washington, D.C., for Respondent. ON BRIEF: Anthony Vale, Kate A.\nMahoney, PEPPER HAMILTON LLP, Philadelphia, Pennsylvania; Michelle N. Mendez,\nCATHOLIC LEGAL IMMIGRATION NETWORK, INC., Silver Spring, Maryland;\nHimedes V. Chicas, LAW OFFICES OF JEZIC & MOYSE, LLC, Silver Spring,\nMaryland, for Petitioner. Chad A. Readler, Acting Assistant Attorney General, Kiley\nKane, Senior Litigation Counsel, Office of Immigration Litigation, Civil Division,\n\fUNITED STATES DEPARTMENT OF JUSTICE, Washington, D.C., for Respondent.\n\n\n\n\n 2\n\fDUNCAN, Circuit Judge:\n\n After submitting an unsuccessful application for a certificate of citizenship with\n\nthe United States Citizenship and Immigration Services (the “USCIS”), Howard Egba\n\nDuncan, Jr. was placed in removal proceedings. Duncan applied for relief under the\n\nUnited Nations Convention against Torture and Other Cruel, Inhuman or Degrading\n\nTreatment or Punishment (the “CAT”), 8 C.F.R. § 1208.16(c), and also moved to\n\nterminate the proceedings on the basis that he had derived citizenship from his father\n\nunder the Child Citizenship Act of 2000 (the “CCA”), 8 U.S.C. §§ 1431–33. The\n\nimmigration judge (the “IJ”) determined that Duncan had failed to demonstrate the\n\nrequisite governmental acquiescence for relief under the CAT and that he had not derived\n\ncitizenship under the CCA because he was not in the “physical custody” of his father\n\nduring the requisite time period. The Board of Immigration Appeals (the “BIA”)\n\naffirmed on both grounds, finding that the IJ did not clearly err in reaching either\n\nconclusion.\n\n We are compelled to find that the BIA applied the wrong standard of review as to\n\nboth determinations. Consistent with precedent established since the BIA’s decision, we\n\nhold that whether the government would acquiesce to torture under the CAT is a mixed\n\nquestion of fact and law. Similar analysis persuades us that whether Duncan was in the\n\n“physical custody” of his father under the CCA is likewise a mixed question of fact and\n\nlaw. While the IJ’s findings of fact are subject to clear error review, the application of\n\nthose facts to the relevant legal standards constitute legal judgments subject to de novo\n\nreview by the BIA. Accordingly, we grant the petition for review and remand to the BIA.\n\n 3\n\f I.\n\n Duncan is a legal permanent resident of the United States who was born in Nigeria\n\nto a Nigerian mother and an American father. When Duncan was six years old, he and\n\nhis grandmother moved from Nigeria to the United States to live with Duncan’s father.\n\nDuncan lived with his father and grandmother for three months before his father was\n\nincarcerated in April 1998. A few months later, Duncan’s grandmother filed a petition to\n\nbecome Duncan’s guardian, which was granted later that year. Duncan’s father remained\n\nincarcerated until 2011, two years after Duncan’s eighteenth birthday.\n\n Throughout his father’s incarceration, Duncan and his father had limited physical\n\ncontact with one another; Duncan visited his father approximately once a month and the\n\ntwo talked on the phone several times a week. Though Duncan’s father provided some\n\nfinancial support to Duncan and remained involved in certain aspects of his upbringing--\n\ne.g., deciding where he went to school, what shoes his grandmother could purchase for\n\nhim, and whether he would play football--Duncan’s grandmother acted as his primary\n\ncaretaker, driving him to and from school and providing him shelter, clothing, and\n\nconsistent financial support.\n\n Prior to the instant removal proceedings and before his eighteenth birthday,\n\nDuncan applied for a certificate of citizenship on July 14, 2009. His application was\n\ndenied in March 2010. Duncan appealed the denial of his application, which the\n\nAdministrative Appeals Office (the “AAO”) affirmed in February 2015, finding that\n\n\n\n 4\n\fDuncan failed to establish that he was in the “legal custody” or “physical custody” of his\n\nfather because he did not reside with his father during the relevant period. 1\n\n After Duncan’s appeal was denied, the government initiated removal proceedings\n\nagainst him pursuant to 8 U.S.C. § 1227(a)(2) based on his convictions for four crimes\n\ncommitted between October 2008 and January 2011. The government charged three\n\ngrounds of removability: (1) his conviction of a crime of violence under 18 U.S.C. § 16,\n\nwhich was an aggravated felony; (2) his conviction of two crimes involving moral\n\nturpitude that did not arise from a single scheme; and (3) his conviction for a firearm\n\noffense.\n\n Duncan moved to terminate the proceedings on the basis that he was not\n\nremovable because he had derived citizenship through his father under the CCA. As a\n\ncitizen, he would not be removable from the United States under § 1227(a)(2), which\n\nonly applies to aliens. Ojo v. Lynch, 813 F.3d 533, 535 (4th Cir. 2016).\n\n Under the CCA, a child born outside the United States automatically becomes a\n\ncitizen where (1) the child has at least one parent that is a citizen of the United States,\n\neither by birth or naturalization; (2) the child is under eighteen years old; and (3) the child\n\nresides in the United States in the legal and physical custody of the citizen parent.\n\n8 U.S.C. § 1431(a). Neither party disputed before the IJ that Duncan satisfies the first\n\n 1\n Neither party contends that the AAO’s decision was binding or dispositive as to\nDuncan’s derivative citizenship claim before the IJ, the BIA, or this court. Instead, as the\nIJ recognized in its decision, where a respondent is claiming derivative citizenship in\nremoval proceedings and such claim “has reasonable support, it cannot be rejected\narbitrarily.” J.A. 180 (quoting Matter of Tijerina-Villarreal, 13 I&N Dec. 327, 331 (BIA\n1969)).\n\n 5\n\ftwo requirements. Rather, they disagreed as to whether Duncan was in the “legal\n\ncustody” and “physical custody” of his father during the relevant period--from February\n\n27, 2001, when the CCA was enacted, to October 17, 2009, when Duncan turned\n\neighteen years old--given that his father was incarcerated. See 8 C.F.R. § 320.2\n\n(providing that the requirements of the CCA must “have been met after February 26,\n\n2001”).\n\n Following an evidentiary hearing at which Duncan and his father testified, the IJ\n\ndetermined that Duncan had not derived citizenship from his father because he was not in\n\nthe “physical custody” of his father during the relevant period. 2 In reaching this\n\nconclusion, the IJ reasoned that Duncan was not in the physical care of his father and that\n\nhis father did not personally supervise him or make day-to-day decisions over his\n\nwelfare. The IJ did not address whether Duncan satisfied the legal custody requirement\n\nunder § 1431(a). Consequently, the IJ held that Duncan was removable and denied his\n\nsubsequent motion to reconsider.\n\n In addition to his derivative citizenship claim, Duncan applied for cancellation of\n\nremoval, which the IJ denied. Namely, the IJ found that because Duncan had been\n\nconvicted of an aggravated felony, he was disqualified from receiving cancellation of\n\nremoval.\n\n\n\n\n 2\n Neither party disputes that the IJ properly identified Maryland--where Duncan\nresided during the relevant period--as the state whose law governed the physical custody\ninquiry under the CCA.\n\n 6\n\f Duncan also applied for relief under the CAT. Under the CAT’s implementing\n\nregulations, relief is authorized when an individual demonstrates that it is more likely\n\nthan not that “he or she would be tortured if removed to the proposed country of\n\nremoval.” 8 C.F.R. § 1208.16(c)(2). To satisfy this standard, a petitioner is required to\n\nmake two distinct showings. Turkson v. Holder, 667 F.3d 523, 526 (4th Cir. 2012)\n\n(citing 8 C.F.R. § 208.16(c)(2)). First, the petitioner must demonstrate that it is more\n\nlikely than not that he will be tortured if removed. Second, the petitioner must show that\n\nsuch mistreatment “will occur at the hands of government or with the consent or\n\nacquiescence of government.” Id. at 526. While the IJ found Duncan credible, the IJ\n\ndenied him CAT relief on the basis that he had not met his burden of proving either that it\n\nwas more likely than not that he would be tortured if removed to Nigeria or that such\n\ntorture would be by or with the consent or acquiescence of public officials.\n\n Duncan appealed the IJ’s removal order to the BIA. In a single-member decision,\n\nthe BIA dismissed his appeal. Affirming the IJ’s determination that Duncan is ineligible\n\nfor CAT relief, the BIA concluded that the IJ “did not clearly err in finding that the\n\ntorture [Duncan] fears would not come at the hands of a public official or with the\n\nacquiescence of those officials.” 3 J.A. 353. The BIA also found that the IJ “did not\n\nclearly err in finding that [Duncan’s] father did not have physical custody of the\n\nrespondent during the relevant time period” and affirmed the IJ’s determination that\n\n\n 3\n The BIA declined to reach the IJ’s determination that Duncan would not likely\nbe subject to torture under the CAT.\n\n\n 7\n\fDuncan did not derive citizenship from his father under the CCA. J.A. 351. Like the IJ,\n\nthe BIA did not address whether Duncan was in the “legal custody” of his father during\n\nthe relevant time period. 4 This appeal followed.\n\n\n\n II.\n\n Duncan challenges the BIA’s denial of his request for relief under the CAT and its\n\nrejection of his derivative citizenship claim. Specifically, he argues that the BIA applied\n\nthe wrong standard of review when it affirmed both of the IJ’s determinations, which the\n\nBIA concluded were pure questions of fact and accordingly reviewed for clear error.\n\nWhether the BIA has applied the proper standard of review is a question of law for\n\npurposes of our jurisdiction under 8 U.S.C. § 1252(a)(2)(D), which we review de novo.\n\nUpatcha v. Sessions, 849 F.3d 181, 184 (4th Cir. 2017).\n\n For the reasons that follow, we conclude that the BIA incorrectly reviewed the IJ’s\n\ndeterminations--government acquiescence under the CAT and “physical custody” under\n\nthe CCA--for clear error. We therefore grant Duncan’s petition for review and remand to\n\n\n\n\n 4\n Accordingly, we do not reach the question of whether Duncan was in the “legal\ncustody” of his father during the relevant time period. On remand, however, depending\non the BIA’s determinations, it may be necessary for the BIA to address both whether\nDuncan was in his father’s “physical custody” and “legal custody” pursuant to 8 U.S.C.\n§ 1431(a).\n\n\n 8\n\fthe BIA for application of the correct standard of review. 5 We address Duncan’s claims\n\nunder the CAT and the CCA in turn.\n\n\n\n A.\n\n Duncan first argues that the BIA applied the wrong standard of review in\n\naffirming the IJ’s determination that he is ineligible for relief under the CAT.\n\nSpecifically, he argues that the BIA should have reviewed the IJ’s determination de novo\n\nrather than for clear error.\n\n We recently addressed this issue in Cruz-Quintanilla v. Whitaker, 914 F.3d 884\n\n(4th Cir. 2019), which binds us here. There, we held that the government acquiescence\n\ndetermination under the CAT is a mixed question of fact and law and that an IJ’s\n\n“determination that the evidence did not meet the relevant standard is a legal judgment\n\nsubject to de novo review by the [BIA].” Id. at 885.\n\n Here, neither party disputes that the BIA reviewed the IJ’s determination that\n\nDuncan did not establish a likelihood of government acquiescence for clear error rather\n\nthan de novo. Accordingly, we remand Duncan’s CAT claim so that the BIA may apply\n\nthe correct standard of review.\n\n\n\n\n 5\n We therefore do not reach the question of whether one of Duncan’s convictions\nconstitutes an aggravated felony and, accordingly whether he is eligible for cancellation\nof removal, in light of the Supreme Court’s ruling in Sessions v. Dimaya, 138 S. Ct. 1204\n(2018)--a question that the government concedes should be remanded to the BIA to\nconsider, having declined to reach it previously.\n\n 9\n\f B.\n\n Next, Duncan argues that the BIA applied the wrong standard of review in\n\naffirming the IJ’s determination that he has not derived citizenship from his father under\n\nthe CCA such that he cannot be removed. Namely, he contends that the BIA erred in\n\napplying clear error review to the question of whether he was in the “physical custody” of\n\nhis father under the CCA. As this question is a matter of first impression before the\n\ncourt, we first address the relevant regulations dictating the BIA’s standards of review of\n\nIJ decisions.\n\n The BIA’s review of an IJ’s decisions is governed by 8 C.F.R. § 1003.1(d)(3).\n\nPrior to 2002, the regulations provided for de novo review by the BIA over all aspects of\n\nIJ decisions. Subsequently, however, new regulations established a standard of review\n\nunder which the BIA reviews findings of fact for clear error. 8 C.F.R. § 1003.1(d)(3)(i).\n\nBut the BIA reviews de novo “all other issues,” id. § 1003.1(d)(3)(ii), “including, in cases\n\ninvolving mixed questions of law and fact, the application of the governing legal standard\n\nto the facts found by the immigration judge.” Cruz-Quintanilla, 914 F.3d at 889 (internal\n\ncitation omitted).\n\n Guided by our precedent in similar contexts, we conclude that whether an\n\nindividual was in the “physical custody” of a parent under the CCA is a mixed question\n\nof fact and law. We first review the analysis in those cases and then turn to the question\n\nof the applicability of that analysis to the physical custody determination under the CCA.\n\n\n\n i.\n\n 10\n\f Mixed questions of fact and law require a review of two determinations--what the\n\nfacts were in a particular case, and the legal conclusions to which those facts lead.\n\nTurkson, 667 F.3d at 527. The IJ’s determination of “what happened” is by its nature a\n\nfactual finding giving rise to review for clear error by the BIA. See Upatcha, 849 F.3d at\n\n185. But applying the relevant legal standard to those facts and deciding whether that\n\nstandard was met is a legal judgment subject to de novo review. Id.\n\n We have approached similar IJ determinations as a two-step inquiry, requiring the\n\nBIA to review an IJ’s factual findings for clear error and its application of the appropriate\n\nlegal standard de novo. In Turkson v. Holder, for example, we held that whether a\n\npetitioner would be subject to torture within the meaning of the CAT is a mixed question\n\nof fact and law. 667 F.3d at 529. The BIA reviews for clear error the IJ’s factual\n\nfindings as to what would happen to the petitioner upon removal. But the BIA reviews\n\nde novo the IJ’s legal conclusion as to whether this future mistreatment amounts to\n\n“torture,” which is “a term of art under the CAT . . . with a specific legal definition.” Id.\n\nat 526, 530. Put another way, although the BIA defers to the IJ’s findings of historical\n\nfacts and the likelihood that they would occur in the future, the BIA “exercise[s] its\n\nindependent judgment to evaluate . . . the legal significance of the facts” as well as “the\n\nultimate conclusions to which those facts lead.” Id. at 527. We later held that the same\n\nstandard of review applies to the question of whether the government would acquiesce to\n\nsuch torture under the CAT, as discussed supra. Cruz-Quintanilla, 914 F.3d at 885.\n\n Similarly, in Upatcha we held that whether a petitioner entered into a good faith\n\nmarriage under 8 U.S.C. § 1186a(c)(4)(B) is a mixed question of fact and law. 849 F.3d\n\n 11\n\fat 184; see Massis v. Mukasey, 549 F.3d 631, 636 n.6 (4th Cir. 2008) (explaining that the\n\nBIA reviews the IJ’s factual findings of what happened to an individual for clear error,\n\nbut reviews de novo the “application of the law to . . . facts--to determine, for example,\n\nwhether those facts amount to ‘exceptional and extremely unusual hardship’” (citation\n\nomitted). The IJ’s factual determinations--such as the petitioner’s credibility and the\n\ndegree to which the couple’s finances were intermingled--are subject to clear error\n\nreview. In contrast, the IJ’s ultimate legal judgment--determining whether the\n\npetitioner’s marriage satisfies the good faith standard under 8 U.S.C. § 1186a(c)(4)(B)--is\n\nsubject to de novo review. Upatcha, 849 F.3d at 185.\n\n Applying these same analytical steps, as set out below, we conclude that whether a\n\nforeign-born child was in the “physical custody” of her citizen parent under the CCA is a\n\nmixed question of fact and law. It requires the IJ first to determine the specific, relevant\n\nfacts of the parent-child relationship and then to assess, on the basis of those facts,\n\nwhether the parent had “physical custody” over the child as a legal matter. 6\n\n\n\n ii.\n\n The analytical steps that the IJ must take in determining whether a child was in the\n\n“physical custody” of her parent under the CCA underscore our conclusion that this\n\ndetermination is necessarily a mixed question. Under the CCA, a child born outside of\n\n 6\n We note that the Sixth Circuit has stated, without explaining, that “[t]he IJ’s\nruling that [the] petitioner . . . did not reside in his citizen father’s physical custody at the\ntime of his naturalization or at any time thereafter is a factual finding.” Karimijanaki v.\nHolder, 579 F.3d 710, 721 (6th Cir. 2009).\n\n 12\n\fthe United States automatically becomes a citizen when, inter alia, the child is residing in\n\nthe United States in the “physical custody of the citizen parent.” 8 U.S.C. § 1431(a)(3).\n\nCongress has not defined “physical custody” in the CCA or its accompanying\n\nregulations. Rather, “it has long been a hallmark of our federalism principles that full\n\nauthority over domestic-relations matters resides not in the national government, but in\n\nthe several States.” Ojo, 813 F.3d at 540 (citing Ex parte Burrus, 136 U.S. 586, 593–94\n\n(1890)).\n\n In the absence of a federal definition, and because both the Supreme Court and our\n\nown cases look to state law to determine legal relationships in the family context, we turn\n\nto state law to determine the meaning of “physical custody” under the CCA. See, e.g., De\n\nSylva v. Ballentine, 351 U.S. 570, 580 (1956) (turning to state law to discern whether an\n\nillegitimate child is included within the term “children” as used in the Copyright Act,\n\nreasoning that “there is no federal law of domestic relations, which is primarily a matter\n\nof state concern”). 7\n\n “Physical custody” under the CCA therefore presumptively means “physical\n\ncustody” as defined under the law of the state in question--in this case, Maryland. Which\n\nstate law governs the CCA’s physical custody determination is significant because states\n\n\n 7\n Indeed, in the absence of a definition of the term “adoption” under the CCA, we\nhave looked to state law instruments to determine when an individual was adopted for\npurposes of deriving citizenship under the statute. Ojo, 813 F.3d at 539–41 (“[I]f\nCongress had intended a modified definition of the term ‘adopted’ for purposes of federal\nimmigration law and sought to place the interpretation thereof in the hands of an\nadministrative agency, such as the BIA, Congress would have made that intention\n‘unmistakably clear.’”) (citing Gregory v. Ashcroft, 501 U.S. 452, 460 (1991)).\n\n 13\n\fhave appeared to adopt different approaches to determining physical custody, and the\n\nsame set of facts may result in different legal outcomes depending upon where they\n\noccur.\n\n Accordingly, for the limited purpose of illustrating why the CCA’s physical\n\ncustody inquiry is necessarily a mixed question of fact and law, we find it helpful to\n\ncontrast two states’ approaches--that of Montana and Nevada. However, we clarify that\n\nin doing so, we take no position as to whether the physical presence of a parent is\n\nnecessary for that parent to have physical custody of her child under either state’s law,\n\nnor under the law of Maryland.\n\n We begin with the example of the physical custody inquiry under Montana law.\n\nMontana recognizes that a parent’s right to custody of her child “is a fundamental,\n\nconstitutionally protected right.” Girard v. Williams, 966 P.2d 1155, 1158–59 (Mont.\n\n1998). Regarding physical custody in particular, the Montana Supreme Court has held\n\nthat such custody “is not limited to having actual, immediate control of the physical\n\npresence of the child. Rather, this phrase relates to the custodial rights involved in the\n\ncare and control of the child.” Henderson v. Henderson, 568 P.2d 177, 179 (Mont.\n\n1977). Indeed, that court has held that a parent who had been incarcerated for five years\n\ndid not voluntarily relinquish his right to physical custody “when considered in\n\nconjunction with his actions to maintain contact with his children.” Girard, 966 P.2d at\n\n1164–65 (holding that nonparents lacked standing to pursue a custodial claim where they\n\nfailed to show that the children were not in the physical custody of their parent).\n\n\n\n 14\n\f In contrast, it appears that Nevada requires a parent to reside with a child as a\n\ncomponent of physical custody. See Rivero v. Rivero, 216 P.3d 213, 222 (Nev. 2009)\n\n(“Physical custody involves the time that a child physically spends in the care of a parent.\n\nDuring this time, the child resides with the parent and that parent provides supervision for\n\nthe child and makes the day-to-day decisions regarding the child.”).\n\n Consequently, the same facts may nonetheless lead an IJ to conclude that a parent\n\nhas physical custody over her child under one state’s laws but not another’s. Take, for\n\nexample, a child who resides with one parent during the school year and with the other\n\nduring the summer vacation months. In Montana, it would appear that both parents retain\n\nphysical custody over the child throughout the entire year. In other words, the parent\n\nwith whom the child resides during the summer is not divested of her physical custody\n\nover the child during the school year, when the child resides with the other parent. See In\n\nre Marriage of Susen, 788 P.2d 332, 334 (Mont. 1990) (affirming an award of joint legal\n\nand physical custody where the parents live in separate states and the court imposed a\n\nsummer and school year schedule). In contrast, in Nevada it appears that only the parent\n\nwith whom the child physically resides at the time has custody of the child--meaning that\n\nthe parent with whom the child resides in the summer has physical custody only during\n\nthe summer. See Bluestein v. Bluestein, 345 P.3d 1044, 1048 (Nev. 2015) (observing that\n\nas a general matter, where a child resides with each parent “at least 40 percent of the\n\n\n\n\n 15\n\ftime, equal to at least 146 days over one calendar year, the parents share[] joint physical\n\ncustody”); Rivero, 216 P.3d at 222. 8\n\n In sum, we conclude that the physical custody determination under the CCA\n\nrequires a bifurcated approach. While the IJ’s findings of fact are subject to clear error\n\nreview, the IJ’s application of the facts to the relevant state law in determining whether\n\nan individual satisfies the physical custody requirement under § 1431(a) is a legal\n\njudgment subject to de novo review by the BIA. Accordingly, we find that the BIA erred\n\nin reviewing for clear error the IJ’s legal judgment as to whether, pursuant to Maryland\n\nlaw, Duncan satisfied the CCA’s physical custody requirement. Because the BIA applied\n\nthe wrong standard of review to this determination, we remand. Should the BIA resolve\n\nthe physical custody determination in Duncan’s favor, it must also address whether or not\n\nDuncan was in his father’s “legal custody” as the statute so requires for purposes of\n\nderivative citizenship. 8 U.S.C. § 1431(a).\n\n\n\n III.\n\n For the foregoing reasons, we grant Duncan’s petition for review and remand the\n\ncase to the BIA for further proceedings consistent with this opinion.\n\n 8\n We emphasize that we make no holding regarding the application of Montana or\nNevada law to the CCA’s physical custody requirement. Indeed, the tensions between\nstate law defining custodial rights prospectively in context of divorce proceedings on the\none hand, and the retroactive application of those definitions to evaluate parent-child\nrelationships for purposes of the CCA on the other, may complicate any attempt to assess\nphysical custody as a simple factual matter. However, we need not reach those issues\nhere.\n\n\n 16\n\f PETITION FOR REVIEW GRANTED;\nREMANDED FOR FURTHER PROCEEDINGS\n\n\n\n\n 17\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Howard Duncan v. William Barr\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-03-22\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 17-2423\\n\\n\\nHOWARD EGBA DUNCAN, JR., a/k/a Duncan Egbaf, a/k/a Howard Duncan,\\n\\n Petitioner,\\n\\nv.\\n\\nWILLIAM P. BARR, Attorney General,\\n\\n Respondent.\\n\\n\\nOn Petition for Review of an Order of the Board of Immigration Appeals.\\n\\n\\nArgued: November 1, 2018 Decided: March 19, 2019\\n Amended: March 22, 2019\\n\\n\\nBefore MOTZ, DUNCAN and QUATTLEBAUM, Circuit Judges.\\n\\n\\nPetition for review granted; remanded for further proceedings by published opinion.\\nJudge Duncan wrote the opinion, in which Judge Motz and Judge Quattlebaum\\nconcurred.\\n\\n\\nARGUED: Michael S. DePrince, PEPPER HAMILTON LLP, Philadelphia,\\nPennsylvania, for Petitioner. Lindsay Donahue, UNITED STATES DEPARTMENT OF\\nJUSTICE, Washington, D.C., for Respondent. ON BRIEF: Anthony Vale, Kate A.\\nMahoney, PEPPER HAMILTON LLP, Philadelphia, Pennsylvania; Michelle N. Mendez,\\nCATHOLIC LEGAL IMMIGRATION NETWORK, INC., Silver Spring, Maryland;\\nHimedes V. Chicas, LAW OFFICES OF JEZIC & MOYSE, LLC, Silver Spring,\\nMaryland, for Petitioner. Chad A. Readler, Acting Assistant Attorney General, Kiley\\nKane, Senior Litigation Counsel, Office of Immigration Litigation, Civil Division,\\n\\fUNITED STATES DEPARTMENT OF JUSTICE, Washington, D.C., for Respondent.\\n\\n\\n\\n\\n 2\\n\\fDUNCAN, Circuit Judge:\\n\\n After submitting an unsuccessful application for a certificate of citizenship with\\n\\nthe United States Citizenship and Immigration Services (the “USCIS”), Howard Egba\\n\\nDuncan, Jr. was placed in removal proceedings. Duncan applied for relief under the\\n\\nUnited Nations Convention against Torture and Other Cruel, Inhuman or Degrading\\n\\nTreatment or Punishment (the “CAT”), 8 C.F.R. § 1208.16(c), and also moved to\\n\\nterminate the proceedings on the basis that he had derived citizenship from his father\\n\\nunder the Child Citizenship Act of 2000 (the “CCA”), 8 U.S.C. §§ 1431–33. The\\n\\nimmigration judge (the “IJ”) determined that Duncan had failed to demonstrate the\\n\\nrequisite governmental acquiescence for relief under the CAT and that he had not derived\\n\\ncitizenship under the CCA because he was not in the “physical custody” of his father\\n\\nduring the requisite time period. The Board of Immigration Appeals (the “BIA”)\\n\\naffirmed on both grounds, finding that the IJ did not clearly err in reaching either\\n\\nconclusion.\\n\\n We are compelled to find that the BIA applied the wrong standard of review as to\\n\\nboth determinations. Consistent with precedent established since the BIA’s decision, we\\n\\nhold that whether the government would acquiesce to torture under the CAT is a mixed\\n\\nquestion of fact and law. Similar analysis persuades us that whether Duncan was in the\\n\\n“physical custody” of his father under the CCA is likewise a mixed question of fact and\\n\\nlaw. While the IJ’s findings of fact are subject to clear error review, the application of\\n\\nthose facts to the relevant legal standards constitute legal judgments subject to de novo\\n\\nreview by the BIA. Accordingly, we grant the petition for review and remand to the BIA.\\n\\n 3\\n\\f I.\\n\\n Duncan is a legal permanent resident of the United States who was born in Nigeria\\n\\nto a Nigerian mother and an American father. When Duncan was six years old, he and\\n\\nhis grandmother moved from Nigeria to the United States to live with Duncan’s father.\\n\\nDuncan lived with his father and grandmother for three months before his father was\\n\\nincarcerated in April 1998. A few months later, Duncan’s grandmother filed a petition to\\n\\nbecome Duncan’s guardian, which was granted later that year. Duncan’s father remained\\n\\nincarcerated until 2011, two years after Duncan’s eighteenth birthday.\\n\\n Throughout his father’s incarceration, Duncan and his father had limited physical\\n\\ncontact with one another; Duncan visited his father approximately once a month and the\\n\\ntwo talked on the phone several times a week. Though Duncan’s father provided some\\n\\nfinancial support to Duncan and remained involved in certain aspects of his upbringing--\\n\\ne.g., deciding where he went to school, what shoes his grandmother could purchase for\\n\\nhim, and whether he would play football--Duncan’s grandmother acted as his primary\\n\\ncaretaker, driving him to and from school and providing him shelter, clothing, and\\n\\nconsistent financial support.\\n\\n Prior to the instant removal proceedings and before his eighteenth birthday,\\n\\nDuncan applied for a certificate of citizenship on July 14, 2009. His application was\\n\\ndenied in March 2010. Duncan appealed the denial of his application, which the\\n\\nAdministrative Appeals Office (the “AAO”) affirmed in February 2015, finding that\\n\\n\\n\\n 4\\n\\fDuncan failed to establish that he was in the “legal custody” or “physical custody” of his\\n\\nfather because he did not reside with his father during the relevant period. 1\\n\\n After Duncan’s appeal was denied, the government initiated removal proceedings\\n\\nagainst him pursuant to 8 U.S.C. § 1227(a)(2) based on his convictions for four crimes\\n\\ncommitted between October 2008 and January 2011. The government charged three\\n\\ngrounds of removability: (1) his conviction of a crime of violence under 18 U.S.C. § 16,\\n\\nwhich was an aggravated felony; (2) his conviction of two crimes involving moral\\n\\nturpitude that did not arise from a single scheme; and (3) his conviction for a firearm\\n\\noffense.\\n\\n Duncan moved to terminate the proceedings on the basis that he was not\\n\\nremovable because he had derived citizenship through his father under the CCA. As a\\n\\ncitizen, he would not be removable from the United States under § 1227(a)(2), which\\n\\nonly applies to aliens. Ojo v. Lynch, 813 F.3d 533, 535 (4th Cir. 2016).\\n\\n Under the CCA, a child born outside the United States automatically becomes a\\n\\ncitizen where (1) the child has at least one parent that is a citizen of the United States,\\n\\neither by birth or naturalization; (2) the child is under eighteen years old; and (3) the child\\n\\nresides in the United States in the legal and physical custody of the citizen parent.\\n\\n8 U.S.C. § 1431(a). Neither party disputed before the IJ that Duncan satisfies the first\\n\\n 1\\n Neither party contends that the AAO’s decision was binding or dispositive as to\\nDuncan’s derivative citizenship claim before the IJ, the BIA, or this court. Instead, as the\\nIJ recognized in its decision, where a respondent is claiming derivative citizenship in\\nremoval proceedings and such claim “has reasonable support, it cannot be rejected\\narbitrarily.” J.A. 180 (quoting Matter of Tijerina-Villarreal, 13 I&N Dec. 327, 331 (BIA\\n1969)).\\n\\n 5\\n\\ftwo requirements. Rather, they disagreed as to whether Duncan was in the “legal\\n\\ncustody” and “physical custody” of his father during the relevant period--from February\\n\\n27, 2001, when the CCA was enacted, to October 17, 2009, when Duncan turned\\n\\neighteen years old--given that his father was incarcerated. See 8 C.F.R. § 320.2\\n\\n(providing that the requirements of the CCA must “have been met after February 26,\\n\\n2001”).\\n\\n Following an evidentiary hearing at which Duncan and his father testified, the IJ\\n\\ndetermined that Duncan had not derived citizenship from his father because he was not in\\n\\nthe “physical custody” of his father during the relevant period. 2 In reaching this\\n\\nconclusion, the IJ reasoned that Duncan was not in the physical care of his father and that\\n\\nhis father did not personally supervise him or make day-to-day decisions over his\\n\\nwelfare. The IJ did not address whether Duncan satisfied the legal custody requirement\\n\\nunder § 1431(a). Consequently, the IJ held that Duncan was removable and denied his\\n\\nsubsequent motion to reconsider.\\n\\n In addition to his derivative citizenship claim, Duncan applied for cancellation of\\n\\nremoval, which the IJ denied. Namely, the IJ found that because Duncan had been\\n\\nconvicted of an aggravated felony, he was disqualified from receiving cancellation of\\n\\nremoval.\\n\\n\\n\\n\\n 2\\n Neither party disputes that the IJ properly identified Maryland--where Duncan\\nresided during the relevant period--as the state whose law governed the physical custody\\ninquiry under the CCA.\\n\\n 6\\n\\f Duncan also applied for relief under the CAT. Under the CAT’s implementing\\n\\nregulations, relief is authorized when an individual demonstrates that it is more likely\\n\\nthan not that “he or she would be tortured if removed to the proposed country of\\n\\nremoval.” 8 C.F.R. § 1208.16(c)(2). To satisfy this standard, a petitioner is required to\\n\\nmake two distinct showings. Turkson v. Holder, 667 F.3d 523, 526 (4th Cir. 2012)\\n\\n(citing 8 C.F.R. § 208.16(c)(2)). First, the petitioner must demonstrate that it is more\\n\\nlikely than not that he will be tortured if removed. Second, the petitioner must show that\\n\\nsuch mistreatment “will occur at the hands of government or with the consent or\\n\\nacquiescence of government.” Id. at 526. While the IJ found Duncan credible, the IJ\\n\\ndenied him CAT relief on the basis that he had not met his burden of proving either that it\\n\\nwas more likely than not that he would be tortured if removed to Nigeria or that such\\n\\ntorture would be by or with the consent or acquiescence of public officials.\\n\\n Duncan appealed the IJ’s removal order to the BIA. In a single-member decision,\\n\\nthe BIA dismissed his appeal. Affirming the IJ’s determination that Duncan is ineligible\\n\\nfor CAT relief, the BIA concluded that the IJ “did not clearly err in finding that the\\n\\ntorture [Duncan] fears would not come at the hands of a public official or with the\\n\\nacquiescence of those officials.” 3 J.A. 353. The BIA also found that the IJ “did not\\n\\nclearly err in finding that [Duncan’s] father did not have physical custody of the\\n\\nrespondent during the relevant time period” and affirmed the IJ’s determination that\\n\\n\\n 3\\n The BIA declined to reach the IJ’s determination that Duncan would not likely\\nbe subject to torture under the CAT.\\n\\n\\n 7\\n\\fDuncan did not derive citizenship from his father under the CCA. J.A. 351. Like the IJ,\\n\\nthe BIA did not address whether Duncan was in the “legal custody” of his father during\\n\\nthe relevant time period. 4 This appeal followed.\\n\\n\\n\\n II.\\n\\n Duncan challenges the BIA’s denial of his request for relief under the CAT and its\\n\\nrejection of his derivative citizenship claim. Specifically, he argues that the BIA applied\\n\\nthe wrong standard of review when it affirmed both of the IJ’s determinations, which the\\n\\nBIA concluded were pure questions of fact and accordingly reviewed for clear error.\\n\\nWhether the BIA has applied the proper standard of review is a question of law for\\n\\npurposes of our jurisdiction under 8 U.S.C. § 1252(a)(2)(D), which we review de novo.\\n\\nUpatcha v. Sessions, 849 F.3d 181, 184 (4th Cir. 2017).\\n\\n For the reasons that follow, we conclude that the BIA incorrectly reviewed the IJ’s\\n\\ndeterminations--government acquiescence under the CAT and “physical custody” under\\n\\nthe CCA--for clear error. We therefore grant Duncan’s petition for review and remand to\\n\\n\\n\\n\\n 4\\n Accordingly, we do not reach the question of whether Duncan was in the “legal\\ncustody” of his father during the relevant time period. On remand, however, depending\\non the BIA’s determinations, it may be necessary for the BIA to address both whether\\nDuncan was in his father’s “physical custody” and “legal custody” pursuant to 8 U.S.C.\\n§ 1431(a).\\n\\n\\n 8\\n\\fthe BIA for application of the correct standard of review. 5 We address Duncan’s claims\\n\\nunder the CAT and the CCA in turn.\\n\\n\\n\\n A.\\n\\n Duncan first argues that the BIA applied the wrong standard of review in\\n\\naffirming the IJ’s determination that he is ineligible for relief under the CAT.\\n\\nSpecifically, he argues that the BIA should have reviewed the IJ’s determination de novo\\n\\nrather than for clear error.\\n\\n We recently addressed this issue in Cruz-Quintanilla v. Whitaker, 914 F.3d 884\\n\\n(4th Cir. 2019), which binds us here. There, we held that the government acquiescence\\n\\ndetermination under the CAT is a mixed question of fact and law and that an IJ’s\\n\\n“determination that the evidence did not meet the relevant standard is a legal judgment\\n\\nsubject to de novo review by the [BIA].” Id. at 885.\\n\\n Here, neither party disputes that the BIA reviewed the IJ’s determination that\\n\\nDuncan did not establish a likelihood of government acquiescence for clear error rather\\n\\nthan de novo. Accordingly, we remand Duncan’s CAT claim so that the BIA may apply\\n\\nthe correct standard of review.\\n\\n\\n\\n\\n 5\\n We therefore do not reach the question of whether one of Duncan’s convictions\\nconstitutes an aggravated felony and, accordingly whether he is eligible for cancellation\\nof removal, in light of the Supreme Court’s ruling in Sessions v. Dimaya, 138 S. Ct. 1204\\n(2018)--a question that the government concedes should be remanded to the BIA to\\nconsider, having declined to reach it previously.\\n\\n 9\\n\\f B.\\n\\n Next, Duncan argues that the BIA applied the wrong standard of review in\\n\\naffirming the IJ’s determination that he has not derived citizenship from his father under\\n\\nthe CCA such that he cannot be removed. Namely, he contends that the BIA erred in\\n\\napplying clear error review to the question of whether he was in the “physical custody” of\\n\\nhis father under the CCA. As this question is a matter of first impression before the\\n\\ncourt, we first address the relevant regulations dictating the BIA’s standards of review of\\n\\nIJ decisions.\\n\\n The BIA’s review of an IJ’s decisions is governed by 8 C.F.R. § 1003.1(d)(3).\\n\\nPrior to 2002, the regulations provided for de novo review by the BIA over all aspects of\\n\\nIJ decisions. Subsequently, however, new regulations established a standard of review\\n\\nunder which the BIA reviews findings of fact for clear error. 8 C.F.R. § 1003.1(d)(3)(i).\\n\\nBut the BIA reviews de novo “all other issues,” id. § 1003.1(d)(3)(ii), “including, in cases\\n\\ninvolving mixed questions of law and fact, the application of the governing legal standard\\n\\nto the facts found by the immigration judge.” Cruz-Quintanilla, 914 F.3d at 889 (internal\\n\\ncitation omitted).\\n\\n Guided by our precedent in similar contexts, we conclude that whether an\\n\\nindividual was in the “physical custody” of a parent under the CCA is a mixed question\\n\\nof fact and law. We first review the analysis in those cases and then turn to the question\\n\\nof the applicability of that analysis to the physical custody determination under the CCA.\\n\\n\\n\\n i.\\n\\n 10\\n\\f Mixed questions of fact and law require a review of two determinations--what the\\n\\nfacts were in a particular case, and the legal conclusions to which those facts lead.\\n\\nTurkson, 667 F.3d at 527. The IJ’s determination of “what happened” is by its nature a\\n\\nfactual finding giving rise to review for clear error by the BIA. See Upatcha, 849 F.3d at\\n\\n185. But applying the relevant legal standard to those facts and deciding whether that\\n\\nstandard was met is a legal judgment subject to de novo review. Id.\\n\\n We have approached similar IJ determinations as a two-step inquiry, requiring the\\n\\nBIA to review an IJ’s factual findings for clear error and its application of the appropriate\\n\\nlegal standard de novo. In Turkson v. Holder, for example, we held that whether a\\n\\npetitioner would be subject to torture within the meaning of the CAT is a mixed question\\n\\nof fact and law. 667 F.3d at 529. The BIA reviews for clear error the IJ’s factual\\n\\nfindings as to what would happen to the petitioner upon removal. But the BIA reviews\\n\\nde novo the IJ’s legal conclusion as to whether this future mistreatment amounts to\\n\\n“torture,” which is “a term of art under the CAT . . . with a specific legal definition.” Id.\\n\\nat 526, 530. Put another way, although the BIA defers to the IJ’s findings of historical\\n\\nfacts and the likelihood that they would occur in the future, the BIA “exercise[s] its\\n\\nindependent judgment to evaluate . . . the legal significance of the facts” as well as “the\\n\\nultimate conclusions to which those facts lead.” Id. at 527. We later held that the same\\n\\nstandard of review applies to the question of whether the government would acquiesce to\\n\\nsuch torture under the CAT, as discussed supra. Cruz-Quintanilla, 914 F.3d at 885.\\n\\n Similarly, in Upatcha we held that whether a petitioner entered into a good faith\\n\\nmarriage under 8 U.S.C. § 1186a(c)(4)(B) is a mixed question of fact and law. 849 F.3d\\n\\n 11\\n\\fat 184; see Massis v. Mukasey, 549 F.3d 631, 636 n.6 (4th Cir. 2008) (explaining that the\\n\\nBIA reviews the IJ’s factual findings of what happened to an individual for clear error,\\n\\nbut reviews de novo the “application of the law to . . . facts--to determine, for example,\\n\\nwhether those facts amount to ‘exceptional and extremely unusual hardship’” (citation\\n\\nomitted). The IJ’s factual determinations--such as the petitioner’s credibility and the\\n\\ndegree to which the couple’s finances were intermingled--are subject to clear error\\n\\nreview. In contrast, the IJ’s ultimate legal judgment--determining whether the\\n\\npetitioner’s marriage satisfies the good faith standard under 8 U.S.C. § 1186a(c)(4)(B)--is\\n\\nsubject to de novo review. Upatcha, 849 F.3d at 185.\\n\\n Applying these same analytical steps, as set out below, we conclude that whether a\\n\\nforeign-born child was in the “physical custody” of her citizen parent under the CCA is a\\n\\nmixed question of fact and law. It requires the IJ first to determine the specific, relevant\\n\\nfacts of the parent-child relationship and then to assess, on the basis of those facts,\\n\\nwhether the parent had “physical custody” over the child as a legal matter. 6\\n\\n\\n\\n ii.\\n\\n The analytical steps that the IJ must take in determining whether a child was in the\\n\\n“physical custody” of her parent under the CCA underscore our conclusion that this\\n\\ndetermination is necessarily a mixed question. Under the CCA, a child born outside of\\n\\n 6\\n We note that the Sixth Circuit has stated, without explaining, that “[t]he IJ’s\\nruling that [the] petitioner . . . did not reside in his citizen father’s physical custody at the\\ntime of his naturalization or at any time thereafter is a factual finding.” Karimijanaki v.\\nHolder, 579 F.3d 710, 721 (6th Cir. 2009).\\n\\n 12\\n\\fthe United States automatically becomes a citizen when, inter alia, the child is residing in\\n\\nthe United States in the “physical custody of the citizen parent.” 8 U.S.C. § 1431(a)(3).\\n\\nCongress has not defined “physical custody” in the CCA or its accompanying\\n\\nregulations. Rather, “it has long been a hallmark of our federalism principles that full\\n\\nauthority over domestic-relations matters resides not in the national government, but in\\n\\nthe several States.” Ojo, 813 F.3d at 540 (citing Ex parte Burrus, 136 U.S. 586, 593–94\\n\\n(1890)).\\n\\n In the absence of a federal definition, and because both the Supreme Court and our\\n\\nown cases look to state law to determine legal relationships in the family context, we turn\\n\\nto state law to determine the meaning of “physical custody” under the CCA. See, e.g., De\\n\\nSylva v. Ballentine, 351 U.S. 570, 580 (1956) (turning to state law to discern whether an\\n\\nillegitimate child is included within the term “children” as used in the Copyright Act,\\n\\nreasoning that “there is no federal law of domestic relations, which is primarily a matter\\n\\nof state concern”). 7\\n\\n “Physical custody” under the CCA therefore presumptively means “physical\\n\\ncustody” as defined under the law of the state in question--in this case, Maryland. Which\\n\\nstate law governs the CCA’s physical custody determination is significant because states\\n\\n\\n 7\\n Indeed, in the absence of a definition of the term “adoption” under the CCA, we\\nhave looked to state law instruments to determine when an individual was adopted for\\npurposes of deriving citizenship under the statute. Ojo, 813 F.3d at 539–41 (“[I]f\\nCongress had intended a modified definition of the term ‘adopted’ for purposes of federal\\nimmigration law and sought to place the interpretation thereof in the hands of an\\nadministrative agency, such as the BIA, Congress would have made that intention\\n‘unmistakably clear.’”) (citing Gregory v. Ashcroft, 501 U.S. 452, 460 (1991)).\\n\\n 13\\n\\fhave appeared to adopt different approaches to determining physical custody, and the\\n\\nsame set of facts may result in different legal outcomes depending upon where they\\n\\noccur.\\n\\n Accordingly, for the limited purpose of illustrating why the CCA’s physical\\n\\ncustody inquiry is necessarily a mixed question of fact and law, we find it helpful to\\n\\ncontrast two states’ approaches--that of Montana and Nevada. However, we clarify that\\n\\nin doing so, we take no position as to whether the physical presence of a parent is\\n\\nnecessary for that parent to have physical custody of her child under either state’s law,\\n\\nnor under the law of Maryland.\\n\\n We begin with the example of the physical custody inquiry under Montana law.\\n\\nMontana recognizes that a parent’s right to custody of her child “is a fundamental,\\n\\nconstitutionally protected right.” Girard v. Williams, 966 P.2d 1155, 1158–59 (Mont.\\n\\n1998). Regarding physical custody in particular, the Montana Supreme Court has held\\n\\nthat such custody “is not limited to having actual, immediate control of the physical\\n\\npresence of the child. Rather, this phrase relates to the custodial rights involved in the\\n\\ncare and control of the child.” Henderson v. Henderson, 568 P.2d 177, 179 (Mont.\\n\\n1977). Indeed, that court has held that a parent who had been incarcerated for five years\\n\\ndid not voluntarily relinquish his right to physical custody “when considered in\\n\\nconjunction with his actions to maintain contact with his children.” Girard, 966 P.2d at\\n\\n1164–65 (holding that nonparents lacked standing to pursue a custodial claim where they\\n\\nfailed to show that the children were not in the physical custody of their parent).\\n\\n\\n\\n 14\\n\\f In contrast, it appears that Nevada requires a parent to reside with a child as a\\n\\ncomponent of physical custody. See Rivero v. Rivero, 216 P.3d 213, 222 (Nev. 2009)\\n\\n(“Physical custody involves the time that a child physically spends in the care of a parent.\\n\\nDuring this time, the child resides with the parent and that parent provides supervision for\\n\\nthe child and makes the day-to-day decisions regarding the child.”).\\n\\n Consequently, the same facts may nonetheless lead an IJ to conclude that a parent\\n\\nhas physical custody over her child under one state’s laws but not another’s. Take, for\\n\\nexample, a child who resides with one parent during the school year and with the other\\n\\nduring the summer vacation months. In Montana, it would appear that both parents retain\\n\\nphysical custody over the child throughout the entire year. In other words, the parent\\n\\nwith whom the child resides during the summer is not divested of her physical custody\\n\\nover the child during the school year, when the child resides with the other parent. See In\\n\\nre Marriage of Susen, 788 P.2d 332, 334 (Mont. 1990) (affirming an award of joint legal\\n\\nand physical custody where the parents live in separate states and the court imposed a\\n\\nsummer and school year schedule). In contrast, in Nevada it appears that only the parent\\n\\nwith whom the child physically resides at the time has custody of the child--meaning that\\n\\nthe parent with whom the child resides in the summer has physical custody only during\\n\\nthe summer. See Bluestein v. Bluestein, 345 P.3d 1044, 1048 (Nev. 2015) (observing that\\n\\nas a general matter, where a child resides with each parent “at least 40 percent of the\\n\\n\\n\\n\\n 15\\n\\ftime, equal to at least 146 days over one calendar year, the parents share[] joint physical\\n\\ncustody”); Rivero, 216 P.3d at 222. 8\\n\\n In sum, we conclude that the physical custody determination under the CCA\\n\\nrequires a bifurcated approach. While the IJ’s findings of fact are subject to clear error\\n\\nreview, the IJ’s application of the facts to the relevant state law in determining whether\\n\\nan individual satisfies the physical custody requirement under § 1431(a) is a legal\\n\\njudgment subject to de novo review by the BIA. Accordingly, we find that the BIA erred\\n\\nin reviewing for clear error the IJ’s legal judgment as to whether, pursuant to Maryland\\n\\nlaw, Duncan satisfied the CCA’s physical custody requirement. Because the BIA applied\\n\\nthe wrong standard of review to this determination, we remand. Should the BIA resolve\\n\\nthe physical custody determination in Duncan’s favor, it must also address whether or not\\n\\nDuncan was in his father’s “legal custody” as the statute so requires for purposes of\\n\\nderivative citizenship. 8 U.S.C. § 1431(a).\\n\\n\\n\\n III.\\n\\n For the foregoing reasons, we grant Duncan’s petition for review and remand the\\n\\ncase to the BIA for further proceedings consistent with this opinion.\\n\\n 8\\n We emphasize that we make no holding regarding the application of Montana or\\nNevada law to the CCA’s physical custody requirement. Indeed, the tensions between\\nstate law defining custodial rights prospectively in context of divorce proceedings on the\\none hand, and the retroactive application of those definitions to evaluate parent-child\\nrelationships for purposes of the CCA on the other, may complicate any attempt to assess\\nphysical custody as a simple factual matter. However, we need not reach those issues\\nhere.\\n\\n\\n 16\\n\\f PETITION FOR REVIEW GRANTED;\\nREMANDED FOR FURTHER PROCEEDINGS\\n\\n\\n\\n\\n 17\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1066,"cells":{"id":{"kind":"number","value":4603306,"string":"4,603,306"},"name":{"kind":"string","value":"R.F., a Minor Child, BY AND THROUGH Her Parents and Next Friends, E.F. and H.F.; E.F.; H.F., on Their Own Behalves, Plaintiffs - Appellants, v. CECIL COUNTY PUBLIC SCHOOLS, Defendant - Appellee, and D'Ette W. Devine, Superintendent (Officially); Sarah Farr, Director of Special Education (Officially), Defendants. Council of Parent Attorneys and Advocates, Inc. ; Disability Rights Maryland ; National Disability Rights Network ; The Judge David L. Bazelon Center for Mental Health Law, Amici Supporting Appellant."},"name_abbreviation":{"kind":"string","value":"R.F. v. Cecil County Public Schools"},"decision_date":{"kind":"string","value":"2019-03-25"},"docket_number":{"kind":"string","value":"18-1780"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Agee, Harris, Duncan\", \"parties\": \"\", \"opinions\": [{\"author\": \"NETWORK; THE JUDGE DAVID L. BAZELON CENTER FOR MENTAL\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-1780\\n\\n\\nR.F., a minor child, by and through her PARENTS and next friends, E.F. and H.F.;\\nE.F.; H.F., on their own behalves,\\n\\n Plaintiffs – Appellants,\\n\\n v.\\n\\nCECIL COUNTY PUBLIC SCHOOLS,\\n\\n Defendant – Appellee,\\n\\n and\\n\\nD’ETTE W. DEVINE, Superintendent (officially); SARAH FARR, Director of\\nSpecial Education (officially),\\n\\n Defendants.\\n\\n------------------------------\\n\\nCOUNCIL OF PARENT ATTORNEYS AND ADVOCATES, INC.;\\nDISABILITY RIGHTS MARYLAND; NATIONAL DISABILITY RIGHTS\\nNETWORK; THE JUDGE DAVID L. BAZELON CENTER FOR MENTAL\\nHEALTH LAW,\\n\\n Amici Supporting Appellant.\\n\\n\\nAppeal from the United States District Court for the District of Maryland, at Baltimore.\\nAlbert David Copperthite, Magistrate Judge. (1:17-cv-02203-ADC)\\n\\n\\nArgued: January 29, 2019 Decided: March 25, 2019\\n\\fBefore AGEE and HARRIS, Circuit Judges, and DUNCAN, Senior Circuit Judge.\\n\\n\\nAffirmed by published opinion. Senior Judge Duncan wrote the opinion, in which Judge\\nAgee and Judge Harris joined.\\n\\n\\nARGUED: Wayne Darryl Steedman, STEEDMAN LAW GROUP, Lutherville,\\nMaryland, for Appellants. David Andrew Burkhouse, PESSIN KATZ LAW, P.A.,\\nColumbia, Maryland, for Appellee. Peter J. Anthony, DENTONS US LLP, Washington,\\nD.C., for Amici Curiae. ON BRIEF: Cheryl A. Steele Steedman, STEEDMAN LAW\\nGROUP, Lutherville, Maryland; Kevin Golembiewski, BERNEY & SANG,\\nPhiladelphia, Pennsylvania, for Appellants. Adam E. Konstas, Towson, Maryland,\\nRochelle S. Eisenberg, PESSIN KATZ LAW, P.A., Columbia, Maryland, for Appellee.\\nIra A. Burnim, Lewis Bossing, THE JUDGE DAVID L. BAZELON CENTER FOR\\nMENTAL HEALTH LAW, Washington, D.C.; Richard D. Salgado, Dallas, Texas, A.\\nDavid Mayhall, DENTONS US LLP, Washington, D.C., for Amicus The Judge David L.\\nBazelon Center for Mental Health Law. Selene Almazan-Altobelli, COUNCIL OF\\nPARENT ATTORNEYS AND ADVOCATES, INC., Towson, Maryland, for Amicus\\nCouncil of Parent Attorneys and Advocates, Inc., National Disability Rights Network,\\nand Disability Rights of Maryland.\\n\\n\\n\\n\\n 2\\n\\fDUNCAN, Senior Circuit Judge:\\n\\n R.F., an elementary school student with a disability, and her parents (collectively\\n\\n“Appellants”) challenge the district court’s decision to affirm the determination of a\\n\\nMaryland Administrative Law Judge (an “ALJ”) that Cecil County Public Schools\\n\\n(“CCPS”) provided R.F. with a free appropriate public education (a “FAPE”) under the\\n\\nIndividuals with Disabilities Education Act (the “IDEA”), 20 U.S.C. § 1400 et seq.\\n\\nAppellants contend that CCPS violated the IDEA by (1) failing to educate R.F. in the\\n\\nleast restrictive environment (the “LRE”), (2) failing to implement R.F.’s Individualized\\n\\nEducation Program (her “IEP”), (3) denying R.F.’s parents the opportunity to participate\\n\\nin her educational decisionmaking, and (4) providing an IEP that was inappropriate for\\n\\nR.F.’s needs. The ALJ found, and the district court agreed, that while CCPS violated\\n\\ncertain procedural requirements of the IDEA, those violations did not substantively deny\\n\\nR.F. a FAPE in violation of the IDEA. For the reasons that follow, we affirm.\\n\\n\\n\\n I.\\n\\n R.F., who was seven years old when these proceedings began, is a CCPS student\\n\\nwith a disability who is entitled to special education and related services under the\\n\\nIDEA. 1 R.F. and her parents contend that CCPS failed to comply with the IDEA in\\n\\n\\n 1\\n All facts are taken from the ALJ’s findings of fact, J.A. 23–51, except where\\notherwise indicated. The parties agree that there are no genuine issues of material fact\\nwith these findings aside from the finding that R.F.’s behavior intervention plan (the\\n“BIP”) is “appropriate to address [her] problem behaviors.” J.A. 28. We address the\\nappropriateness of the BIP infra.\\n\\n 3\\n\\fseveral respects and that, in so doing, CCPS denied R.F. a FAPE in violation of the\\n\\nIDEA. Before addressing these arguments, we first provide a brief overview of the\\n\\napplicable regulatory framework and the facts and procedural history of this case.\\n\\n\\n\\n A.\\n\\n The IDEA provides funds for states to educate children with disabilities, subject to\\n\\nconditions imposing substantive requirements on the education that is provided. 20\\n\\nU.S.C. § 1412. The statute was enacted to ensure that children with disabilities have\\n\\naccess to an education that meets their unique needs, to protect the rights of these\\n\\nchildren and their parents, and to prevent the unnecessary exclusion of these children\\n\\n“from the public school system and from being educated with their peers.” 2 Id. § 1400.\\n\\n To that end, the IDEA requires that participating states provide a FAPE to children\\n\\nwith disabilities. Id. § 1412(a)(1). The mechanism by which a state provides a FAPE is\\n\\nan IEP--a document that describes the child’s unique needs and the state’s plan for\\n\\nmeeting those needs. See Endrew F. ex rel. Joseph F. v. Douglas Cty. Sch. Dist. RE-1,\\n\\n137 S. Ct. 988, 994 (2017) (“The IEP is the centerpiece of the [IDEA’s] education\\n\\ndelivery system for disabled children.”) (citation and internal quotation marks omitted).\\n\\nThe IDEA requires participating states to “develop[], review[], and revise[]” an IEP for\\n\\neach child with a disability. 20 U.S.C. § 1412(a)(4). An IEP must contain an assessment\\n\\n 2\\n The IDEA is an updated version of the Education for All Handicapped Children\\nAct of 1975, Pub. L. No. 94-142, 89 Stat. 773 (1975) (current version at 20 U.S.C. § 1400\\net seq.), under which some of the caselaw setting out IDEA requirements was initially\\ndeveloped.\\n\\n 4\\n\\fof the child’s “present levels of academic achievement and functional performance,”\\n\\nmeasurable annual goals that are designed to “meet the child’s needs that result from the\\n\\nchild’s disability” along with a statement of how progress toward those goals will be\\n\\nmeasured, a description of “the special education and related services and supplementary\\n\\naids and services” that the school will provide for the child, and an “explanation of the\\n\\nextent[] . . . to which the child will not participate with nondisabled children in the\\n\\nregular class.” Id. § 1414(d)(1)(A)(i). The IEP team--a group comprised mainly of\\n\\nschool staff and a child’s parents--should revise the IEP “as appropriate” to address\\n\\nvarious circumstances, including a “lack of expected progress towards the annual goals”;\\n\\n“the results of any reevaluation”; “information about the child provided to, or by, the\\n\\nparents”; “the child’s anticipated needs”; or “other matters.” Id. § 1414(d)(4)(A). The\\n\\nIDEA requires that a child’s parents be included in the IEP decisionmaking process as\\n\\nmembers of the IEP team. Id. § 1414(d)(1)(B).\\n\\n\\n\\n B.\\n\\n R.F. has been diagnosed with severe autism spectrum disorder and a rare genetic\\n\\ndisorder. 3 She generally communicates without using words, and she “exhibits complex,\\n\\nchallenging, disruptive behaviors” such as hyperactivity and aggression. J.A. 24. Her\\n\\naggressive behaviors, which include “grabbing people, pulling hair, biting, and placing\\n\\n\\n 3\\n R.F. was one of only two people in the world diagnosed with this disorder when\\nshe received that diagnosis. The long-term consequences of this disorder, including its\\nimpact on R.F.’s educational potential, are unknown.\\n\\n 5\\n\\fher mouth on others,” often manifest during transitions in the school day. Id. R.F. also\\n\\nexhibits physical limitations--for instance, she has significant neuromuscular deficits, so\\n\\nshe sometimes needs assistance sitting up straight and being aware of her body’s position\\n\\nwhen navigating steps and curbs. R.F. “requires adult supervision and assistance at all\\n\\ntimes.” Id. She also has a short attention span and has difficulty processing information\\n\\nquickly.\\n\\n CCPS first identified R.F. as a student qualifying for special education and related\\n\\nservices when she was two years old. It developed IEPs for R.F. for half-day\\n\\nkindergarten in the 2014–2015 school year and for full-day kindergarten in the 2015–\\n\\n2016 school year.\\n\\n Before R.F. entered first grade, CCPS took steps to address R.F.’s behavioral\\n\\nissues. CCPS hired a consultant from the Kennedy Krieger Institute to instruct its staff\\n\\non conducting functional behavior assessments (“FBAs”) for students with significant\\n\\ndisabilities and autism. CCPS staff conducted an FBA for R.F. in April 2016 and created\\n\\na behavior intervention plan (a “BIP”) for her that focused on biting as her primary\\n\\ninterfering behavior.\\n\\n The BIP set out actions for CCPS staff to take to reduce R.F.’s unwanted biting\\n\\nand to intervene when she began to bite. Steps to reduce R.F.’s biting included ensuring\\n\\nthat R.F.’s NovaChat (a device that allows R.F. to press pictures on a screen to\\n\\ncommunicate) was accessible to her at all times, maintaining a “clear and consistent daily\\n\\nroutine” and a visual schedule to ease transitions during the day, reminding R.F. of\\n\\nappropriate behaviors by presenting social stories to her throughout the day, providing\\n\\n 6\\n\\fR.F. with “short verbal instructions with visual supports,” and using a token\\n\\nreinforcement system. J.A. 29. Steps to intervene when R.F. began to bite included\\n\\nredirecting R.F. to her NovaChat, to appropriate oral stimulation items, or to vibration\\n\\ntools meant to calm R.F., followed by reviewing social stories to remind R.F. why biting\\n\\nis inappropriate.\\n\\n As relevant to the dispute on appeal, R.F.’s IEP team--comprised primarily of\\n\\nCCPS staff and R.F.’s parents--met in May 2016 to revise her IEP for the 2016–2017 first\\n\\ngrade school year (the “May 2016 IEP”). The May 2016 IEP incorporated R.F.’s BIP. It\\n\\nalso included thirteen goals to address R.F.’s academic, behavioral, physical, and speech\\n\\nand language needs. The IEP team determined that to make progress on these goals, R.F.\\n\\nwould require sixteen hours and fifty-five minutes outside the general education setting\\n\\nand fourteen hours and thirty-five minutes inside the general education setting each week.\\n\\n R.F.’s mother attended this meeting and objected to the May 2016 IEP. She did\\n\\nnot think that R.F. should be included in classes with nondisabled peers and requested\\n\\nthat CCPS pay for R.F.’s tuition at the Benedictine School, a private school. The other\\n\\nmembers of R.F.’s IEP team disagreed and noted that CCPS was developing an intensive\\n\\ncommunication support classroom (an “ICSC”) for children with communicative\\n\\ndifficulties. The IEP team again met in June 2016 to evaluate R.F.’s progress on her IEP\\n\\n\\n\\n\\n 7\\n\\fgoals before the start of the 2016–2017 school year. Appellants’ arguments on appeal\\n\\nfocus solely on the 2016–2017 school year. 4\\n\\n At the start of the 2016–2017 school year, CCPS provided most of R.F.’s special\\n\\neducation services in the ICSC. Although CCPS anticipated the participation of other\\n\\nstudents in the ICSC, those students did not attend in the fall of 2016 due to unexpected\\n\\ncircumstances. Consequently, R.F. was the only student in the ICSC. R.F. joined the\\n\\ngeneral education classroom for “specials” (e.g. gym, art, music), recess, field trips, and\\n\\noccasional reading and math classes.\\n\\n Mr. K., a special education teacher, provided R.F. with special education services\\n\\nin the ICSC. CCPS also assigned a paraprofessional to support R.F. throughout the day.\\n\\nIn the ICSC and throughout R.F.’s day, CCPS offered R.F. a number of specialized\\n\\nservices, including individualized supervision and instruction, and supports. These\\n\\nsupports included objects meant to help R.F. transition to new activities and locations, a\\n\\nvisual schedule with verbal cues, and low lighting and reduced noise. CCPS\\n\\n“implemented the BIP regularly, but not perfectly.” J.A. 44. For instance, while Mr. K.\\n\\nused the behavior reduction and intervention steps in the BIP, he did not always follow\\n\\nthem in order. To monitor R.F.’s progress toward her IEP goals, Mr. K. collected data on\\n\\nR.F.’s behavior and performance every other week and incorporated that data into\\n\\n\\n\\n\\n 4\\n Appellants initially asserted claims arising from the 2014–2015 and 2015–2016\\nschool years, but these claims were disposed of by the ALJ below, and Appellants do not\\npursue them on appeal.\\n\\n 8\\n\\fquarterly progress reports. He destroyed his raw data after writing the quarterly reports,\\n\\neven though CCPS requires teachers to maintain data for two years.\\n\\n In August 2016, approximately three weeks after the start of school, Mr. K. began\\n\\nto notice that R.F. struggled when she joined her nondisabled peers in the general\\n\\neducation setting. She had difficulty walking between classrooms and staying seated and\\n\\nquiet in the general education classroom. She also often failed to finish her lunch in the\\n\\nschool lunchroom because she became distracted.\\n\\n In response to these difficulties, Mr. K. gradually began providing more\\n\\ninstruction to R.F. in the ICSC instead of the general education classroom. For instance,\\n\\nwhile R.F.’s schedule placed her in the general education classroom for reading\\n\\ncomprehension, Mr. K. would sometimes remove her from that class and take her back to\\n\\nthe ICSC. This decision varied daily and, according to Mr. K., was “responsive to her\\n\\nneeds depending on her success in the class.” S.A. 3. 5 On some days, Mr. K. was unable\\n\\nto take R.F. to the general education classroom “if she was exhibiting really aggressive\\n\\nbehaviors or if she was having a really difficult time walking or with mobility.” S.A. 4.\\n\\nAs a result of these adjustments, R.F.’s hours in the ICSC exceeded the number specified\\n\\nin the May 2016 IEP.\\n\\n In December 2016, R.F.’s IEP team met again to revise her IEP (the “December\\n\\n2016 IEP”). The team decided to reduce the number of hours that R.F. spent in the\\n\\ngeneral education setting so that she would only attend specials with nondisabled peers.\\n\\n 5\\n Citations to the “S.A.” refer to the Supplemental Appendix filed by CCPS in this\\nappeal.\\n\\n 9\\n\\fAccordingly, the December 2016 IEP increased R.F.’s weekly time outside the general\\n\\neducation setting from sixteen hours and fifty-five minutes to twenty-nine hours.\\n\\n R.F.’s parents attended the meeting and opposed CCPS’s approach. R.F.’s mother\\n\\nagain expressed opposition to placing R.F. in a general education setting “at all during the\\n\\nschool day.” J.A. 45. R.F.’s parents also presented a report by Lisa Frank, an education\\n\\nconsultant, who recommended placement in a “full-day evidence-based program for\\n\\nchildren with autism” like the Benedictine School. Id. The other members of the IEP\\n\\nteam disagreed with this proposed placement and determined that the ICSC was the best\\n\\nplacement for R.F.\\n\\n\\n\\n C.\\n\\n Shortly after R.F.’s IEP team compiled the December 2016 IEP, R.F.’s parents\\n\\ninitiated this action, alleging that CCPS violated the IDEA and seeking to have R.F.\\n\\nplaced at the Benedictine School or another private school at CCPS’s expense. As\\n\\nrequired under the IDEA, they first filed a due process complaint with Maryland’s Office\\n\\nof Administrative Hearings, resulting in a hearing before an ALJ. See 20 U.S.C.\\n\\n§ 1415(f). The hearing before the ALJ addressed whether CCPS denied R.F. a FAPE or\\n\\nfailed to offer her an IEP that would provide her with a FAPE during the 2016–2017\\n\\nschool year.\\n\\n Mr. K testified at the hearing. As relevant to one of Appellants’ principal claims\\n\\nconcerning CCPS’s procedural violations of the statute, Mr. K. stated that he was\\n\\nunaware that CCPS required teachers to maintain raw data for two years. The ALJ\\n\\n 10\\n\\fconcluded that he had violated CCPS’s retention policy but “did not do so for any\\n\\nnefarious purpose,” and she declined to draw any negative inferences from his testimony.\\n\\nJ.A. 71.\\n\\n The ALJ also heard evidence regarding how CCPS calculates special education\\n\\nhours for the purposes of preparing IEPs and recording services provided. She found\\n\\nthat, while Maryland requires schools to define special education hours in terms of the\\n\\nnumber of hours a child spends outside the general education classroom, CCPS defines\\n\\nthem in terms of the number of hours of instruction focused on a child’s IEP goals.\\n\\nTherefore, the ALJ concluded that experts who testified that R.F.’s IEP contained an\\n\\ninadequate number of special education hours did so based on a misunderstanding of how\\n\\nCCPS calculates those hours.\\n\\n Based on the testimony and data presented at the hearing, the ALJ evaluated R.F.’s\\n\\nprogress on her IEP goals. She found that R.F. had made progress toward some of her\\n\\nphysical goals as well as some of her speech and language goals. She also found that\\n\\nR.F. did not make progress toward her behavioral or academic goals. She concluded that,\\n\\noverall, R.F. had “made incremental progress on some, but not all of her goals” and that\\n\\nthis was appropriate for R.F. “given her unique circumstances.” J.A. 86.\\n\\n The ALJ issued a decision holding that CCPS procedurally violated the IDEA by\\n\\nchanging R.F.’s placement in August 2016 by gradually increasing her hours in the ICSC\\n\\nwithout notifying her parents or revising her IEP. She also concluded, however, that this\\n\\nviolation did not deny R.F. a FAPE, crediting Mr. K.’s testimony that R.F. was having\\n\\ndifficulty in the general education setting and benefitted from additional time in the\\n\\n 11\\n\\fICSC. Overall, the ALJ concluded that “CCPS offered [R.F.] ‘an IEP reasonably\\n\\ncalculated to [enable her to] make progress appropriate in light of the child’s\\n\\ncircumstances.’” J.A. 87 (quoting Endrew F., 137 S. Ct. at 999).\\n\\n Appellants challenged the ALJ’s decision in federal district court, naming as\\n\\ndefendants CCPS, its superintendent, and its director of special education, in their official\\n\\ncapacities. 6 The district court granted CCPS’s motion for summary judgment for reasons\\n\\nsimilar to those stated in the ALJ’s decision. 7 This appeal followed.\\n\\n\\n\\n II.\\n\\n In IDEA cases, we conduct a modified de novo review, “giving ‘due weight’ to the\\n\\nunderlying administrative proceedings.” M.S. ex rel. Simchick v. Fairfax Cty. Sch. Bd.,\\n\\n553 F.3d 315, 323 (4th Cir. 2009) (citation omitted). Under our precedent, whether an\\n\\neducational program offered by the state is appropriate for purposes of the FAPE analysis\\n\\nis a question of fact.8 We consider an ALJ’s factual findings to be “prima facie correct.”\\n\\nDoyle v. Arlington Cty. Sch. Bd., 953 F.2d 100, 105 (4th Cir. 1991). However, the\\n\\n“ultimate decision as to whether the state has complied with the IDEA” is an independent\\n\\n 6\\n Throughout this opinion, we refer to these defendants collectively as “CCPS.”\\n 7\\n The district judge referred the case to a federal magistrate judge for all\\nproceedings and the entry of judgment by consent of the parties, in accordance with 28\\nU.S.C. § 636(c).\\n 8\\n We note, however, that several other circuits treat the issue of whether the school\\ndistrict has provided a FAPE as a mixed question of fact and law. See, e.g., K.E. ex rel.\\nK.E. v. Indep. Sch. Dist. No. 15, 647 F.3d 795, 804 (8th Cir. 2011) (“Whether a child has\\nreceived a FAPE is a mixed question of law and fact.”).\\n\\n 12\\n\\fdecision made by the district court. Sumter Cty. Sch. Dist. 17 v. Heffernan ex rel. TH,\\n\\n642 F.3d 478, 484 (4th Cir. 2011). In making this independent decision, courts should\\n\\nnot “substitute their own notions of sound educational policy for those of the school\\n\\nauthorities which they review.” Bd. of Educ. of Hendrick Hudson Cent. Sch. Dist. v.\\n\\nRowley, 458 U.S. 176, 206 (1982).\\n\\n\\n\\n III.\\n\\n Appellants contend that CCPS violated the IDEA in several respects. Whether a\\n\\nstate has violated the IDEA has procedural and substantive components. Procedurally,\\n\\nthe state must comply with the stated requirements of the IDEA. Id. at 206–07.\\n\\nSubstantively, the state must offer the child a FAPE, which requires a targeted\\n\\neducational program setting reasonably calculated goals for a child’s progress in light of\\n\\nthe child’s particular circumstances. Endrew F., 137 S. Ct. at 999.\\n\\n We first reexamine our precedent in light of the Supreme Court’s recent decision\\n\\nin Endrew F., 137 S. Ct. 988, clarifying the FAPE standard. We then address Appellants’\\n\\nspecific contentions regarding CCPS’s compliance with the IDEA.\\n\\n\\n\\n A.\\n\\n To meet the substantive requirements of the IDEA, a school must provide a child\\n\\nwith a FAPE. M.L. ex rel. Leiman v. Smith, 867 F.3d 487, 499 (4th Cir. 2017). The\\n\\nSupreme Court recently held in Endrew F. that to satisfy the FAPE requirement, “a\\n\\n\\n\\n 13\\n\\fschool must offer an IEP reasonably calculated to enable a child to make progress\\n\\nappropriate in light of the child’s circumstances.” 137 S. Ct. at 999.\\n\\n In establishing this standard, the Court rejected the Tenth Circuit’s approach,\\n\\nwhich held that the education and services provided to children with disabilities “must be\\n\\ncalculated to confer some educational benefit” to meet the FAPE requirement and that a\\n\\nchild’s IEP “is adequate as long as it is calculated to confer an educational benefit that is\\n\\nmerely more than de minimis” (the “de minimis standard”). Id. at 997 (alterations,\\n\\ncitation, and internal quotation marks omitted). Before Endrew F., we required schools\\n\\nto provide “some educational benefit” to a child to meet their substantive obligation to\\n\\nprovide the child with a FAPE. See O.S. v. Fairfax Cty. Sch. Bd., 804 F.3d 354, 358 (4th\\n\\nCir. 2015) (quoting Rowley, 458 U.S. at 200) (collecting cases). This prior standard is\\n\\nsimilar to the Tenth Circuit’s de minimis standard, and we clarify again that it is no\\n\\nlonger good law. See M.L., 867 F.3d at 496 (acknowledging that “[o]ur prior FAPE\\n\\nstandard is similar to that of the Tenth Circuit, which was overturned by Endrew F.”).\\n\\n Instead, we follow the Court’s standard as articulated in Endrew F. and hold that\\n\\n“[t]o meet its substantive obligation under the IDEA, a school must offer an IEP\\n\\nreasonably calculated to enable a child to make progress appropriate in light of the child’s\\n\\ncircumstances.” 9 Endrew F., 137 S. Ct. at 999. This standard is framed in terms of each\\n\\n\\n 9\\n Indeed, we implicitly did so in T.B., Jr. ex rel. T.B., Sr. v. Prince George’s\\nCounty Board of Education, 897 F.3d 566 (4th Cir. 2018). In that case, we held that a\\nschool board procedurally violated the IDEA by failing to promptly evaluate a child for\\nspecial education. Id. at 573. We concluded, however, that the school did not\\nsubstantively violate the IDEA because its failure did not deny the child a FAPE. Id. at\\n(Continued)\\n 14\\n\\fchild’s unique circumstances because “[a] focus on the particular child is at the core of\\n\\nthe IDEA.” Id. Consequently, “the benefits obtainable by children at one end of the\\n\\nspectrum [of disability] will differ dramatically from those obtainable by children at the\\n\\nother end, with infinite variations in between.” Id. (quoting Rowley, 458 U.S. at 202).\\n\\nOur analysis is therefore grounded in each particular child’s circumstances.\\n\\n\\n\\n B.\\n\\n Having established the relevant standard for the FAPE requirement, we turn to the\\n\\nissues on appeal in this case. In sum, we hold that CCPS did violate certain procedural\\n\\nrequirements of the IDEA, most notably by changing R.F.’s placement without notifying\\n\\nher parents or modifying her IEP. However, any procedural violations did not deny R.F.\\n\\na FAPE.\\n\\n Appellants contend that CCPS violated the IDEA in four respects: (1) by failing to\\n\\neducate R.F. in the LRE, (2) by failing to implement the classroom placement in R.F.’s\\n\\nIEP when Mr. K. increased her hours in the ICSC, (3) by denying R.F.’s parents the right\\n\\nto participate in her education, and (4) by failing to provide an IEP appropriate for R.F.’s\\n\\nneeds. We address each issue in turn.\\n\\n\\n\\n\\n575. In doing so, we quoted Endrew F.’s standard to explain the substantive requirement\\nof the IDEA, but it was not central to our holding because the case did not turn on\\nwhether the child’s IEP was reasonably calculated to provide the child with a FAPE. See\\nid. at 571.\\n\\n 15\\n\\f 1.\\n\\n Appellants contend that CCPS failed to educate R.F. in the LRE because it\\n\\nprovided her most of her instruction in the ICSC, where R.F. was the only student. They\\n\\nseek an order placing R.F. at a private school where she would be educated among peers\\n\\nwith disabilities. We reject this contention.\\n\\n The IDEA requires participating states to educate children with disabilities in the\\n\\nLRE--that is, alongside children who are not disabled “[t]o the maximum extent\\n\\nappropriate.” 20 U.S.C. § 1412(a)(5). It permits states to remove a child with disabilities\\n\\nfrom the “regular educational environment . . . only when the nature or severity of the\\n\\ndisability of a child is such that education in regular classes [with appropriate supports]\\n\\ncannot be achieved satisfactorily.” Id. We have acknowledged that this statutory\\n\\nlanguage “obviously indicates a strong congressional preference for mainstreaming”\\n\\nstudents into the general education classroom but that “[m]ainstreaming . . . is not\\n\\nappropriate for every [child with a disability].” DeVries ex rel. DeBlaay v. Fairfax Cty.\\n\\nSch. Bd., 882 F.2d 876, 878 (4th Cir. 1989). Instead, “[t]he proper inquiry is whether a\\n\\nproposed placement is appropriate under the [IDEA]”--in other words, whether a child’s\\n\\nplacement--the setting where the child learns--provides the child with a FAPE. Id.\\n\\n(citation omitted).\\n\\n Here, placement in the ICSC was “reasonably calculated to enable [R.F.] to make\\n\\nprogress appropriate in light of [her] circumstances.” Endrew F., 137 S. Ct. at 999. The\\n\\nALJ’s analysis here is instructive; she noted that “CCPS was not hiding [R.F.] from her\\n\\n 16\\n\\fpeers; [R.F.] was afforded opportunities to interact with other first graders, albeit not to\\n\\nthe degree CCPS would have preferred.” J.A. 73–74. Indeed, while R.F. received most\\n\\nof her instruction in the ICSC, CCPS gave her multiple daily opportunities to interact\\n\\nwith her nondisabled peers. For instance, she attended specials with the general\\n\\neducation population and walked around the school each day to practice greeting other\\n\\nstudents. These opportunities, combined with R.F.’s instructional time in the ICSC, did\\n\\nnot deny R.F. a FAPE, particularly where Mr. K. noted that R.F. had trouble\\n\\nconcentrating and accessing material in the general education population. R.F. had\\n\\nopportunities to interact with her peers “[t]o the maximum extent appropriate,” given\\n\\nR.F.’s unique circumstances and academic and behavioral needs. 20 U.S.C. § 1412(a)(5).\\n\\n Appellants argue that the conclusions of the ALJ and the district court regarding\\n\\nR.F.’s placement improperly conflate the LRE and FAPE requirements. However, as\\n\\nthey themselves recognize, the statutory obligation requires placement in the least\\n\\nrestrictive environment appropriate for the child’s education. See Devries, 882 F.2d at\\n\\n880. As in DeVries, that required an environment where R.F. could benefit from “a\\n\\nstructured program” and the opportunity for “one-to-one instruction.” Id. at 879.\\n\\n Appellants argue that they are not urging CCPS to increase the number of hours\\n\\nthat R.F. spends with her peers who are not disabled; instead, they contend that the LRE\\n\\nfor R.F. would include more time among peers with disabilities, and they seek placement\\n\\nin a private school to achieve that outcome. This argument miscomprehends the LRE\\n\\nrequirement, which is defined in terms of the extent to which children with disabilities\\n\\n“are educated with children who are not disabled.” Id. at 878 (emphasis added). But\\n\\n 17\\n\\feven under Appellants’ standard, CCPS did not violate the LRE requirement. Instead, the\\n\\nALJ correctly noted that “CCPS thought there would be other students in the [ICSC], but\\n\\nit did not turn out that way” due to unforeseen circumstances. J.A. 73. CCPS cannot be\\n\\nsaid to have denied R.F. a FAPE merely because fewer students with disabilities enrolled\\n\\nat R.F.’s school than CCPS anticipated. Accordingly, we agree with the ALJ and the\\n\\ndistrict court that CCPS did not violate the LRE requirement.\\n\\n\\n\\n 2.\\n\\n Next, Appellants contend that CCPS violated the IDEA by failing to follow R.F.’s\\n\\nIEP. Specifically, they argue that CCPS failed to implement R.F.’s IEP when Mr. K.\\n\\nchanged R.F.’s placement and began providing her with more instruction hours in the\\n\\nICSC than her IEP called for. While this was a procedural violation of the IDEA, we\\n\\nhold that it was not a substantive violation because R.F. was not denied a FAPE as a\\n\\nresult.\\n\\n A school must follow procedures specified in the IDEA before changing the\\n\\nchild’s placement as identified in her IEP. See 20 U.S.C. § 1415(b)(3) (requiring written\\n\\nprior notice to the child’s parents before the local education agency may change a child’s\\n\\neducational placement). Here, CCPS did not follow these procedures before changing\\n\\nR.F.’s placement. Instead, Mr. K. increased her hours in the ICSC beyond those\\n\\nspecified in her IEP without giving notice to R.F.’s parents. This constitutes a procedural\\n\\nviolation.\\n\\n\\n\\n 18\\n\\f However, as we have noted, not all procedural violations of the IDEA result in the\\n\\ndenial of a FAPE. T.B., Jr., 897 F.3d at 573. Indeed, Mr. K.’s decision to provide R.F.\\n\\nwith more instruction in the ICSC than her IEP specified was “reasonably calculated to\\n\\nenable [R.F.] to make progress appropriate in light of [her] circumstances.” Endrew F.,\\n\\n137 S. Ct. at 999. Mr. K. recognized that R.F. was struggling in the general education\\n\\nclassroom, and he determined that she would make more progress with more one-on-one\\n\\ninstruction in the ICSC. He did so on a gradual and individualized basis, based on close\\n\\nattention to R.F.’s performance in a general education setting and in the ICSC. We\\n\\nconclude that R.F. received a FAPE when CCPS changed her placement, even though it\\n\\nfailed to follow the IDEA’s procedural requirements.\\n\\n\\n\\n 3.\\n\\n Appellants also contend that CCPS violated the IDEA by taking certain actions\\n\\nthat impeded her parents from participating in decisions about her education. The IDEA\\n\\nand its regulations grant the parents of a child with a disability certain procedural rights,\\n\\nincluding the right to “examine all records” relating to that child and to “participate in\\n\\nmeetings with respect to the identification, evaluation, and educational placement” of the\\n\\nchild. 20 U.S.C. § 1415(b); see 34 C.F.R. § 300.322 (setting out parent participation\\n\\nregulations for IEP development). The IDEA also “grants parents independent,\\n\\nenforceable rights” that are not limited to procedural matters, including “the entitlement\\n\\nto a [FAPE] for the parents’ child.” Winkelman ex rel. Winkelman v. Parma City Sch.\\n\\nDist., 550 U.S. 516, 533 (2007). We first clarify the grounds on which an ALJ may\\n\\n 19\\n\\fdetermine that a violation of parents’ rights under the IDEA resulted in the denial of a\\n\\nFAPE to a child before turning to Appellants’ contentions here.\\n\\n\\n\\n a.\\n\\n Parents who seek to enforce their rights or the rights of their child under the IDEA\\n\\nfirst seek review through a due process hearing before an ALJ. 20 U.S.C. § 1415(f). In\\n\\ngeneral, the ALJ must determine whether a school violated the IDEA by deciding “on\\n\\nsubstantive grounds . . . whether the child received a [FAPE].” Id. § 1415(f)(3)(E)(i).\\n\\nHowever, “[i]n matters alleging a procedural violation, an ALJ “may find that a child did\\n\\nnot receive a [FAPE]” if the ALJ determines that a procedural right was violated and that\\n\\nthe violation “significantly impeded the parents’ opportunity to participate in the\\n\\ndecisionmaking process regarding the provision of a [FAPE] to the parents’ child.” Id.\\n\\n§ 1415(f)(3)(E)(ii)(II).\\n\\n Under § 1415(f)(3)(E)(ii)(II), an ALJ must answer each of the following in the\\n\\naffirmative to find that a procedural violation of the parental rights provisions of the\\n\\nIDEA constitutes a violation of the IDEA: (1) whether the plaintiffs “alleg[ed] a\\n\\nprocedural violation,” (2) whether that violation “significantly impeded the parents’\\n\\nopportunity to participate in the decisionmaking process regarding the provision of a\\n\\n[FAPE] to the parents’ child,” and (3) whether the child “did not receive a [FAPE]” as a\\n\\nresult. Id. § 1415(f)(3)(E). Unless an ALJ determines that a given procedural violation\\n\\ndenied the child a FAPE, she may only order compliance with the IDEA’s procedural\\n\\nrequirements and cannot grant other forms of relief, such as private placement or\\n\\n 20\\n\\fcompensatory education. See Fry v. Napoleon Cmty. Schs., 137 S. Ct. 743, 754 n.6\\n\\n(2017) (“Without finding the denial of a FAPE, a hearing officer may do nothing more\\n\\nthan order a school district to comply with the [IDEA’s] various procedural\\n\\nrequirements.”).\\n\\n\\n\\n b.\\n\\n Our analysis here starts and ends with the second prong of this standard: whether a\\n\\nviolation of parents’ procedural rights under the IDEA “significantly impeded” their\\n\\nopportunity to participate in decisionmaking regarding their child’s education.\\n\\nAppellants contend that CCPS violated their parental participation rights under the IDEA\\n\\nby changing R.F.’s placement without involving them in an IEP meeting and by\\n\\ndestroying data relating to R.F.’s progress on her IEP goals. We hold that neither\\n\\nconstitutes a significant impediment to parental participation on these facts.\\n\\n With respect to changing R.F.’s placement, the parties agree that “Mr. K.’s\\n\\nunilateral determination to alter the environment in which some of R.F.’s IEP services\\n\\nwere offered . . . constituted a procedural violation of [the parental rights provisions of]\\n\\nthe IDEA.” Appellees’ Br. at 17; see 20 U.S.C. § 1415(b)(3).\\n\\n However, R.F.’s parents’ opportunity to participate in decisionmaking regarding\\n\\nR.F.’s education was not “significantly impeded” when CCPS changed R.F.’s placement\\n\\nfor four months without involving her parents. 20 U.S.C. § 1415(f)(3)(E)(ii)(II). As\\n\\ndiscussed above, in changing R.F.’s placement, CCPS provided her more special\\n\\neducation services, not fewer, in the ICSC, consistent with her parents’ objection that her\\n\\n 21\\n\\fIEP contained too many hours in the general education classroom. CCPS did not\\n\\nsignificantly impede R.F.’s parents’ participation rights when it failed to inform them that\\n\\nit was gradually changing R.F.’s placement in line with their expressed wishes.\\n\\n Additionally, R.F.’s parents did eventually have an opportunity to participate in\\n\\ndecisions about R.F.’s placement when her mother attended the December 2016 IEP\\n\\nmeeting. See D.S. v. Bayonne Bd. of Educ., 602 F.3d 553, 565 (3d Cir. 2010) (holding\\n\\nthat a school district did not violate the IDEA when it ignored parents’ letters for months\\n\\nbut included the parents in their child’s IEP meeting because “they ultimately had an\\n\\nopportunity to participate meaningfully in the creation of an IEP” for their child).\\n\\nTherefore, the only form of relief that Appellants seek--private placement for R.F.--\\n\\n“cannot reasonably be traced” to CCPS’s failure to include R.F.’s parents in decisions\\n\\nregarding her placement in August 2016. Id. at 566. We cannot agree with Appellants\\n\\nthat CCPS’s procedural violation of R.F.’s parents’ right to participate in decisions about\\n\\nher placement rises to the level of a substantive IDEA violation that could be cured by\\n\\nprivate placement.\\n\\n Appellants also contend that CCPS violated their parental rights under the IDEA\\n\\nwhen Mr. K. destroyed the raw data that he collected on R.F.’s progress before her\\n\\nparents could review it. However, as the ALJ noted, “the IDEA does not specify how\\n\\noften a school system should collect data or how long it should be maintained.” J.A. 72.\\n\\nInstead, it only requires that the IEP describe how the child’s progress toward her goals\\n\\nwill be measured. 20 U.S.C. § 1414(d)(1)(A)(i)(III). The ALJ found that while Mr. K.\\n\\nviolated CCPS’s records retention policy, which required him to preserve the data for two\\n\\n 22\\n\\fyears, he did not violate the IDEA when he destroyed R.F.’s raw data after making his\\n\\nquarterly reports. We agree that this was not a procedural violation of the IDEA.\\n\\n Regardless of whether the data destruction was a procedural violation of the\\n\\nIDEA, R.F.’s parents could still view summaries of the data in Mr. K.’s quarterly reports.\\n\\nTherefore, their ability to “participate in the decisionmaking process” regarding R.F.’s\\n\\neducation was not “significantly impeded.” 20 U.S.C. § 1415(f)(3)(E)(ii)(II).\\n\\n We in no way minimize the necessity of compliance with the procedural\\n\\nrequirements of the IDEA, including those pertaining to parental participation. See\\n\\nDiBuo ex rel. DiBuo v. Bd. of Educ., 309 F.3d 184, 191 (4th Cir. 2002) (explaining, in a\\n\\ncase before § 1415(f)(3)(E)(ii)(II) was enacted, that “[w]e have no doubt that a\\n\\nprocedural violation of the IDEA . . . that causes interference with the parents’ ability to\\n\\nparticipate in the development of their child’s IEP will often actually interfere with the\\n\\nprovision of a FAPE to that child”). But here, we cannot find that CCPS significantly\\n\\nimpeded R.F.’s parents’ participation rights when it changed R.F.’s placement and\\n\\ndestroyed raw data on R.F.’s progress. Accordingly, we affirm that CCPS did not violate\\n\\nR.F.’s parents’ rights under the IDEA.\\n\\n\\n\\n 4.\\n\\n Finally, Appellants contend that CCPS violated the IDEA because it failed to\\n\\nprovide R.F. with an IEP that was sufficient to meet her needs, thus denying her a FAPE.\\n\\nSpecifically, they contend that R.F.’s BIP was insufficient because it primarily focused\\n\\non biting while ignoring R.F.’s other behaviors, that R.F.’s IEP was inadequate because it\\n\\n 23\\n\\flacked a social skills goal, and that R.F.’s IEP contained an insufficient number of hours\\n\\nof special education instruction to meet her needs. We disagree.\\n\\n As we have discussed, “[t]o meet its substantive obligation under the IDEA, a\\n\\nschool must offer an IEP reasonably calculated to enable a child to make progress\\n\\nappropriate in light of the child’s circumstances.” Endrew F., 137 S. Ct. at 999. Courts\\n\\nconduct this analysis with an understanding that “crafting an appropriate program of\\n\\neducation requires a prospective judgment by school officials.” Id.\\n\\n First, with respect to the BIP, Appellants contend that it rendered R.F.’s IEP\\n\\ninadequate because it should have addressed behaviors other than biting. 10 However, the\\n\\nALJ found that, at the time the May 2016 IEP was created, biting was R.F.’s primary\\n\\nproblem behavior. She also deferred to testimony by Sarah Farr, CCPS’s director of\\n\\nspecial education, that “[t]he skills set forth in the BIP for the primary behavior [here,\\n\\nbiting] can be generalized to other behaviors.” J.A. 68–69. Therefore, the behavior\\n\\nstrategies in the May 2016 IEP were “reasonably calculated” in light of R.F.’s\\n\\ncircumstances at the time that IEP was created, and CCPS did not deny her a FAPE.\\n\\nEndrew F., 137 S. Ct. at 999.\\n\\n Appellants contend that the December 2016 IEP was inadequate because it\\n\\nincorporated the BIP without revising it to include interventions for R.F.’s other\\n\\ninterfering behaviors. However, Appellants present no evidence that by the time the IEP\\n\\n\\n 10\\n Although the BIP itself is defined by Maryland regulations, see Md. Code Regs.\\n§ 13a.08.04.02(B)(1), its incorporation by reference into R.F.’s IEP gives rise to review\\nunder the IDEA framework governing the adequacy of IEPs.\\n\\n 24\\n\\fteam met to revise R.F.’s IEP in December, CCPS was aware that biting was not R.F.’s\\n\\nonly interfering behavior. While it is true that Mr. K. testified in March 2017 that if he\\n\\nwere to develop a new BIP for R.F., it would include biting, hair pulling, grabbing,\\n\\nhitting, kicking, and scratching, this says nothing about what CCPS knew in December\\n\\n2016. Without other evidence indicating that CCPS knew in December 2016 that R.F.\\n\\nneeded interventions for behaviors other than biting, we cannot say that CCPS\\n\\nprocedurally violated the IDEA by failing to account for those behaviors in her IEP.\\n\\n Regardless, any error in failing to update the BIP did not deny R.F. a FAPE\\n\\nbecause CCPS took steps that were “reasonably calculated” to address R.F.’s behavioral\\n\\nneeds “in light of [her] circumstances.” Id. For instance, Farr testified that R.F.’s\\n\\nexisting BIP was sufficient to address R.F.’s behaviors. Farr explained that R.F.’s other\\n\\ninterfering behaviors did not need to be included in a new BIP because “they’re being\\n\\naddressed in a very appropriate way. [CCPS is] altering the environment to change those\\n\\nbehaviors.” S.A. 24. Farr emphasized that R.F.’s interfering behaviors, including biting,\\n\\nhave decreased because CCPS is taking steps to reduce those behaviors. Therefore,\\n\\nCCPS did not violate the IDEA and deny R.F. a FAPE by failing to address behaviors\\n\\nother than biting in the BIP that was incorporated in her May 2016 and December 2016\\n\\nIEPs.\\n\\n Second, with respect to whether R.F.’s IEP was inadequate because it lacked a\\n\\nsocial skills goal, the ALJ found that “[R.F.] could benefit if her IEP contained a\\n\\nmeasurable socialization goal” but noted that “an IEP is not required to contain every\\n\\ngoal from which a student might benefit.” J.A. 70. She concluded that “[t]aking the IEP\\n\\n 25\\n\\fas a whole,” R.F. “was not denied a FAPE due to the lack of a social skills goal in her\\n\\nIEP.” Id. We agree and note that the IEP did build in opportunities for R.F. to practice\\n\\nher social skills. For instance, R.F.’s BIP included the use of social stories to remind R.F.\\n\\nof appropriate social interactions, and her schedule included regular walks around the\\n\\nbuilding to greet students.\\n\\n Finally, with respect to whether R.F.’s IEP contained inadequate hours of special\\n\\neducation, the ALJ correctly noted that, because IEPs are prospective, Appellants cannot\\n\\nrely on the fact that R.F.’s hours of special education were increased in the December\\n\\n2016 IEP as evidence that the May 2016 IEP was defective when created. See J.A. 74\\n\\n(“The appropriateness of the May 2016 IEP must be judged as of the time it was adopted,\\n\\nnot in December 2016.”). The ALJ also found that Appellants’ experts who testified that\\n\\nthe May 2016 IEP contained an inadequate number of special education hours did so\\n\\nunder an incorrect understanding of the way CCPS calculates and records special\\n\\neducation hours. Appellants offered no other evidence that the May 2016 IEP contained\\n\\nan inadequate number of special education hours to enable R.F. to “make progress\\n\\nappropriate in light of the [her] circumstances.” Endrew F., 137 S. Ct. at 999. Therefore,\\n\\nwe affirm and conclude that the content of R.F.’s IEP was sufficient to provide her with a\\n\\nFAPE.\\n\\n\\n\\n 5.\\n\\n In sum, although CCPS violated the IDEA in some procedural respects, we affirm\\n\\nbecause it did not deny R.F. a FAPE. The education that R.F. actually received during\\n\\n 26\\n\\fthe 2016–2017 school year reinforces our decision that CCPS provided her with a FAPE.\\n\\nThe May 2016 IEP set out thirteen goals addressing “all of R.[F.]’s identified special\\n\\nneeds.” J.A. 35. These goals “focus[ed] on the particular child.” Endrew F., 137 S. Ct.\\n\\nat 999. The IEP’s use of the ICSC, with its specialized supports to target R.F.’s issues\\n\\nwith focus and stress, “aim[ed] to enable [her] to make progress,” while its efforts to\\n\\ninclude R.F. in a general educational setting for specials aimed to avoid unduly isolating\\n\\nher from her peers at school. Id.\\n\\n Under this IEP, as the ALJ found, R.F. did make “progress toward achieving some\\n\\nof the goals on her IEP during the 2016/2017 school year,” although not all of them. J.A.\\n\\n46. To facilitate her progress, Mr. K. and a paraprofessional worked closely and\\n\\nconstructively with R.F. throughout the year to determine how to best enable her to make\\n\\nprogress towards these goals. Such efforts include an ongoing assessment of whether\\n\\nR.F. was able to make progress in general educational settings.\\n\\n The IEP did not aim for grade-level advancement through the general curriculum\\n\\nor for standard letter grades because these were not considered “a reasonable prospect”\\n\\nfor R.F. Endrew F., 137 S. Ct. at 1000. But this does not indicate a failure to set\\n\\n“challenging objectives” for R.F. Id. The IEP team also revised the IEP in December\\n\\n2016 to account for the progress that R.F. had made to date.\\n\\n This combination of reasonably ambitious goals that were focused on R.F.’s\\n\\nparticular circumstances and that were pursued through the careful and attentive\\n\\ninstruction of specialized professionals provided the education that R.F. is entitled to\\n\\n\\n\\n 27\\n\\funder the statute. We therefore conclude that CCPS provided R.F. with a FAPE despite\\n\\nits procedural violations of the IDEA.\\n\\n\\n\\n IV.\\n\\n Although CCPS procedurally violated the IDEA in certain technical respects, it\\n\\ndid not substantively violate the IDEA because it did not deny R.F. a FAPE. We\\n\\ntherefore\\n\\n AFFIRM.\\n\\n\\n\\n\\n 28\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4380559/\", \"author_raw\": \"NETWORK; THE JUDGE DAVID L. BAZELON CENTER FOR MENTAL\"}]}"},"judge1":{"kind":"string","value":"AGEE"},"judge2":{"kind":"string","value":"HARRIS"},"judge3":{"kind":"string","value":"DUNCAN"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4603306/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: R.F., a Minor Child, BY AND THROUGH Her Parents and Next Friends, E.F. and H.F.; E.F.; H.F., on Their Own Behalves, Plaintiffs - Appellants, v. CECIL COUNTY PUBLIC SCHOOLS, Defendant - Appellee, and D'Ette W. Devine, Superintendent (Officially); Sarah Farr, Director of Special Education (Officially), Defendants. Council of Parent Attorneys and Advocates, Inc. ; Disability Rights Maryland ; National Disability Rights Network ; The Judge David L. Bazelon Center for Mental Health Law, Amici Supporting Appellant.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-03-25\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-1780\n\n\nR.F., a minor child, by and through her PARENTS and next friends, E.F. and H.F.;\nE.F.; H.F., on their own behalves,\n\n Plaintiffs – Appellants,\n\n v.\n\nCECIL COUNTY PUBLIC SCHOOLS,\n\n Defendant – Appellee,\n\n and\n\nD’ETTE W. DEVINE, Superintendent (officially); SARAH FARR, Director of\nSpecial Education (officially),\n\n Defendants.\n\n------------------------------\n\nCOUNCIL OF PARENT ATTORNEYS AND ADVOCATES, INC.;\nDISABILITY RIGHTS MARYLAND; NATIONAL DISABILITY RIGHTS\nNETWORK; THE JUDGE DAVID L. BAZELON CENTER FOR MENTAL\nHEALTH LAW,\n\n Amici Supporting Appellant.\n\n\nAppeal from the United States District Court for the District of Maryland, at Baltimore.\nAlbert David Copperthite, Magistrate Judge. (1:17-cv-02203-ADC)\n\n\nArgued: January 29, 2019 Decided: March 25, 2019\n\fBefore AGEE and HARRIS, Circuit Judges, and DUNCAN, Senior Circuit Judge.\n\n\nAffirmed by published opinion. Senior Judge Duncan wrote the opinion, in which Judge\nAgee and Judge Harris joined.\n\n\nARGUED: Wayne Darryl Steedman, STEEDMAN LAW GROUP, Lutherville,\nMaryland, for Appellants. David Andrew Burkhouse, PESSIN KATZ LAW, P.A.,\nColumbia, Maryland, for Appellee. Peter J. Anthony, DENTONS US LLP, Washington,\nD.C., for Amici Curiae. ON BRIEF: Cheryl A. Steele Steedman, STEEDMAN LAW\nGROUP, Lutherville, Maryland; Kevin Golembiewski, BERNEY & SANG,\nPhiladelphia, Pennsylvania, for Appellants. Adam E. Konstas, Towson, Maryland,\nRochelle S. Eisenberg, PESSIN KATZ LAW, P.A., Columbia, Maryland, for Appellee.\nIra A. Burnim, Lewis Bossing, THE JUDGE DAVID L. BAZELON CENTER FOR\nMENTAL HEALTH LAW, Washington, D.C.; Richard D. Salgado, Dallas, Texas, A.\nDavid Mayhall, DENTONS US LLP, Washington, D.C., for Amicus The Judge David L.\nBazelon Center for Mental Health Law. Selene Almazan-Altobelli, COUNCIL OF\nPARENT ATTORNEYS AND ADVOCATES, INC., Towson, Maryland, for Amicus\nCouncil of Parent Attorneys and Advocates, Inc., National Disability Rights Network,\nand Disability Rights of Maryland.\n\n\n\n\n 2\n\fDUNCAN, Senior Circuit Judge:\n\n R.F., an elementary school student with a disability, and her parents (collectively\n\n“Appellants”) challenge the district court’s decision to affirm the determination of a\n\nMaryland Administrative Law Judge (an “ALJ”) that Cecil County Public Schools\n\n(“CCPS”) provided R.F. with a free appropriate public education (a “FAPE”) under the\n\nIndividuals with Disabilities Education Act (the “IDEA”), 20 U.S.C. § 1400 et seq.\n\nAppellants contend that CCPS violated the IDEA by (1) failing to educate R.F. in the\n\nleast restrictive environment (the “LRE”), (2) failing to implement R.F.’s Individualized\n\nEducation Program (her “IEP”), (3) denying R.F.’s parents the opportunity to participate\n\nin her educational decisionmaking, and (4) providing an IEP that was inappropriate for\n\nR.F.’s needs. The ALJ found, and the district court agreed, that while CCPS violated\n\ncertain procedural requirements of the IDEA, those violations did not substantively deny\n\nR.F. a FAPE in violation of the IDEA. For the reasons that follow, we affirm.\n\n\n\n I.\n\n R.F., who was seven years old when these proceedings began, is a CCPS student\n\nwith a disability who is entitled to special education and related services under the\n\nIDEA. 1 R.F. and her parents contend that CCPS failed to comply with the IDEA in\n\n\n 1\n All facts are taken from the ALJ’s findings of fact, J.A. 23–51, except where\notherwise indicated. The parties agree that there are no genuine issues of material fact\nwith these findings aside from the finding that R.F.’s behavior intervention plan (the\n“BIP”) is “appropriate to address [her] problem behaviors.” J.A. 28. We address the\nappropriateness of the BIP infra.\n\n 3\n\fseveral respects and that, in so doing, CCPS denied R.F. a FAPE in violation of the\n\nIDEA. Before addressing these arguments, we first provide a brief overview of the\n\napplicable regulatory framework and the facts and procedural history of this case.\n\n\n\n A.\n\n The IDEA provides funds for states to educate children with disabilities, subject to\n\nconditions imposing substantive requirements on the education that is provided. 20\n\nU.S.C. § 1412. The statute was enacted to ensure that children with disabilities have\n\naccess to an education that meets their unique needs, to protect the rights of these\n\nchildren and their parents, and to prevent the unnecessary exclusion of these children\n\n“from the public school system and from being educated with their peers.” 2 Id. § 1400.\n\n To that end, the IDEA requires that participating states provide a FAPE to children\n\nwith disabilities. Id. § 1412(a)(1). The mechanism by which a state provides a FAPE is\n\nan IEP--a document that describes the child’s unique needs and the state’s plan for\n\nmeeting those needs. See Endrew F. ex rel. Joseph F. v. Douglas Cty. Sch. Dist. RE-1,\n\n137 S. Ct. 988, 994 (2017) (“The IEP is the centerpiece of the [IDEA’s] education\n\ndelivery system for disabled children.”) (citation and internal quotation marks omitted).\n\nThe IDEA requires participating states to “develop[], review[], and revise[]” an IEP for\n\neach child with a disability. 20 U.S.C. § 1412(a)(4). An IEP must contain an assessment\n\n 2\n The IDEA is an updated version of the Education for All Handicapped Children\nAct of 1975, Pub. L. No. 94-142, 89 Stat. 773 (1975) (current version at 20 U.S.C. § 1400\net seq.), under which some of the caselaw setting out IDEA requirements was initially\ndeveloped.\n\n 4\n\fof the child’s “present levels of academic achievement and functional performance,”\n\nmeasurable annual goals that are designed to “meet the child’s needs that result from the\n\nchild’s disability” along with a statement of how progress toward those goals will be\n\nmeasured, a description of “the special education and related services and supplementary\n\naids and services” that the school will provide for the child, and an “explanation of the\n\nextent[] . . . to which the child will not participate with nondisabled children in the\n\nregular class.” Id. § 1414(d)(1)(A)(i). The IEP team--a group comprised mainly of\n\nschool staff and a child’s parents--should revise the IEP “as appropriate” to address\n\nvarious circumstances, including a “lack of expected progress towards the annual goals”;\n\n“the results of any reevaluation”; “information about the child provided to, or by, the\n\nparents”; “the child’s anticipated needs”; or “other matters.” Id. § 1414(d)(4)(A). The\n\nIDEA requires that a child’s parents be included in the IEP decisionmaking process as\n\nmembers of the IEP team. Id. § 1414(d)(1)(B).\n\n\n\n B.\n\n R.F. has been diagnosed with severe autism spectrum disorder and a rare genetic\n\ndisorder. 3 She generally communicates without using words, and she “exhibits complex,\n\nchallenging, disruptive behaviors” such as hyperactivity and aggression. J.A. 24. Her\n\naggressive behaviors, which include “grabbing people, pulling hair, biting, and placing\n\n\n 3\n R.F. was one of only two people in the world diagnosed with this disorder when\nshe received that diagnosis. The long-term consequences of this disorder, including its\nimpact on R.F.’s educational potential, are unknown.\n\n 5\n\fher mouth on others,” often manifest during transitions in the school day. Id. R.F. also\n\nexhibits physical limitations--for instance, she has significant neuromuscular deficits, so\n\nshe sometimes needs assistance sitting up straight and being aware of her body’s position\n\nwhen navigating steps and curbs. R.F. “requires adult supervision and assistance at all\n\ntimes.” Id. She also has a short attention span and has difficulty processing information\n\nquickly.\n\n CCPS first identified R.F. as a student qualifying for special education and related\n\nservices when she was two years old. It developed IEPs for R.F. for half-day\n\nkindergarten in the 2014–2015 school year and for full-day kindergarten in the 2015–\n\n2016 school year.\n\n Before R.F. entered first grade, CCPS took steps to address R.F.’s behavioral\n\nissues. CCPS hired a consultant from the Kennedy Krieger Institute to instruct its staff\n\non conducting functional behavior assessments (“FBAs”) for students with significant\n\ndisabilities and autism. CCPS staff conducted an FBA for R.F. in April 2016 and created\n\na behavior intervention plan (a “BIP”) for her that focused on biting as her primary\n\ninterfering behavior.\n\n The BIP set out actions for CCPS staff to take to reduce R.F.’s unwanted biting\n\nand to intervene when she began to bite. Steps to reduce R.F.’s biting included ensuring\n\nthat R.F.’s NovaChat (a device that allows R.F. to press pictures on a screen to\n\ncommunicate) was accessible to her at all times, maintaining a “clear and consistent daily\n\nroutine” and a visual schedule to ease transitions during the day, reminding R.F. of\n\nappropriate behaviors by presenting social stories to her throughout the day, providing\n\n 6\n\fR.F. with “short verbal instructions with visual supports,” and using a token\n\nreinforcement system. J.A. 29. Steps to intervene when R.F. began to bite included\n\nredirecting R.F. to her NovaChat, to appropriate oral stimulation items, or to vibration\n\ntools meant to calm R.F., followed by reviewing social stories to remind R.F. why biting\n\nis inappropriate.\n\n As relevant to the dispute on appeal, R.F.’s IEP team--comprised primarily of\n\nCCPS staff and R.F.’s parents--met in May 2016 to revise her IEP for the 2016–2017 first\n\ngrade school year (the “May 2016 IEP”). The May 2016 IEP incorporated R.F.’s BIP. It\n\nalso included thirteen goals to address R.F.’s academic, behavioral, physical, and speech\n\nand language needs. The IEP team determined that to make progress on these goals, R.F.\n\nwould require sixteen hours and fifty-five minutes outside the general education setting\n\nand fourteen hours and thirty-five minutes inside the general education setting each week.\n\n R.F.’s mother attended this meeting and objected to the May 2016 IEP. She did\n\nnot think that R.F. should be included in classes with nondisabled peers and requested\n\nthat CCPS pay for R.F.’s tuition at the Benedictine School, a private school. The other\n\nmembers of R.F.’s IEP team disagreed and noted that CCPS was developing an intensive\n\ncommunication support classroom (an “ICSC”) for children with communicative\n\ndifficulties. The IEP team again met in June 2016 to evaluate R.F.’s progress on her IEP\n\n\n\n\n 7\n\fgoals before the start of the 2016–2017 school year. Appellants’ arguments on appeal\n\nfocus solely on the 2016–2017 school year. 4\n\n At the start of the 2016–2017 school year, CCPS provided most of R.F.’s special\n\neducation services in the ICSC. Although CCPS anticipated the participation of other\n\nstudents in the ICSC, those students did not attend in the fall of 2016 due to unexpected\n\ncircumstances. Consequently, R.F. was the only student in the ICSC. R.F. joined the\n\ngeneral education classroom for “specials” (e.g. gym, art, music), recess, field trips, and\n\noccasional reading and math classes.\n\n Mr. K., a special education teacher, provided R.F. with special education services\n\nin the ICSC. CCPS also assigned a paraprofessional to support R.F. throughout the day.\n\nIn the ICSC and throughout R.F.’s day, CCPS offered R.F. a number of specialized\n\nservices, including individualized supervision and instruction, and supports. These\n\nsupports included objects meant to help R.F. transition to new activities and locations, a\n\nvisual schedule with verbal cues, and low lighting and reduced noise. CCPS\n\n“implemented the BIP regularly, but not perfectly.” J.A. 44. For instance, while Mr. K.\n\nused the behavior reduction and intervention steps in the BIP, he did not always follow\n\nthem in order. To monitor R.F.’s progress toward her IEP goals, Mr. K. collected data on\n\nR.F.’s behavior and performance every other week and incorporated that data into\n\n\n\n\n 4\n Appellants initially asserted claims arising from the 2014–2015 and 2015–2016\nschool years, but these claims were disposed of by the ALJ below, and Appellants do not\npursue them on appeal.\n\n 8\n\fquarterly progress reports. He destroyed his raw data after writing the quarterly reports,\n\neven though CCPS requires teachers to maintain data for two years.\n\n In August 2016, approximately three weeks after the start of school, Mr. K. began\n\nto notice that R.F. struggled when she joined her nondisabled peers in the general\n\neducation setting. She had difficulty walking between classrooms and staying seated and\n\nquiet in the general education classroom. She also often failed to finish her lunch in the\n\nschool lunchroom because she became distracted.\n\n In response to these difficulties, Mr. K. gradually began providing more\n\ninstruction to R.F. in the ICSC instead of the general education classroom. For instance,\n\nwhile R.F.’s schedule placed her in the general education classroom for reading\n\ncomprehension, Mr. K. would sometimes remove her from that class and take her back to\n\nthe ICSC. This decision varied daily and, according to Mr. K., was “responsive to her\n\nneeds depending on her success in the class.” S.A. 3. 5 On some days, Mr. K. was unable\n\nto take R.F. to the general education classroom “if she was exhibiting really aggressive\n\nbehaviors or if she was having a really difficult time walking or with mobility.” S.A. 4.\n\nAs a result of these adjustments, R.F.’s hours in the ICSC exceeded the number specified\n\nin the May 2016 IEP.\n\n In December 2016, R.F.’s IEP team met again to revise her IEP (the “December\n\n2016 IEP”). The team decided to reduce the number of hours that R.F. spent in the\n\ngeneral education setting so that she would only attend specials with nondisabled peers.\n\n 5\n Citations to the “S.A.” refer to the Supplemental Appendix filed by CCPS in this\nappeal.\n\n 9\n\fAccordingly, the December 2016 IEP increased R.F.’s weekly time outside the general\n\neducation setting from sixteen hours and fifty-five minutes to twenty-nine hours.\n\n R.F.’s parents attended the meeting and opposed CCPS’s approach. R.F.’s mother\n\nagain expressed opposition to placing R.F. in a general education setting “at all during the\n\nschool day.” J.A. 45. R.F.’s parents also presented a report by Lisa Frank, an education\n\nconsultant, who recommended placement in a “full-day evidence-based program for\n\nchildren with autism” like the Benedictine School. Id. The other members of the IEP\n\nteam disagreed with this proposed placement and determined that the ICSC was the best\n\nplacement for R.F.\n\n\n\n C.\n\n Shortly after R.F.’s IEP team compiled the December 2016 IEP, R.F.’s parents\n\ninitiated this action, alleging that CCPS violated the IDEA and seeking to have R.F.\n\nplaced at the Benedictine School or another private school at CCPS’s expense. As\n\nrequired under the IDEA, they first filed a due process complaint with Maryland’s Office\n\nof Administrative Hearings, resulting in a hearing before an ALJ. See 20 U.S.C.\n\n§ 1415(f). The hearing before the ALJ addressed whether CCPS denied R.F. a FAPE or\n\nfailed to offer her an IEP that would provide her with a FAPE during the 2016–2017\n\nschool year.\n\n Mr. K testified at the hearing. As relevant to one of Appellants’ principal claims\n\nconcerning CCPS’s procedural violations of the statute, Mr. K. stated that he was\n\nunaware that CCPS required teachers to maintain raw data for two years. The ALJ\n\n 10\n\fconcluded that he had violated CCPS’s retention policy but “did not do so for any\n\nnefarious purpose,” and she declined to draw any negative inferences from his testimony.\n\nJ.A. 71.\n\n The ALJ also heard evidence regarding how CCPS calculates special education\n\nhours for the purposes of preparing IEPs and recording services provided. She found\n\nthat, while Maryland requires schools to define special education hours in terms of the\n\nnumber of hours a child spends outside the general education classroom, CCPS defines\n\nthem in terms of the number of hours of instruction focused on a child’s IEP goals.\n\nTherefore, the ALJ concluded that experts who testified that R.F.’s IEP contained an\n\ninadequate number of special education hours did so based on a misunderstanding of how\n\nCCPS calculates those hours.\n\n Based on the testimony and data presented at the hearing, the ALJ evaluated R.F.’s\n\nprogress on her IEP goals. She found that R.F. had made progress toward some of her\n\nphysical goals as well as some of her speech and language goals. She also found that\n\nR.F. did not make progress toward her behavioral or academic goals. She concluded that,\n\noverall, R.F. had “made incremental progress on some, but not all of her goals” and that\n\nthis was appropriate for R.F. “given her unique circumstances.” J.A. 86.\n\n The ALJ issued a decision holding that CCPS procedurally violated the IDEA by\n\nchanging R.F.’s placement in August 2016 by gradually increasing her hours in the ICSC\n\nwithout notifying her parents or revising her IEP. She also concluded, however, that this\n\nviolation did not deny R.F. a FAPE, crediting Mr. K.’s testimony that R.F. was having\n\ndifficulty in the general education setting and benefitted from additional time in the\n\n 11\n\fICSC. Overall, the ALJ concluded that “CCPS offered [R.F.] ‘an IEP reasonably\n\ncalculated to [enable her to] make progress appropriate in light of the child’s\n\ncircumstances.’” J.A. 87 (quoting Endrew F., 137 S. Ct. at 999).\n\n Appellants challenged the ALJ’s decision in federal district court, naming as\n\ndefendants CCPS, its superintendent, and its director of special education, in their official\n\ncapacities. 6 The district court granted CCPS’s motion for summary judgment for reasons\n\nsimilar to those stated in the ALJ’s decision. 7 This appeal followed.\n\n\n\n II.\n\n In IDEA cases, we conduct a modified de novo review, “giving ‘due weight’ to the\n\nunderlying administrative proceedings.” M.S. ex rel. Simchick v. Fairfax Cty. Sch. Bd.,\n\n553 F.3d 315, 323 (4th Cir. 2009) (citation omitted). Under our precedent, whether an\n\neducational program offered by the state is appropriate for purposes of the FAPE analysis\n\nis a question of fact.8 We consider an ALJ’s factual findings to be “prima facie correct.”\n\nDoyle v. Arlington Cty. Sch. Bd., 953 F.2d 100, 105 (4th Cir. 1991). However, the\n\n“ultimate decision as to whether the state has complied with the IDEA” is an independent\n\n 6\n Throughout this opinion, we refer to these defendants collectively as “CCPS.”\n 7\n The district judge referred the case to a federal magistrate judge for all\nproceedings and the entry of judgment by consent of the parties, in accordance with 28\nU.S.C. § 636(c).\n 8\n We note, however, that several other circuits treat the issue of whether the school\ndistrict has provided a FAPE as a mixed question of fact and law. See, e.g., K.E. ex rel.\nK.E. v. Indep. Sch. Dist. No. 15, 647 F.3d 795, 804 (8th Cir. 2011) (“Whether a child has\nreceived a FAPE is a mixed question of law and fact.”).\n\n 12\n\fdecision made by the district court. Sumter Cty. Sch. Dist. 17 v. Heffernan ex rel. TH,\n\n642 F.3d 478, 484 (4th Cir. 2011). In making this independent decision, courts should\n\nnot “substitute their own notions of sound educational policy for those of the school\n\nauthorities which they review.” Bd. of Educ. of Hendrick Hudson Cent. Sch. Dist. v.\n\nRowley, 458 U.S. 176, 206 (1982).\n\n\n\n III.\n\n Appellants contend that CCPS violated the IDEA in several respects. Whether a\n\nstate has violated the IDEA has procedural and substantive components. Procedurally,\n\nthe state must comply with the stated requirements of the IDEA. Id. at 206–07.\n\nSubstantively, the state must offer the child a FAPE, which requires a targeted\n\neducational program setting reasonably calculated goals for a child’s progress in light of\n\nthe child’s particular circumstances. Endrew F., 137 S. Ct. at 999.\n\n We first reexamine our precedent in light of the Supreme Court’s recent decision\n\nin Endrew F., 137 S. Ct. 988, clarifying the FAPE standard. We then address Appellants’\n\nspecific contentions regarding CCPS’s compliance with the IDEA.\n\n\n\n A.\n\n To meet the substantive requirements of the IDEA, a school must provide a child\n\nwith a FAPE. M.L. ex rel. Leiman v. Smith, 867 F.3d 487, 499 (4th Cir. 2017). The\n\nSupreme Court recently held in Endrew F. that to satisfy the FAPE requirement, “a\n\n\n\n 13\n\fschool must offer an IEP reasonably calculated to enable a child to make progress\n\nappropriate in light of the child’s circumstances.” 137 S. Ct. at 999.\n\n In establishing this standard, the Court rejected the Tenth Circuit’s approach,\n\nwhich held that the education and services provided to children with disabilities “must be\n\ncalculated to confer some educational benefit” to meet the FAPE requirement and that a\n\nchild’s IEP “is adequate as long as it is calculated to confer an educational benefit that is\n\nmerely more than de minimis” (the “de minimis standard”). Id. at 997 (alterations,\n\ncitation, and internal quotation marks omitted). Before Endrew F., we required schools\n\nto provide “some educational benefit” to a child to meet their substantive obligation to\n\nprovide the child with a FAPE. See O.S. v. Fairfax Cty. Sch. Bd., 804 F.3d 354, 358 (4th\n\nCir. 2015) (quoting Rowley, 458 U.S. at 200) (collecting cases). This prior standard is\n\nsimilar to the Tenth Circuit’s de minimis standard, and we clarify again that it is no\n\nlonger good law. See M.L., 867 F.3d at 496 (acknowledging that “[o]ur prior FAPE\n\nstandard is similar to that of the Tenth Circuit, which was overturned by Endrew F.”).\n\n Instead, we follow the Court’s standard as articulated in Endrew F. and hold that\n\n“[t]o meet its substantive obligation under the IDEA, a school must offer an IEP\n\nreasonably calculated to enable a child to make progress appropriate in light of the child’s\n\ncircumstances.” 9 Endrew F., 137 S. Ct. at 999. This standard is framed in terms of each\n\n\n 9\n Indeed, we implicitly did so in T.B., Jr. ex rel. T.B., Sr. v. Prince George’s\nCounty Board of Education, 897 F.3d 566 (4th Cir. 2018). In that case, we held that a\nschool board procedurally violated the IDEA by failing to promptly evaluate a child for\nspecial education. Id. at 573. We concluded, however, that the school did not\nsubstantively violate the IDEA because its failure did not deny the child a FAPE. Id. at\n(Continued)\n 14\n\fchild’s unique circumstances because “[a] focus on the particular child is at the core of\n\nthe IDEA.” Id. Consequently, “the benefits obtainable by children at one end of the\n\nspectrum [of disability] will differ dramatically from those obtainable by children at the\n\nother end, with infinite variations in between.” Id. (quoting Rowley, 458 U.S. at 202).\n\nOur analysis is therefore grounded in each particular child’s circumstances.\n\n\n\n B.\n\n Having established the relevant standard for the FAPE requirement, we turn to the\n\nissues on appeal in this case. In sum, we hold that CCPS did violate certain procedural\n\nrequirements of the IDEA, most notably by changing R.F.’s placement without notifying\n\nher parents or modifying her IEP. However, any procedural violations did not deny R.F.\n\na FAPE.\n\n Appellants contend that CCPS violated the IDEA in four respects: (1) by failing to\n\neducate R.F. in the LRE, (2) by failing to implement the classroom placement in R.F.’s\n\nIEP when Mr. K. increased her hours in the ICSC, (3) by denying R.F.’s parents the right\n\nto participate in her education, and (4) by failing to provide an IEP appropriate for R.F.’s\n\nneeds. We address each issue in turn.\n\n\n\n\n575. In doing so, we quoted Endrew F.’s standard to explain the substantive requirement\nof the IDEA, but it was not central to our holding because the case did not turn on\nwhether the child’s IEP was reasonably calculated to provide the child with a FAPE. See\nid. at 571.\n\n 15\n\f 1.\n\n Appellants contend that CCPS failed to educate R.F. in the LRE because it\n\nprovided her most of her instruction in the ICSC, where R.F. was the only student. They\n\nseek an order placing R.F. at a private school where she would be educated among peers\n\nwith disabilities. We reject this contention.\n\n The IDEA requires participating states to educate children with disabilities in the\n\nLRE--that is, alongside children who are not disabled “[t]o the maximum extent\n\nappropriate.” 20 U.S.C. § 1412(a)(5). It permits states to remove a child with disabilities\n\nfrom the “regular educational environment . . . only when the nature or severity of the\n\ndisability of a child is such that education in regular classes [with appropriate supports]\n\ncannot be achieved satisfactorily.” Id. We have acknowledged that this statutory\n\nlanguage “obviously indicates a strong congressional preference for mainstreaming”\n\nstudents into the general education classroom but that “[m]ainstreaming . . . is not\n\nappropriate for every [child with a disability].” DeVries ex rel. DeBlaay v. Fairfax Cty.\n\nSch. Bd., 882 F.2d 876, 878 (4th Cir. 1989). Instead, “[t]he proper inquiry is whether a\n\nproposed placement is appropriate under the [IDEA]”--in other words, whether a child’s\n\nplacement--the setting where the child learns--provides the child with a FAPE. Id.\n\n(citation omitted).\n\n Here, placement in the ICSC was “reasonably calculated to enable [R.F.] to make\n\nprogress appropriate in light of [her] circumstances.” Endrew F., 137 S. Ct. at 999. The\n\nALJ’s analysis here is instructive; she noted that “CCPS was not hiding [R.F.] from her\n\n 16\n\fpeers; [R.F.] was afforded opportunities to interact with other first graders, albeit not to\n\nthe degree CCPS would have preferred.” J.A. 73–74. Indeed, while R.F. received most\n\nof her instruction in the ICSC, CCPS gave her multiple daily opportunities to interact\n\nwith her nondisabled peers. For instance, she attended specials with the general\n\neducation population and walked around the school each day to practice greeting other\n\nstudents. These opportunities, combined with R.F.’s instructional time in the ICSC, did\n\nnot deny R.F. a FAPE, particularly where Mr. K. noted that R.F. had trouble\n\nconcentrating and accessing material in the general education population. R.F. had\n\nopportunities to interact with her peers “[t]o the maximum extent appropriate,” given\n\nR.F.’s unique circumstances and academic and behavioral needs. 20 U.S.C. § 1412(a)(5).\n\n Appellants argue that the conclusions of the ALJ and the district court regarding\n\nR.F.’s placement improperly conflate the LRE and FAPE requirements. However, as\n\nthey themselves recognize, the statutory obligation requires placement in the least\n\nrestrictive environment appropriate for the child’s education. See Devries, 882 F.2d at\n\n880. As in DeVries, that required an environment where R.F. could benefit from “a\n\nstructured program” and the opportunity for “one-to-one instruction.” Id. at 879.\n\n Appellants argue that they are not urging CCPS to increase the number of hours\n\nthat R.F. spends with her peers who are not disabled; instead, they contend that the LRE\n\nfor R.F. would include more time among peers with disabilities, and they seek placement\n\nin a private school to achieve that outcome. This argument miscomprehends the LRE\n\nrequirement, which is defined in terms of the extent to which children with disabilities\n\n“are educated with children who are not disabled.” Id. at 878 (emphasis added). But\n\n 17\n\feven under Appellants’ standard, CCPS did not violate the LRE requirement. Instead, the\n\nALJ correctly noted that “CCPS thought there would be other students in the [ICSC], but\n\nit did not turn out that way” due to unforeseen circumstances. J.A. 73. CCPS cannot be\n\nsaid to have denied R.F. a FAPE merely because fewer students with disabilities enrolled\n\nat R.F.’s school than CCPS anticipated. Accordingly, we agree with the ALJ and the\n\ndistrict court that CCPS did not violate the LRE requirement.\n\n\n\n 2.\n\n Next, Appellants contend that CCPS violated the IDEA by failing to follow R.F.’s\n\nIEP. Specifically, they argue that CCPS failed to implement R.F.’s IEP when Mr. K.\n\nchanged R.F.’s placement and began providing her with more instruction hours in the\n\nICSC than her IEP called for. While this was a procedural violation of the IDEA, we\n\nhold that it was not a substantive violation because R.F. was not denied a FAPE as a\n\nresult.\n\n A school must follow procedures specified in the IDEA before changing the\n\nchild’s placement as identified in her IEP. See 20 U.S.C. § 1415(b)(3) (requiring written\n\nprior notice to the child’s parents before the local education agency may change a child’s\n\neducational placement). Here, CCPS did not follow these procedures before changing\n\nR.F.’s placement. Instead, Mr. K. increased her hours in the ICSC beyond those\n\nspecified in her IEP without giving notice to R.F.’s parents. This constitutes a procedural\n\nviolation.\n\n\n\n 18\n\f However, as we have noted, not all procedural violations of the IDEA result in the\n\ndenial of a FAPE. T.B., Jr., 897 F.3d at 573. Indeed, Mr. K.’s decision to provide R.F.\n\nwith more instruction in the ICSC than her IEP specified was “reasonably calculated to\n\nenable [R.F.] to make progress appropriate in light of [her] circumstances.” Endrew F.,\n\n137 S. Ct. at 999. Mr. K. recognized that R.F. was struggling in the general education\n\nclassroom, and he determined that she would make more progress with more one-on-one\n\ninstruction in the ICSC. He did so on a gradual and individualized basis, based on close\n\nattention to R.F.’s performance in a general education setting and in the ICSC. We\n\nconclude that R.F. received a FAPE when CCPS changed her placement, even though it\n\nfailed to follow the IDEA’s procedural requirements.\n\n\n\n 3.\n\n Appellants also contend that CCPS violated the IDEA by taking certain actions\n\nthat impeded her parents from participating in decisions about her education. The IDEA\n\nand its regulations grant the parents of a child with a disability certain procedural rights,\n\nincluding the right to “examine all records” relating to that child and to “participate in\n\nmeetings with respect to the identification, evaluation, and educational placement” of the\n\nchild. 20 U.S.C. § 1415(b); see 34 C.F.R. § 300.322 (setting out parent participation\n\nregulations for IEP development). The IDEA also “grants parents independent,\n\nenforceable rights” that are not limited to procedural matters, including “the entitlement\n\nto a [FAPE] for the parents’ child.” Winkelman ex rel. Winkelman v. Parma City Sch.\n\nDist., 550 U.S. 516, 533 (2007). We first clarify the grounds on which an ALJ may\n\n 19\n\fdetermine that a violation of parents’ rights under the IDEA resulted in the denial of a\n\nFAPE to a child before turning to Appellants’ contentions here.\n\n\n\n a.\n\n Parents who seek to enforce their rights or the rights of their child under the IDEA\n\nfirst seek review through a due process hearing before an ALJ. 20 U.S.C. § 1415(f). In\n\ngeneral, the ALJ must determine whether a school violated the IDEA by deciding “on\n\nsubstantive grounds . . . whether the child received a [FAPE].” Id. § 1415(f)(3)(E)(i).\n\nHowever, “[i]n matters alleging a procedural violation, an ALJ “may find that a child did\n\nnot receive a [FAPE]” if the ALJ determines that a procedural right was violated and that\n\nthe violation “significantly impeded the parents’ opportunity to participate in the\n\ndecisionmaking process regarding the provision of a [FAPE] to the parents’ child.” Id.\n\n§ 1415(f)(3)(E)(ii)(II).\n\n Under § 1415(f)(3)(E)(ii)(II), an ALJ must answer each of the following in the\n\naffirmative to find that a procedural violation of the parental rights provisions of the\n\nIDEA constitutes a violation of the IDEA: (1) whether the plaintiffs “alleg[ed] a\n\nprocedural violation,” (2) whether that violation “significantly impeded the parents’\n\nopportunity to participate in the decisionmaking process regarding the provision of a\n\n[FAPE] to the parents’ child,” and (3) whether the child “did not receive a [FAPE]” as a\n\nresult. Id. § 1415(f)(3)(E). Unless an ALJ determines that a given procedural violation\n\ndenied the child a FAPE, she may only order compliance with the IDEA’s procedural\n\nrequirements and cannot grant other forms of relief, such as private placement or\n\n 20\n\fcompensatory education. See Fry v. Napoleon Cmty. Schs., 137 S. Ct. 743, 754 n.6\n\n(2017) (“Without finding the denial of a FAPE, a hearing officer may do nothing more\n\nthan order a school district to comply with the [IDEA’s] various procedural\n\nrequirements.”).\n\n\n\n b.\n\n Our analysis here starts and ends with the second prong of this standard: whether a\n\nviolation of parents’ procedural rights under the IDEA “significantly impeded” their\n\nopportunity to participate in decisionmaking regarding their child’s education.\n\nAppellants contend that CCPS violated their parental participation rights under the IDEA\n\nby changing R.F.’s placement without involving them in an IEP meeting and by\n\ndestroying data relating to R.F.’s progress on her IEP goals. We hold that neither\n\nconstitutes a significant impediment to parental participation on these facts.\n\n With respect to changing R.F.’s placement, the parties agree that “Mr. K.’s\n\nunilateral determination to alter the environment in which some of R.F.’s IEP services\n\nwere offered . . . constituted a procedural violation of [the parental rights provisions of]\n\nthe IDEA.” Appellees’ Br. at 17; see 20 U.S.C. § 1415(b)(3).\n\n However, R.F.’s parents’ opportunity to participate in decisionmaking regarding\n\nR.F.’s education was not “significantly impeded” when CCPS changed R.F.’s placement\n\nfor four months without involving her parents. 20 U.S.C. § 1415(f)(3)(E)(ii)(II). As\n\ndiscussed above, in changing R.F.’s placement, CCPS provided her more special\n\neducation services, not fewer, in the ICSC, consistent with her parents’ objection that her\n\n 21\n\fIEP contained too many hours in the general education classroom. CCPS did not\n\nsignificantly impede R.F.’s parents’ participation rights when it failed to inform them that\n\nit was gradually changing R.F.’s placement in line with their expressed wishes.\n\n Additionally, R.F.’s parents did eventually have an opportunity to participate in\n\ndecisions about R.F.’s placement when her mother attended the December 2016 IEP\n\nmeeting. See D.S. v. Bayonne Bd. of Educ., 602 F.3d 553, 565 (3d Cir. 2010) (holding\n\nthat a school district did not violate the IDEA when it ignored parents’ letters for months\n\nbut included the parents in their child’s IEP meeting because “they ultimately had an\n\nopportunity to participate meaningfully in the creation of an IEP” for their child).\n\nTherefore, the only form of relief that Appellants seek--private placement for R.F.--\n\n“cannot reasonably be traced” to CCPS’s failure to include R.F.’s parents in decisions\n\nregarding her placement in August 2016. Id. at 566. We cannot agree with Appellants\n\nthat CCPS’s procedural violation of R.F.’s parents’ right to participate in decisions about\n\nher placement rises to the level of a substantive IDEA violation that could be cured by\n\nprivate placement.\n\n Appellants also contend that CCPS violated their parental rights under the IDEA\n\nwhen Mr. K. destroyed the raw data that he collected on R.F.’s progress before her\n\nparents could review it. However, as the ALJ noted, “the IDEA does not specify how\n\noften a school system should collect data or how long it should be maintained.” J.A. 72.\n\nInstead, it only requires that the IEP describe how the child’s progress toward her goals\n\nwill be measured. 20 U.S.C. § 1414(d)(1)(A)(i)(III). The ALJ found that while Mr. K.\n\nviolated CCPS’s records retention policy, which required him to preserve the data for two\n\n 22\n\fyears, he did not violate the IDEA when he destroyed R.F.’s raw data after making his\n\nquarterly reports. We agree that this was not a procedural violation of the IDEA.\n\n Regardless of whether the data destruction was a procedural violation of the\n\nIDEA, R.F.’s parents could still view summaries of the data in Mr. K.’s quarterly reports.\n\nTherefore, their ability to “participate in the decisionmaking process” regarding R.F.’s\n\neducation was not “significantly impeded.” 20 U.S.C. § 1415(f)(3)(E)(ii)(II).\n\n We in no way minimize the necessity of compliance with the procedural\n\nrequirements of the IDEA, including those pertaining to parental participation. See\n\nDiBuo ex rel. DiBuo v. Bd. of Educ., 309 F.3d 184, 191 (4th Cir. 2002) (explaining, in a\n\ncase before § 1415(f)(3)(E)(ii)(II) was enacted, that “[w]e have no doubt that a\n\nprocedural violation of the IDEA . . . that causes interference with the parents’ ability to\n\nparticipate in the development of their child’s IEP will often actually interfere with the\n\nprovision of a FAPE to that child”). But here, we cannot find that CCPS significantly\n\nimpeded R.F.’s parents’ participation rights when it changed R.F.’s placement and\n\ndestroyed raw data on R.F.’s progress. Accordingly, we affirm that CCPS did not violate\n\nR.F.’s parents’ rights under the IDEA.\n\n\n\n 4.\n\n Finally, Appellants contend that CCPS violated the IDEA because it failed to\n\nprovide R.F. with an IEP that was sufficient to meet her needs, thus denying her a FAPE.\n\nSpecifically, they contend that R.F.’s BIP was insufficient because it primarily focused\n\non biting while ignoring R.F.’s other behaviors, that R.F.’s IEP was inadequate because it\n\n 23\n\flacked a social skills goal, and that R.F.’s IEP contained an insufficient number of hours\n\nof special education instruction to meet her needs. We disagree.\n\n As we have discussed, “[t]o meet its substantive obligation under the IDEA, a\n\nschool must offer an IEP reasonably calculated to enable a child to make progress\n\nappropriate in light of the child’s circumstances.” Endrew F., 137 S. Ct. at 999. Courts\n\nconduct this analysis with an understanding that “crafting an appropriate program of\n\neducation requires a prospective judgment by school officials.” Id.\n\n First, with respect to the BIP, Appellants contend that it rendered R.F.’s IEP\n\ninadequate because it should have addressed behaviors other than biting. 10 However, the\n\nALJ found that, at the time the May 2016 IEP was created, biting was R.F.’s primary\n\nproblem behavior. She also deferred to testimony by Sarah Farr, CCPS’s director of\n\nspecial education, that “[t]he skills set forth in the BIP for the primary behavior [here,\n\nbiting] can be generalized to other behaviors.” J.A. 68–69. Therefore, the behavior\n\nstrategies in the May 2016 IEP were “reasonably calculated” in light of R.F.’s\n\ncircumstances at the time that IEP was created, and CCPS did not deny her a FAPE.\n\nEndrew F., 137 S. Ct. at 999.\n\n Appellants contend that the December 2016 IEP was inadequate because it\n\nincorporated the BIP without revising it to include interventions for R.F.’s other\n\ninterfering behaviors. However, Appellants present no evidence that by the time the IEP\n\n\n 10\n Although the BIP itself is defined by Maryland regulations, see Md. Code Regs.\n§ 13a.08.04.02(B)(1), its incorporation by reference into R.F.’s IEP gives rise to review\nunder the IDEA framework governing the adequacy of IEPs.\n\n 24\n\fteam met to revise R.F.’s IEP in December, CCPS was aware that biting was not R.F.’s\n\nonly interfering behavior. While it is true that Mr. K. testified in March 2017 that if he\n\nwere to develop a new BIP for R.F., it would include biting, hair pulling, grabbing,\n\nhitting, kicking, and scratching, this says nothing about what CCPS knew in December\n\n2016. Without other evidence indicating that CCPS knew in December 2016 that R.F.\n\nneeded interventions for behaviors other than biting, we cannot say that CCPS\n\nprocedurally violated the IDEA by failing to account for those behaviors in her IEP.\n\n Regardless, any error in failing to update the BIP did not deny R.F. a FAPE\n\nbecause CCPS took steps that were “reasonably calculated” to address R.F.’s behavioral\n\nneeds “in light of [her] circumstances.” Id. For instance, Farr testified that R.F.’s\n\nexisting BIP was sufficient to address R.F.’s behaviors. Farr explained that R.F.’s other\n\ninterfering behaviors did not need to be included in a new BIP because “they’re being\n\naddressed in a very appropriate way. [CCPS is] altering the environment to change those\n\nbehaviors.” S.A. 24. Farr emphasized that R.F.’s interfering behaviors, including biting,\n\nhave decreased because CCPS is taking steps to reduce those behaviors. Therefore,\n\nCCPS did not violate the IDEA and deny R.F. a FAPE by failing to address behaviors\n\nother than biting in the BIP that was incorporated in her May 2016 and December 2016\n\nIEPs.\n\n Second, with respect to whether R.F.’s IEP was inadequate because it lacked a\n\nsocial skills goal, the ALJ found that “[R.F.] could benefit if her IEP contained a\n\nmeasurable socialization goal” but noted that “an IEP is not required to contain every\n\ngoal from which a student might benefit.” J.A. 70. She concluded that “[t]aking the IEP\n\n 25\n\fas a whole,” R.F. “was not denied a FAPE due to the lack of a social skills goal in her\n\nIEP.” Id. We agree and note that the IEP did build in opportunities for R.F. to practice\n\nher social skills. For instance, R.F.’s BIP included the use of social stories to remind R.F.\n\nof appropriate social interactions, and her schedule included regular walks around the\n\nbuilding to greet students.\n\n Finally, with respect to whether R.F.’s IEP contained inadequate hours of special\n\neducation, the ALJ correctly noted that, because IEPs are prospective, Appellants cannot\n\nrely on the fact that R.F.’s hours of special education were increased in the December\n\n2016 IEP as evidence that the May 2016 IEP was defective when created. See J.A. 74\n\n(“The appropriateness of the May 2016 IEP must be judged as of the time it was adopted,\n\nnot in December 2016.”). The ALJ also found that Appellants’ experts who testified that\n\nthe May 2016 IEP contained an inadequate number of special education hours did so\n\nunder an incorrect understanding of the way CCPS calculates and records special\n\neducation hours. Appellants offered no other evidence that the May 2016 IEP contained\n\nan inadequate number of special education hours to enable R.F. to “make progress\n\nappropriate in light of the [her] circumstances.” Endrew F., 137 S. Ct. at 999. Therefore,\n\nwe affirm and conclude that the content of R.F.’s IEP was sufficient to provide her with a\n\nFAPE.\n\n\n\n 5.\n\n In sum, although CCPS violated the IDEA in some procedural respects, we affirm\n\nbecause it did not deny R.F. a FAPE. The education that R.F. actually received during\n\n 26\n\fthe 2016–2017 school year reinforces our decision that CCPS provided her with a FAPE.\n\nThe May 2016 IEP set out thirteen goals addressing “all of R.[F.]’s identified special\n\nneeds.” J.A. 35. These goals “focus[ed] on the particular child.” Endrew F., 137 S. Ct.\n\nat 999. The IEP’s use of the ICSC, with its specialized supports to target R.F.’s issues\n\nwith focus and stress, “aim[ed] to enable [her] to make progress,” while its efforts to\n\ninclude R.F. in a general educational setting for specials aimed to avoid unduly isolating\n\nher from her peers at school. Id.\n\n Under this IEP, as the ALJ found, R.F. did make “progress toward achieving some\n\nof the goals on her IEP during the 2016/2017 school year,” although not all of them. J.A.\n\n46. To facilitate her progress, Mr. K. and a paraprofessional worked closely and\n\nconstructively with R.F. throughout the year to determine how to best enable her to make\n\nprogress towards these goals. Such efforts include an ongoing assessment of whether\n\nR.F. was able to make progress in general educational settings.\n\n The IEP did not aim for grade-level advancement through the general curriculum\n\nor for standard letter grades because these were not considered “a reasonable prospect”\n\nfor R.F. Endrew F., 137 S. Ct. at 1000. But this does not indicate a failure to set\n\n“challenging objectives” for R.F. Id. The IEP team also revised the IEP in December\n\n2016 to account for the progress that R.F. had made to date.\n\n This combination of reasonably ambitious goals that were focused on R.F.’s\n\nparticular circumstances and that were pursued through the careful and attentive\n\ninstruction of specialized professionals provided the education that R.F. is entitled to\n\n\n\n 27\n\funder the statute. We therefore conclude that CCPS provided R.F. with a FAPE despite\n\nits procedural violations of the IDEA.\n\n\n\n IV.\n\n Although CCPS procedurally violated the IDEA in certain technical respects, it\n\ndid not substantively violate the IDEA because it did not deny R.F. a FAPE. We\n\ntherefore\n\n AFFIRM.\n\n\n\n\n 28\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: R.F., a Minor Child, BY AND THROUGH Her Parents and Next Friends, E.F. and H.F.; E.F.; H.F., on Their Own Behalves, Plaintiffs - Appellants, v. CECIL COUNTY PUBLIC SCHOOLS, Defendant - Appellee, and D'Ette W. Devine, Superintendent (Officially); Sarah Farr, Director of Special Education (Officially), Defendants. Council of Parent Attorneys and Advocates, Inc. ; Disability Rights Maryland ; National Disability Rights Network ; The Judge David L. Bazelon Center for Mental Health Law, Amici Supporting Appellant.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-03-25\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-1780\\n\\n\\nR.F., a minor child, by and through her PARENTS and next friends, E.F. and H.F.;\\nE.F.; H.F., on their own behalves,\\n\\n Plaintiffs – Appellants,\\n\\n v.\\n\\nCECIL COUNTY PUBLIC SCHOOLS,\\n\\n Defendant – Appellee,\\n\\n and\\n\\nD’ETTE W. DEVINE, Superintendent (officially); SARAH FARR, Director of\\nSpecial Education (officially),\\n\\n Defendants.\\n\\n------------------------------\\n\\nCOUNCIL OF PARENT ATTORNEYS AND ADVOCATES, INC.;\\nDISABILITY RIGHTS MARYLAND; NATIONAL DISABILITY RIGHTS\\nNETWORK; THE JUDGE DAVID L. BAZELON CENTER FOR MENTAL\\nHEALTH LAW,\\n\\n Amici Supporting Appellant.\\n\\n\\nAppeal from the United States District Court for the District of Maryland, at Baltimore.\\nAlbert David Copperthite, Magistrate Judge. (1:17-cv-02203-ADC)\\n\\n\\nArgued: January 29, 2019 Decided: March 25, 2019\\n\\fBefore AGEE and HARRIS, Circuit Judges, and DUNCAN, Senior Circuit Judge.\\n\\n\\nAffirmed by published opinion. Senior Judge Duncan wrote the opinion, in which Judge\\nAgee and Judge Harris joined.\\n\\n\\nARGUED: Wayne Darryl Steedman, STEEDMAN LAW GROUP, Lutherville,\\nMaryland, for Appellants. David Andrew Burkhouse, PESSIN KATZ LAW, P.A.,\\nColumbia, Maryland, for Appellee. Peter J. Anthony, DENTONS US LLP, Washington,\\nD.C., for Amici Curiae. ON BRIEF: Cheryl A. Steele Steedman, STEEDMAN LAW\\nGROUP, Lutherville, Maryland; Kevin Golembiewski, BERNEY & SANG,\\nPhiladelphia, Pennsylvania, for Appellants. Adam E. Konstas, Towson, Maryland,\\nRochelle S. Eisenberg, PESSIN KATZ LAW, P.A., Columbia, Maryland, for Appellee.\\nIra A. Burnim, Lewis Bossing, THE JUDGE DAVID L. BAZELON CENTER FOR\\nMENTAL HEALTH LAW, Washington, D.C.; Richard D. Salgado, Dallas, Texas, A.\\nDavid Mayhall, DENTONS US LLP, Washington, D.C., for Amicus The Judge David L.\\nBazelon Center for Mental Health Law. Selene Almazan-Altobelli, COUNCIL OF\\nPARENT ATTORNEYS AND ADVOCATES, INC., Towson, Maryland, for Amicus\\nCouncil of Parent Attorneys and Advocates, Inc., National Disability Rights Network,\\nand Disability Rights of Maryland.\\n\\n\\n\\n\\n 2\\n\\fDUNCAN, Senior Circuit Judge:\\n\\n R.F., an elementary school student with a disability, and her parents (collectively\\n\\n“Appellants”) challenge the district court’s decision to affirm the determination of a\\n\\nMaryland Administrative Law Judge (an “ALJ”) that Cecil County Public Schools\\n\\n(“CCPS”) provided R.F. with a free appropriate public education (a “FAPE”) under the\\n\\nIndividuals with Disabilities Education Act (the “IDEA”), 20 U.S.C. § 1400 et seq.\\n\\nAppellants contend that CCPS violated the IDEA by (1) failing to educate R.F. in the\\n\\nleast restrictive environment (the “LRE”), (2) failing to implement R.F.’s Individualized\\n\\nEducation Program (her “IEP”), (3) denying R.F.’s parents the opportunity to participate\\n\\nin her educational decisionmaking, and (4) providing an IEP that was inappropriate for\\n\\nR.F.’s needs. The ALJ found, and the district court agreed, that while CCPS violated\\n\\ncertain procedural requirements of the IDEA, those violations did not substantively deny\\n\\nR.F. a FAPE in violation of the IDEA. For the reasons that follow, we affirm.\\n\\n\\n\\n I.\\n\\n R.F., who was seven years old when these proceedings began, is a CCPS student\\n\\nwith a disability who is entitled to special education and related services under the\\n\\nIDEA. 1 R.F. and her parents contend that CCPS failed to comply with the IDEA in\\n\\n\\n 1\\n All facts are taken from the ALJ’s findings of fact, J.A. 23–51, except where\\notherwise indicated. The parties agree that there are no genuine issues of material fact\\nwith these findings aside from the finding that R.F.’s behavior intervention plan (the\\n“BIP”) is “appropriate to address [her] problem behaviors.” J.A. 28. We address the\\nappropriateness of the BIP infra.\\n\\n 3\\n\\fseveral respects and that, in so doing, CCPS denied R.F. a FAPE in violation of the\\n\\nIDEA. Before addressing these arguments, we first provide a brief overview of the\\n\\napplicable regulatory framework and the facts and procedural history of this case.\\n\\n\\n\\n A.\\n\\n The IDEA provides funds for states to educate children with disabilities, subject to\\n\\nconditions imposing substantive requirements on the education that is provided. 20\\n\\nU.S.C. § 1412. The statute was enacted to ensure that children with disabilities have\\n\\naccess to an education that meets their unique needs, to protect the rights of these\\n\\nchildren and their parents, and to prevent the unnecessary exclusion of these children\\n\\n“from the public school system and from being educated with their peers.” 2 Id. § 1400.\\n\\n To that end, the IDEA requires that participating states provide a FAPE to children\\n\\nwith disabilities. Id. § 1412(a)(1). The mechanism by which a state provides a FAPE is\\n\\nan IEP--a document that describes the child’s unique needs and the state’s plan for\\n\\nmeeting those needs. See Endrew F. ex rel. Joseph F. v. Douglas Cty. Sch. Dist. RE-1,\\n\\n137 S. Ct. 988, 994 (2017) (“The IEP is the centerpiece of the [IDEA’s] education\\n\\ndelivery system for disabled children.”) (citation and internal quotation marks omitted).\\n\\nThe IDEA requires participating states to “develop[], review[], and revise[]” an IEP for\\n\\neach child with a disability. 20 U.S.C. § 1412(a)(4). An IEP must contain an assessment\\n\\n 2\\n The IDEA is an updated version of the Education for All Handicapped Children\\nAct of 1975, Pub. L. No. 94-142, 89 Stat. 773 (1975) (current version at 20 U.S.C. § 1400\\net seq.), under which some of the caselaw setting out IDEA requirements was initially\\ndeveloped.\\n\\n 4\\n\\fof the child’s “present levels of academic achievement and functional performance,”\\n\\nmeasurable annual goals that are designed to “meet the child’s needs that result from the\\n\\nchild’s disability” along with a statement of how progress toward those goals will be\\n\\nmeasured, a description of “the special education and related services and supplementary\\n\\naids and services” that the school will provide for the child, and an “explanation of the\\n\\nextent[] . . . to which the child will not participate with nondisabled children in the\\n\\nregular class.” Id. § 1414(d)(1)(A)(i). The IEP team--a group comprised mainly of\\n\\nschool staff and a child’s parents--should revise the IEP “as appropriate” to address\\n\\nvarious circumstances, including a “lack of expected progress towards the annual goals”;\\n\\n“the results of any reevaluation”; “information about the child provided to, or by, the\\n\\nparents”; “the child’s anticipated needs”; or “other matters.” Id. § 1414(d)(4)(A). The\\n\\nIDEA requires that a child’s parents be included in the IEP decisionmaking process as\\n\\nmembers of the IEP team. Id. § 1414(d)(1)(B).\\n\\n\\n\\n B.\\n\\n R.F. has been diagnosed with severe autism spectrum disorder and a rare genetic\\n\\ndisorder. 3 She generally communicates without using words, and she “exhibits complex,\\n\\nchallenging, disruptive behaviors” such as hyperactivity and aggression. J.A. 24. Her\\n\\naggressive behaviors, which include “grabbing people, pulling hair, biting, and placing\\n\\n\\n 3\\n R.F. was one of only two people in the world diagnosed with this disorder when\\nshe received that diagnosis. The long-term consequences of this disorder, including its\\nimpact on R.F.’s educational potential, are unknown.\\n\\n 5\\n\\fher mouth on others,” often manifest during transitions in the school day. Id. R.F. also\\n\\nexhibits physical limitations--for instance, she has significant neuromuscular deficits, so\\n\\nshe sometimes needs assistance sitting up straight and being aware of her body’s position\\n\\nwhen navigating steps and curbs. R.F. “requires adult supervision and assistance at all\\n\\ntimes.” Id. She also has a short attention span and has difficulty processing information\\n\\nquickly.\\n\\n CCPS first identified R.F. as a student qualifying for special education and related\\n\\nservices when she was two years old. It developed IEPs for R.F. for half-day\\n\\nkindergarten in the 2014–2015 school year and for full-day kindergarten in the 2015–\\n\\n2016 school year.\\n\\n Before R.F. entered first grade, CCPS took steps to address R.F.’s behavioral\\n\\nissues. CCPS hired a consultant from the Kennedy Krieger Institute to instruct its staff\\n\\non conducting functional behavior assessments (“FBAs”) for students with significant\\n\\ndisabilities and autism. CCPS staff conducted an FBA for R.F. in April 2016 and created\\n\\na behavior intervention plan (a “BIP”) for her that focused on biting as her primary\\n\\ninterfering behavior.\\n\\n The BIP set out actions for CCPS staff to take to reduce R.F.’s unwanted biting\\n\\nand to intervene when she began to bite. Steps to reduce R.F.’s biting included ensuring\\n\\nthat R.F.’s NovaChat (a device that allows R.F. to press pictures on a screen to\\n\\ncommunicate) was accessible to her at all times, maintaining a “clear and consistent daily\\n\\nroutine” and a visual schedule to ease transitions during the day, reminding R.F. of\\n\\nappropriate behaviors by presenting social stories to her throughout the day, providing\\n\\n 6\\n\\fR.F. with “short verbal instructions with visual supports,” and using a token\\n\\nreinforcement system. J.A. 29. Steps to intervene when R.F. began to bite included\\n\\nredirecting R.F. to her NovaChat, to appropriate oral stimulation items, or to vibration\\n\\ntools meant to calm R.F., followed by reviewing social stories to remind R.F. why biting\\n\\nis inappropriate.\\n\\n As relevant to the dispute on appeal, R.F.’s IEP team--comprised primarily of\\n\\nCCPS staff and R.F.’s parents--met in May 2016 to revise her IEP for the 2016–2017 first\\n\\ngrade school year (the “May 2016 IEP”). The May 2016 IEP incorporated R.F.’s BIP. It\\n\\nalso included thirteen goals to address R.F.’s academic, behavioral, physical, and speech\\n\\nand language needs. The IEP team determined that to make progress on these goals, R.F.\\n\\nwould require sixteen hours and fifty-five minutes outside the general education setting\\n\\nand fourteen hours and thirty-five minutes inside the general education setting each week.\\n\\n R.F.’s mother attended this meeting and objected to the May 2016 IEP. She did\\n\\nnot think that R.F. should be included in classes with nondisabled peers and requested\\n\\nthat CCPS pay for R.F.’s tuition at the Benedictine School, a private school. The other\\n\\nmembers of R.F.’s IEP team disagreed and noted that CCPS was developing an intensive\\n\\ncommunication support classroom (an “ICSC”) for children with communicative\\n\\ndifficulties. The IEP team again met in June 2016 to evaluate R.F.’s progress on her IEP\\n\\n\\n\\n\\n 7\\n\\fgoals before the start of the 2016–2017 school year. Appellants’ arguments on appeal\\n\\nfocus solely on the 2016–2017 school year. 4\\n\\n At the start of the 2016–2017 school year, CCPS provided most of R.F.’s special\\n\\neducation services in the ICSC. Although CCPS anticipated the participation of other\\n\\nstudents in the ICSC, those students did not attend in the fall of 2016 due to unexpected\\n\\ncircumstances. Consequently, R.F. was the only student in the ICSC. R.F. joined the\\n\\ngeneral education classroom for “specials” (e.g. gym, art, music), recess, field trips, and\\n\\noccasional reading and math classes.\\n\\n Mr. K., a special education teacher, provided R.F. with special education services\\n\\nin the ICSC. CCPS also assigned a paraprofessional to support R.F. throughout the day.\\n\\nIn the ICSC and throughout R.F.’s day, CCPS offered R.F. a number of specialized\\n\\nservices, including individualized supervision and instruction, and supports. These\\n\\nsupports included objects meant to help R.F. transition to new activities and locations, a\\n\\nvisual schedule with verbal cues, and low lighting and reduced noise. CCPS\\n\\n“implemented the BIP regularly, but not perfectly.” J.A. 44. For instance, while Mr. K.\\n\\nused the behavior reduction and intervention steps in the BIP, he did not always follow\\n\\nthem in order. To monitor R.F.’s progress toward her IEP goals, Mr. K. collected data on\\n\\nR.F.’s behavior and performance every other week and incorporated that data into\\n\\n\\n\\n\\n 4\\n Appellants initially asserted claims arising from the 2014–2015 and 2015–2016\\nschool years, but these claims were disposed of by the ALJ below, and Appellants do not\\npursue them on appeal.\\n\\n 8\\n\\fquarterly progress reports. He destroyed his raw data after writing the quarterly reports,\\n\\neven though CCPS requires teachers to maintain data for two years.\\n\\n In August 2016, approximately three weeks after the start of school, Mr. K. began\\n\\nto notice that R.F. struggled when she joined her nondisabled peers in the general\\n\\neducation setting. She had difficulty walking between classrooms and staying seated and\\n\\nquiet in the general education classroom. She also often failed to finish her lunch in the\\n\\nschool lunchroom because she became distracted.\\n\\n In response to these difficulties, Mr. K. gradually began providing more\\n\\ninstruction to R.F. in the ICSC instead of the general education classroom. For instance,\\n\\nwhile R.F.’s schedule placed her in the general education classroom for reading\\n\\ncomprehension, Mr. K. would sometimes remove her from that class and take her back to\\n\\nthe ICSC. This decision varied daily and, according to Mr. K., was “responsive to her\\n\\nneeds depending on her success in the class.” S.A. 3. 5 On some days, Mr. K. was unable\\n\\nto take R.F. to the general education classroom “if she was exhibiting really aggressive\\n\\nbehaviors or if she was having a really difficult time walking or with mobility.” S.A. 4.\\n\\nAs a result of these adjustments, R.F.’s hours in the ICSC exceeded the number specified\\n\\nin the May 2016 IEP.\\n\\n In December 2016, R.F.’s IEP team met again to revise her IEP (the “December\\n\\n2016 IEP”). The team decided to reduce the number of hours that R.F. spent in the\\n\\ngeneral education setting so that she would only attend specials with nondisabled peers.\\n\\n 5\\n Citations to the “S.A.” refer to the Supplemental Appendix filed by CCPS in this\\nappeal.\\n\\n 9\\n\\fAccordingly, the December 2016 IEP increased R.F.’s weekly time outside the general\\n\\neducation setting from sixteen hours and fifty-five minutes to twenty-nine hours.\\n\\n R.F.’s parents attended the meeting and opposed CCPS’s approach. R.F.’s mother\\n\\nagain expressed opposition to placing R.F. in a general education setting “at all during the\\n\\nschool day.” J.A. 45. R.F.’s parents also presented a report by Lisa Frank, an education\\n\\nconsultant, who recommended placement in a “full-day evidence-based program for\\n\\nchildren with autism” like the Benedictine School. Id. The other members of the IEP\\n\\nteam disagreed with this proposed placement and determined that the ICSC was the best\\n\\nplacement for R.F.\\n\\n\\n\\n C.\\n\\n Shortly after R.F.’s IEP team compiled the December 2016 IEP, R.F.’s parents\\n\\ninitiated this action, alleging that CCPS violated the IDEA and seeking to have R.F.\\n\\nplaced at the Benedictine School or another private school at CCPS’s expense. As\\n\\nrequired under the IDEA, they first filed a due process complaint with Maryland’s Office\\n\\nof Administrative Hearings, resulting in a hearing before an ALJ. See 20 U.S.C.\\n\\n§ 1415(f). The hearing before the ALJ addressed whether CCPS denied R.F. a FAPE or\\n\\nfailed to offer her an IEP that would provide her with a FAPE during the 2016–2017\\n\\nschool year.\\n\\n Mr. K testified at the hearing. As relevant to one of Appellants’ principal claims\\n\\nconcerning CCPS’s procedural violations of the statute, Mr. K. stated that he was\\n\\nunaware that CCPS required teachers to maintain raw data for two years. The ALJ\\n\\n 10\\n\\fconcluded that he had violated CCPS’s retention policy but “did not do so for any\\n\\nnefarious purpose,” and she declined to draw any negative inferences from his testimony.\\n\\nJ.A. 71.\\n\\n The ALJ also heard evidence regarding how CCPS calculates special education\\n\\nhours for the purposes of preparing IEPs and recording services provided. She found\\n\\nthat, while Maryland requires schools to define special education hours in terms of the\\n\\nnumber of hours a child spends outside the general education classroom, CCPS defines\\n\\nthem in terms of the number of hours of instruction focused on a child’s IEP goals.\\n\\nTherefore, the ALJ concluded that experts who testified that R.F.’s IEP contained an\\n\\ninadequate number of special education hours did so based on a misunderstanding of how\\n\\nCCPS calculates those hours.\\n\\n Based on the testimony and data presented at the hearing, the ALJ evaluated R.F.’s\\n\\nprogress on her IEP goals. She found that R.F. had made progress toward some of her\\n\\nphysical goals as well as some of her speech and language goals. She also found that\\n\\nR.F. did not make progress toward her behavioral or academic goals. She concluded that,\\n\\noverall, R.F. had “made incremental progress on some, but not all of her goals” and that\\n\\nthis was appropriate for R.F. “given her unique circumstances.” J.A. 86.\\n\\n The ALJ issued a decision holding that CCPS procedurally violated the IDEA by\\n\\nchanging R.F.’s placement in August 2016 by gradually increasing her hours in the ICSC\\n\\nwithout notifying her parents or revising her IEP. She also concluded, however, that this\\n\\nviolation did not deny R.F. a FAPE, crediting Mr. K.’s testimony that R.F. was having\\n\\ndifficulty in the general education setting and benefitted from additional time in the\\n\\n 11\\n\\fICSC. Overall, the ALJ concluded that “CCPS offered [R.F.] ‘an IEP reasonably\\n\\ncalculated to [enable her to] make progress appropriate in light of the child’s\\n\\ncircumstances.’” J.A. 87 (quoting Endrew F., 137 S. Ct. at 999).\\n\\n Appellants challenged the ALJ’s decision in federal district court, naming as\\n\\ndefendants CCPS, its superintendent, and its director of special education, in their official\\n\\ncapacities. 6 The district court granted CCPS’s motion for summary judgment for reasons\\n\\nsimilar to those stated in the ALJ’s decision. 7 This appeal followed.\\n\\n\\n\\n II.\\n\\n In IDEA cases, we conduct a modified de novo review, “giving ‘due weight’ to the\\n\\nunderlying administrative proceedings.” M.S. ex rel. Simchick v. Fairfax Cty. Sch. Bd.,\\n\\n553 F.3d 315, 323 (4th Cir. 2009) (citation omitted). Under our precedent, whether an\\n\\neducational program offered by the state is appropriate for purposes of the FAPE analysis\\n\\nis a question of fact.8 We consider an ALJ’s factual findings to be “prima facie correct.”\\n\\nDoyle v. Arlington Cty. Sch. Bd., 953 F.2d 100, 105 (4th Cir. 1991). However, the\\n\\n“ultimate decision as to whether the state has complied with the IDEA” is an independent\\n\\n 6\\n Throughout this opinion, we refer to these defendants collectively as “CCPS.”\\n 7\\n The district judge referred the case to a federal magistrate judge for all\\nproceedings and the entry of judgment by consent of the parties, in accordance with 28\\nU.S.C. § 636(c).\\n 8\\n We note, however, that several other circuits treat the issue of whether the school\\ndistrict has provided a FAPE as a mixed question of fact and law. See, e.g., K.E. ex rel.\\nK.E. v. Indep. Sch. Dist. No. 15, 647 F.3d 795, 804 (8th Cir. 2011) (“Whether a child has\\nreceived a FAPE is a mixed question of law and fact.”).\\n\\n 12\\n\\fdecision made by the district court. Sumter Cty. Sch. Dist. 17 v. Heffernan ex rel. TH,\\n\\n642 F.3d 478, 484 (4th Cir. 2011). In making this independent decision, courts should\\n\\nnot “substitute their own notions of sound educational policy for those of the school\\n\\nauthorities which they review.” Bd. of Educ. of Hendrick Hudson Cent. Sch. Dist. v.\\n\\nRowley, 458 U.S. 176, 206 (1982).\\n\\n\\n\\n III.\\n\\n Appellants contend that CCPS violated the IDEA in several respects. Whether a\\n\\nstate has violated the IDEA has procedural and substantive components. Procedurally,\\n\\nthe state must comply with the stated requirements of the IDEA. Id. at 206–07.\\n\\nSubstantively, the state must offer the child a FAPE, which requires a targeted\\n\\neducational program setting reasonably calculated goals for a child’s progress in light of\\n\\nthe child’s particular circumstances. Endrew F., 137 S. Ct. at 999.\\n\\n We first reexamine our precedent in light of the Supreme Court’s recent decision\\n\\nin Endrew F., 137 S. Ct. 988, clarifying the FAPE standard. We then address Appellants’\\n\\nspecific contentions regarding CCPS’s compliance with the IDEA.\\n\\n\\n\\n A.\\n\\n To meet the substantive requirements of the IDEA, a school must provide a child\\n\\nwith a FAPE. M.L. ex rel. Leiman v. Smith, 867 F.3d 487, 499 (4th Cir. 2017). The\\n\\nSupreme Court recently held in Endrew F. that to satisfy the FAPE requirement, “a\\n\\n\\n\\n 13\\n\\fschool must offer an IEP reasonably calculated to enable a child to make progress\\n\\nappropriate in light of the child’s circumstances.” 137 S. Ct. at 999.\\n\\n In establishing this standard, the Court rejected the Tenth Circuit’s approach,\\n\\nwhich held that the education and services provided to children with disabilities “must be\\n\\ncalculated to confer some educational benefit” to meet the FAPE requirement and that a\\n\\nchild’s IEP “is adequate as long as it is calculated to confer an educational benefit that is\\n\\nmerely more than de minimis” (the “de minimis standard”). Id. at 997 (alterations,\\n\\ncitation, and internal quotation marks omitted). Before Endrew F., we required schools\\n\\nto provide “some educational benefit” to a child to meet their substantive obligation to\\n\\nprovide the child with a FAPE. See O.S. v. Fairfax Cty. Sch. Bd., 804 F.3d 354, 358 (4th\\n\\nCir. 2015) (quoting Rowley, 458 U.S. at 200) (collecting cases). This prior standard is\\n\\nsimilar to the Tenth Circuit’s de minimis standard, and we clarify again that it is no\\n\\nlonger good law. See M.L., 867 F.3d at 496 (acknowledging that “[o]ur prior FAPE\\n\\nstandard is similar to that of the Tenth Circuit, which was overturned by Endrew F.”).\\n\\n Instead, we follow the Court’s standard as articulated in Endrew F. and hold that\\n\\n“[t]o meet its substantive obligation under the IDEA, a school must offer an IEP\\n\\nreasonably calculated to enable a child to make progress appropriate in light of the child’s\\n\\ncircumstances.” 9 Endrew F., 137 S. Ct. at 999. This standard is framed in terms of each\\n\\n\\n 9\\n Indeed, we implicitly did so in T.B., Jr. ex rel. T.B., Sr. v. Prince George’s\\nCounty Board of Education, 897 F.3d 566 (4th Cir. 2018). In that case, we held that a\\nschool board procedurally violated the IDEA by failing to promptly evaluate a child for\\nspecial education. Id. at 573. We concluded, however, that the school did not\\nsubstantively violate the IDEA because its failure did not deny the child a FAPE. Id. at\\n(Continued)\\n 14\\n\\fchild’s unique circumstances because “[a] focus on the particular child is at the core of\\n\\nthe IDEA.” Id. Consequently, “the benefits obtainable by children at one end of the\\n\\nspectrum [of disability] will differ dramatically from those obtainable by children at the\\n\\nother end, with infinite variations in between.” Id. (quoting Rowley, 458 U.S. at 202).\\n\\nOur analysis is therefore grounded in each particular child’s circumstances.\\n\\n\\n\\n B.\\n\\n Having established the relevant standard for the FAPE requirement, we turn to the\\n\\nissues on appeal in this case. In sum, we hold that CCPS did violate certain procedural\\n\\nrequirements of the IDEA, most notably by changing R.F.’s placement without notifying\\n\\nher parents or modifying her IEP. However, any procedural violations did not deny R.F.\\n\\na FAPE.\\n\\n Appellants contend that CCPS violated the IDEA in four respects: (1) by failing to\\n\\neducate R.F. in the LRE, (2) by failing to implement the classroom placement in R.F.’s\\n\\nIEP when Mr. K. increased her hours in the ICSC, (3) by denying R.F.’s parents the right\\n\\nto participate in her education, and (4) by failing to provide an IEP appropriate for R.F.’s\\n\\nneeds. We address each issue in turn.\\n\\n\\n\\n\\n575. In doing so, we quoted Endrew F.’s standard to explain the substantive requirement\\nof the IDEA, but it was not central to our holding because the case did not turn on\\nwhether the child’s IEP was reasonably calculated to provide the child with a FAPE. See\\nid. at 571.\\n\\n 15\\n\\f 1.\\n\\n Appellants contend that CCPS failed to educate R.F. in the LRE because it\\n\\nprovided her most of her instruction in the ICSC, where R.F. was the only student. They\\n\\nseek an order placing R.F. at a private school where she would be educated among peers\\n\\nwith disabilities. We reject this contention.\\n\\n The IDEA requires participating states to educate children with disabilities in the\\n\\nLRE--that is, alongside children who are not disabled “[t]o the maximum extent\\n\\nappropriate.” 20 U.S.C. § 1412(a)(5). It permits states to remove a child with disabilities\\n\\nfrom the “regular educational environment . . . only when the nature or severity of the\\n\\ndisability of a child is such that education in regular classes [with appropriate supports]\\n\\ncannot be achieved satisfactorily.” Id. We have acknowledged that this statutory\\n\\nlanguage “obviously indicates a strong congressional preference for mainstreaming”\\n\\nstudents into the general education classroom but that “[m]ainstreaming . . . is not\\n\\nappropriate for every [child with a disability].” DeVries ex rel. DeBlaay v. Fairfax Cty.\\n\\nSch. Bd., 882 F.2d 876, 878 (4th Cir. 1989). Instead, “[t]he proper inquiry is whether a\\n\\nproposed placement is appropriate under the [IDEA]”--in other words, whether a child’s\\n\\nplacement--the setting where the child learns--provides the child with a FAPE. Id.\\n\\n(citation omitted).\\n\\n Here, placement in the ICSC was “reasonably calculated to enable [R.F.] to make\\n\\nprogress appropriate in light of [her] circumstances.” Endrew F., 137 S. Ct. at 999. The\\n\\nALJ’s analysis here is instructive; she noted that “CCPS was not hiding [R.F.] from her\\n\\n 16\\n\\fpeers; [R.F.] was afforded opportunities to interact with other first graders, albeit not to\\n\\nthe degree CCPS would have preferred.” J.A. 73–74. Indeed, while R.F. received most\\n\\nof her instruction in the ICSC, CCPS gave her multiple daily opportunities to interact\\n\\nwith her nondisabled peers. For instance, she attended specials with the general\\n\\neducation population and walked around the school each day to practice greeting other\\n\\nstudents. These opportunities, combined with R.F.’s instructional time in the ICSC, did\\n\\nnot deny R.F. a FAPE, particularly where Mr. K. noted that R.F. had trouble\\n\\nconcentrating and accessing material in the general education population. R.F. had\\n\\nopportunities to interact with her peers “[t]o the maximum extent appropriate,” given\\n\\nR.F.’s unique circumstances and academic and behavioral needs. 20 U.S.C. § 1412(a)(5).\\n\\n Appellants argue that the conclusions of the ALJ and the district court regarding\\n\\nR.F.’s placement improperly conflate the LRE and FAPE requirements. However, as\\n\\nthey themselves recognize, the statutory obligation requires placement in the least\\n\\nrestrictive environment appropriate for the child’s education. See Devries, 882 F.2d at\\n\\n880. As in DeVries, that required an environment where R.F. could benefit from “a\\n\\nstructured program” and the opportunity for “one-to-one instruction.” Id. at 879.\\n\\n Appellants argue that they are not urging CCPS to increase the number of hours\\n\\nthat R.F. spends with her peers who are not disabled; instead, they contend that the LRE\\n\\nfor R.F. would include more time among peers with disabilities, and they seek placement\\n\\nin a private school to achieve that outcome. This argument miscomprehends the LRE\\n\\nrequirement, which is defined in terms of the extent to which children with disabilities\\n\\n“are educated with children who are not disabled.” Id. at 878 (emphasis added). But\\n\\n 17\\n\\feven under Appellants’ standard, CCPS did not violate the LRE requirement. Instead, the\\n\\nALJ correctly noted that “CCPS thought there would be other students in the [ICSC], but\\n\\nit did not turn out that way” due to unforeseen circumstances. J.A. 73. CCPS cannot be\\n\\nsaid to have denied R.F. a FAPE merely because fewer students with disabilities enrolled\\n\\nat R.F.’s school than CCPS anticipated. Accordingly, we agree with the ALJ and the\\n\\ndistrict court that CCPS did not violate the LRE requirement.\\n\\n\\n\\n 2.\\n\\n Next, Appellants contend that CCPS violated the IDEA by failing to follow R.F.’s\\n\\nIEP. Specifically, they argue that CCPS failed to implement R.F.’s IEP when Mr. K.\\n\\nchanged R.F.’s placement and began providing her with more instruction hours in the\\n\\nICSC than her IEP called for. While this was a procedural violation of the IDEA, we\\n\\nhold that it was not a substantive violation because R.F. was not denied a FAPE as a\\n\\nresult.\\n\\n A school must follow procedures specified in the IDEA before changing the\\n\\nchild’s placement as identified in her IEP. See 20 U.S.C. § 1415(b)(3) (requiring written\\n\\nprior notice to the child’s parents before the local education agency may change a child’s\\n\\neducational placement). Here, CCPS did not follow these procedures before changing\\n\\nR.F.’s placement. Instead, Mr. K. increased her hours in the ICSC beyond those\\n\\nspecified in her IEP without giving notice to R.F.’s parents. This constitutes a procedural\\n\\nviolation.\\n\\n\\n\\n 18\\n\\f However, as we have noted, not all procedural violations of the IDEA result in the\\n\\ndenial of a FAPE. T.B., Jr., 897 F.3d at 573. Indeed, Mr. K.’s decision to provide R.F.\\n\\nwith more instruction in the ICSC than her IEP specified was “reasonably calculated to\\n\\nenable [R.F.] to make progress appropriate in light of [her] circumstances.” Endrew F.,\\n\\n137 S. Ct. at 999. Mr. K. recognized that R.F. was struggling in the general education\\n\\nclassroom, and he determined that she would make more progress with more one-on-one\\n\\ninstruction in the ICSC. He did so on a gradual and individualized basis, based on close\\n\\nattention to R.F.’s performance in a general education setting and in the ICSC. We\\n\\nconclude that R.F. received a FAPE when CCPS changed her placement, even though it\\n\\nfailed to follow the IDEA’s procedural requirements.\\n\\n\\n\\n 3.\\n\\n Appellants also contend that CCPS violated the IDEA by taking certain actions\\n\\nthat impeded her parents from participating in decisions about her education. The IDEA\\n\\nand its regulations grant the parents of a child with a disability certain procedural rights,\\n\\nincluding the right to “examine all records” relating to that child and to “participate in\\n\\nmeetings with respect to the identification, evaluation, and educational placement” of the\\n\\nchild. 20 U.S.C. § 1415(b); see 34 C.F.R. § 300.322 (setting out parent participation\\n\\nregulations for IEP development). The IDEA also “grants parents independent,\\n\\nenforceable rights” that are not limited to procedural matters, including “the entitlement\\n\\nto a [FAPE] for the parents’ child.” Winkelman ex rel. Winkelman v. Parma City Sch.\\n\\nDist., 550 U.S. 516, 533 (2007). We first clarify the grounds on which an ALJ may\\n\\n 19\\n\\fdetermine that a violation of parents’ rights under the IDEA resulted in the denial of a\\n\\nFAPE to a child before turning to Appellants’ contentions here.\\n\\n\\n\\n a.\\n\\n Parents who seek to enforce their rights or the rights of their child under the IDEA\\n\\nfirst seek review through a due process hearing before an ALJ. 20 U.S.C. § 1415(f). In\\n\\ngeneral, the ALJ must determine whether a school violated the IDEA by deciding “on\\n\\nsubstantive grounds . . . whether the child received a [FAPE].” Id. § 1415(f)(3)(E)(i).\\n\\nHowever, “[i]n matters alleging a procedural violation, an ALJ “may find that a child did\\n\\nnot receive a [FAPE]” if the ALJ determines that a procedural right was violated and that\\n\\nthe violation “significantly impeded the parents’ opportunity to participate in the\\n\\ndecisionmaking process regarding the provision of a [FAPE] to the parents’ child.” Id.\\n\\n§ 1415(f)(3)(E)(ii)(II).\\n\\n Under § 1415(f)(3)(E)(ii)(II), an ALJ must answer each of the following in the\\n\\naffirmative to find that a procedural violation of the parental rights provisions of the\\n\\nIDEA constitutes a violation of the IDEA: (1) whether the plaintiffs “alleg[ed] a\\n\\nprocedural violation,” (2) whether that violation “significantly impeded the parents’\\n\\nopportunity to participate in the decisionmaking process regarding the provision of a\\n\\n[FAPE] to the parents’ child,” and (3) whether the child “did not receive a [FAPE]” as a\\n\\nresult. Id. § 1415(f)(3)(E). Unless an ALJ determines that a given procedural violation\\n\\ndenied the child a FAPE, she may only order compliance with the IDEA’s procedural\\n\\nrequirements and cannot grant other forms of relief, such as private placement or\\n\\n 20\\n\\fcompensatory education. See Fry v. Napoleon Cmty. Schs., 137 S. Ct. 743, 754 n.6\\n\\n(2017) (“Without finding the denial of a FAPE, a hearing officer may do nothing more\\n\\nthan order a school district to comply with the [IDEA’s] various procedural\\n\\nrequirements.”).\\n\\n\\n\\n b.\\n\\n Our analysis here starts and ends with the second prong of this standard: whether a\\n\\nviolation of parents’ procedural rights under the IDEA “significantly impeded” their\\n\\nopportunity to participate in decisionmaking regarding their child’s education.\\n\\nAppellants contend that CCPS violated their parental participation rights under the IDEA\\n\\nby changing R.F.’s placement without involving them in an IEP meeting and by\\n\\ndestroying data relating to R.F.’s progress on her IEP goals. We hold that neither\\n\\nconstitutes a significant impediment to parental participation on these facts.\\n\\n With respect to changing R.F.’s placement, the parties agree that “Mr. K.’s\\n\\nunilateral determination to alter the environment in which some of R.F.’s IEP services\\n\\nwere offered . . . constituted a procedural violation of [the parental rights provisions of]\\n\\nthe IDEA.” Appellees’ Br. at 17; see 20 U.S.C. § 1415(b)(3).\\n\\n However, R.F.’s parents’ opportunity to participate in decisionmaking regarding\\n\\nR.F.’s education was not “significantly impeded” when CCPS changed R.F.’s placement\\n\\nfor four months without involving her parents. 20 U.S.C. § 1415(f)(3)(E)(ii)(II). As\\n\\ndiscussed above, in changing R.F.’s placement, CCPS provided her more special\\n\\neducation services, not fewer, in the ICSC, consistent with her parents’ objection that her\\n\\n 21\\n\\fIEP contained too many hours in the general education classroom. CCPS did not\\n\\nsignificantly impede R.F.’s parents’ participation rights when it failed to inform them that\\n\\nit was gradually changing R.F.’s placement in line with their expressed wishes.\\n\\n Additionally, R.F.’s parents did eventually have an opportunity to participate in\\n\\ndecisions about R.F.’s placement when her mother attended the December 2016 IEP\\n\\nmeeting. See D.S. v. Bayonne Bd. of Educ., 602 F.3d 553, 565 (3d Cir. 2010) (holding\\n\\nthat a school district did not violate the IDEA when it ignored parents’ letters for months\\n\\nbut included the parents in their child’s IEP meeting because “they ultimately had an\\n\\nopportunity to participate meaningfully in the creation of an IEP” for their child).\\n\\nTherefore, the only form of relief that Appellants seek--private placement for R.F.--\\n\\n“cannot reasonably be traced” to CCPS’s failure to include R.F.’s parents in decisions\\n\\nregarding her placement in August 2016. Id. at 566. We cannot agree with Appellants\\n\\nthat CCPS’s procedural violation of R.F.’s parents’ right to participate in decisions about\\n\\nher placement rises to the level of a substantive IDEA violation that could be cured by\\n\\nprivate placement.\\n\\n Appellants also contend that CCPS violated their parental rights under the IDEA\\n\\nwhen Mr. K. destroyed the raw data that he collected on R.F.’s progress before her\\n\\nparents could review it. However, as the ALJ noted, “the IDEA does not specify how\\n\\noften a school system should collect data or how long it should be maintained.” J.A. 72.\\n\\nInstead, it only requires that the IEP describe how the child’s progress toward her goals\\n\\nwill be measured. 20 U.S.C. § 1414(d)(1)(A)(i)(III). The ALJ found that while Mr. K.\\n\\nviolated CCPS’s records retention policy, which required him to preserve the data for two\\n\\n 22\\n\\fyears, he did not violate the IDEA when he destroyed R.F.’s raw data after making his\\n\\nquarterly reports. We agree that this was not a procedural violation of the IDEA.\\n\\n Regardless of whether the data destruction was a procedural violation of the\\n\\nIDEA, R.F.’s parents could still view summaries of the data in Mr. K.’s quarterly reports.\\n\\nTherefore, their ability to “participate in the decisionmaking process” regarding R.F.’s\\n\\neducation was not “significantly impeded.” 20 U.S.C. § 1415(f)(3)(E)(ii)(II).\\n\\n We in no way minimize the necessity of compliance with the procedural\\n\\nrequirements of the IDEA, including those pertaining to parental participation. See\\n\\nDiBuo ex rel. DiBuo v. Bd. of Educ., 309 F.3d 184, 191 (4th Cir. 2002) (explaining, in a\\n\\ncase before § 1415(f)(3)(E)(ii)(II) was enacted, that “[w]e have no doubt that a\\n\\nprocedural violation of the IDEA . . . that causes interference with the parents’ ability to\\n\\nparticipate in the development of their child’s IEP will often actually interfere with the\\n\\nprovision of a FAPE to that child”). But here, we cannot find that CCPS significantly\\n\\nimpeded R.F.’s parents’ participation rights when it changed R.F.’s placement and\\n\\ndestroyed raw data on R.F.’s progress. Accordingly, we affirm that CCPS did not violate\\n\\nR.F.’s parents’ rights under the IDEA.\\n\\n\\n\\n 4.\\n\\n Finally, Appellants contend that CCPS violated the IDEA because it failed to\\n\\nprovide R.F. with an IEP that was sufficient to meet her needs, thus denying her a FAPE.\\n\\nSpecifically, they contend that R.F.’s BIP was insufficient because it primarily focused\\n\\non biting while ignoring R.F.’s other behaviors, that R.F.’s IEP was inadequate because it\\n\\n 23\\n\\flacked a social skills goal, and that R.F.’s IEP contained an insufficient number of hours\\n\\nof special education instruction to meet her needs. We disagree.\\n\\n As we have discussed, “[t]o meet its substantive obligation under the IDEA, a\\n\\nschool must offer an IEP reasonably calculated to enable a child to make progress\\n\\nappropriate in light of the child’s circumstances.” Endrew F., 137 S. Ct. at 999. Courts\\n\\nconduct this analysis with an understanding that “crafting an appropriate program of\\n\\neducation requires a prospective judgment by school officials.” Id.\\n\\n First, with respect to the BIP, Appellants contend that it rendered R.F.’s IEP\\n\\ninadequate because it should have addressed behaviors other than biting. 10 However, the\\n\\nALJ found that, at the time the May 2016 IEP was created, biting was R.F.’s primary\\n\\nproblem behavior. She also deferred to testimony by Sarah Farr, CCPS’s director of\\n\\nspecial education, that “[t]he skills set forth in the BIP for the primary behavior [here,\\n\\nbiting] can be generalized to other behaviors.” J.A. 68–69. Therefore, the behavior\\n\\nstrategies in the May 2016 IEP were “reasonably calculated” in light of R.F.’s\\n\\ncircumstances at the time that IEP was created, and CCPS did not deny her a FAPE.\\n\\nEndrew F., 137 S. Ct. at 999.\\n\\n Appellants contend that the December 2016 IEP was inadequate because it\\n\\nincorporated the BIP without revising it to include interventions for R.F.’s other\\n\\ninterfering behaviors. However, Appellants present no evidence that by the time the IEP\\n\\n\\n 10\\n Although the BIP itself is defined by Maryland regulations, see Md. Code Regs.\\n§ 13a.08.04.02(B)(1), its incorporation by reference into R.F.’s IEP gives rise to review\\nunder the IDEA framework governing the adequacy of IEPs.\\n\\n 24\\n\\fteam met to revise R.F.’s IEP in December, CCPS was aware that biting was not R.F.’s\\n\\nonly interfering behavior. While it is true that Mr. K. testified in March 2017 that if he\\n\\nwere to develop a new BIP for R.F., it would include biting, hair pulling, grabbing,\\n\\nhitting, kicking, and scratching, this says nothing about what CCPS knew in December\\n\\n2016. Without other evidence indicating that CCPS knew in December 2016 that R.F.\\n\\nneeded interventions for behaviors other than biting, we cannot say that CCPS\\n\\nprocedurally violated the IDEA by failing to account for those behaviors in her IEP.\\n\\n Regardless, any error in failing to update the BIP did not deny R.F. a FAPE\\n\\nbecause CCPS took steps that were “reasonably calculated” to address R.F.’s behavioral\\n\\nneeds “in light of [her] circumstances.” Id. For instance, Farr testified that R.F.’s\\n\\nexisting BIP was sufficient to address R.F.’s behaviors. Farr explained that R.F.’s other\\n\\ninterfering behaviors did not need to be included in a new BIP because “they’re being\\n\\naddressed in a very appropriate way. [CCPS is] altering the environment to change those\\n\\nbehaviors.” S.A. 24. Farr emphasized that R.F.’s interfering behaviors, including biting,\\n\\nhave decreased because CCPS is taking steps to reduce those behaviors. Therefore,\\n\\nCCPS did not violate the IDEA and deny R.F. a FAPE by failing to address behaviors\\n\\nother than biting in the BIP that was incorporated in her May 2016 and December 2016\\n\\nIEPs.\\n\\n Second, with respect to whether R.F.’s IEP was inadequate because it lacked a\\n\\nsocial skills goal, the ALJ found that “[R.F.] could benefit if her IEP contained a\\n\\nmeasurable socialization goal” but noted that “an IEP is not required to contain every\\n\\ngoal from which a student might benefit.” J.A. 70. She concluded that “[t]aking the IEP\\n\\n 25\\n\\fas a whole,” R.F. “was not denied a FAPE due to the lack of a social skills goal in her\\n\\nIEP.” Id. We agree and note that the IEP did build in opportunities for R.F. to practice\\n\\nher social skills. For instance, R.F.’s BIP included the use of social stories to remind R.F.\\n\\nof appropriate social interactions, and her schedule included regular walks around the\\n\\nbuilding to greet students.\\n\\n Finally, with respect to whether R.F.’s IEP contained inadequate hours of special\\n\\neducation, the ALJ correctly noted that, because IEPs are prospective, Appellants cannot\\n\\nrely on the fact that R.F.’s hours of special education were increased in the December\\n\\n2016 IEP as evidence that the May 2016 IEP was defective when created. See J.A. 74\\n\\n(“The appropriateness of the May 2016 IEP must be judged as of the time it was adopted,\\n\\nnot in December 2016.”). The ALJ also found that Appellants’ experts who testified that\\n\\nthe May 2016 IEP contained an inadequate number of special education hours did so\\n\\nunder an incorrect understanding of the way CCPS calculates and records special\\n\\neducation hours. Appellants offered no other evidence that the May 2016 IEP contained\\n\\nan inadequate number of special education hours to enable R.F. to “make progress\\n\\nappropriate in light of the [her] circumstances.” Endrew F., 137 S. Ct. at 999. Therefore,\\n\\nwe affirm and conclude that the content of R.F.’s IEP was sufficient to provide her with a\\n\\nFAPE.\\n\\n\\n\\n 5.\\n\\n In sum, although CCPS violated the IDEA in some procedural respects, we affirm\\n\\nbecause it did not deny R.F. a FAPE. The education that R.F. actually received during\\n\\n 26\\n\\fthe 2016–2017 school year reinforces our decision that CCPS provided her with a FAPE.\\n\\nThe May 2016 IEP set out thirteen goals addressing “all of R.[F.]’s identified special\\n\\nneeds.” J.A. 35. These goals “focus[ed] on the particular child.” Endrew F., 137 S. Ct.\\n\\nat 999. The IEP’s use of the ICSC, with its specialized supports to target R.F.’s issues\\n\\nwith focus and stress, “aim[ed] to enable [her] to make progress,” while its efforts to\\n\\ninclude R.F. in a general educational setting for specials aimed to avoid unduly isolating\\n\\nher from her peers at school. Id.\\n\\n Under this IEP, as the ALJ found, R.F. did make “progress toward achieving some\\n\\nof the goals on her IEP during the 2016/2017 school year,” although not all of them. J.A.\\n\\n46. To facilitate her progress, Mr. K. and a paraprofessional worked closely and\\n\\nconstructively with R.F. throughout the year to determine how to best enable her to make\\n\\nprogress towards these goals. Such efforts include an ongoing assessment of whether\\n\\nR.F. was able to make progress in general educational settings.\\n\\n The IEP did not aim for grade-level advancement through the general curriculum\\n\\nor for standard letter grades because these were not considered “a reasonable prospect”\\n\\nfor R.F. Endrew F., 137 S. Ct. at 1000. But this does not indicate a failure to set\\n\\n“challenging objectives” for R.F. Id. The IEP team also revised the IEP in December\\n\\n2016 to account for the progress that R.F. had made to date.\\n\\n This combination of reasonably ambitious goals that were focused on R.F.’s\\n\\nparticular circumstances and that were pursued through the careful and attentive\\n\\ninstruction of specialized professionals provided the education that R.F. is entitled to\\n\\n\\n\\n 27\\n\\funder the statute. We therefore conclude that CCPS provided R.F. with a FAPE despite\\n\\nits procedural violations of the IDEA.\\n\\n\\n\\n IV.\\n\\n Although CCPS procedurally violated the IDEA in certain technical respects, it\\n\\ndid not substantively violate the IDEA because it did not deny R.F. a FAPE. We\\n\\ntherefore\\n\\n AFFIRM.\\n\\n\\n\\n\\n 28\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1067,"cells":{"id":{"kind":"number","value":4603307,"string":"4,603,307"},"name":{"kind":"string","value":"Lance R. BELVILLE; Donald C. Carr; Mindi Stewart; Stanley Stewart; Charles Johnson; Jill Durant; Michael Antramgarza; Quintin Williams; ACA Legal Investigations, Inc. ; John McGee; David H. Patton; Inez A. Patton; Pamela D. Smith; Betty J. Trinque; Sharon Shaffer ; Robert Brandon; Daniel Gallegos ; Timothy Matthews; Samuel Hairston; Rhoda Jeffers; Mary Phippen; Jonathan Poma; Shelley Riley; Charles T. Burd; William S. Troutman; Shane Mayfield; Andrea Martin; Thomas Porter; Hasen Design Build & Development, Inc., Plaintiffs - Appellants, and Dean Richardson; Christine Salamone; Beverly Gorton; Josh Legato; Roofwerks, Inc. ; Mills Allison; Laura Elsinger, And; Gabriel Kletschka, Individually and on Behalf of All Others Similarly Situated; Carolyn Chase ; Greg Peet; Tony Burnett ; George Shaffer; Robert Agris; John E. Grimaldi; Jolene Harris, Plaintiffs, v. FORD MOTOR COMPANY, Defendant - Appellee."},"name_abbreviation":{"kind":"string","value":"Lance Belville v. Ford Motor Company"},"decision_date":{"kind":"string","value":"2019-03-25"},"docket_number":{"kind":"string","value":"18-1470"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Agee, Harris, Duncan\", \"parties\": \"\", \"opinions\": [{\"author\": \"AGEE, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-1470\\n\\n\\nLANCE R. BELVILLE; DONALD C. CARR; MINDI STEWART; STANLEY\\nSTEWART; CHARLES JOHNSON; JILL DURANT; MICHAEL ANTRAMGARZA;\\nQUINTIN WILLIAMS; ACA LEGAL INVESTIGATIONS, INC.; JOHN MCGEE;\\nDAVID H. PATTON; INEZ A. PATTON; PAMELA D. SMITH; BETTY J. TRINQUE;\\nSHARON SHAFFER; ROBERT BRANDON; DANIEL GALLEGOS; TIMOTHY\\nMATTHEWS; SAMUEL HAIRSTON; RHODA JEFFERS; MARY PHIPPEN;\\nJONATHAN POMA; SHELLEY RILEY; CHARLES T. BURD; WILLIAM S.\\nTROUTMAN; SHANE MAYFIELD; ANDREA MARTIN; THOMAS PORTER;\\nHASEN DESIGN BUILD & DEVELOPMENT, INC.,\\n\\n Plaintiffs – Appellants,\\n\\nand\\n\\nDEAN RICHARDSON; CHRISTINE SALAMONE; BEVERLY GORTON; JOSH\\nLEGATO; ROOFWERKS, INC.; MILLS ALLISON; LAURA ELSINGER, and;\\nGABRIEL KLETSCHKA, Individually and on behalf of all others similarly situated;\\nCAROLYN CHASE; GREG PEET; TONY BURNETT; GEORGE SHAFFER;\\nROBERT AGRIS; JOHN E. GRIMALDI; JOLENE HARRIS,\\n\\n Plaintiffs,\\n\\nv.\\n\\nFORD MOTOR COMPANY,\\n\\n Defendant – Appellee.\\n\\n\\nAppeal from the United States District Court for the Southern District of West Virginia,\\nat Huntington. Robert C. Chambers, District Judge. (3:13-cv-06529)\\n\\n\\nArgued: January 29, 2019 Decided: March 25, 2019\\n\\fBefore AGEE and HARRIS, Circuit Judges, and DUNCAN, Senior Circuit Judge.\\n\\n\\nAffirmed by published opinion. Judge Agee wrote the opinion, in which Judge Harris\\nand Senior Judge Duncan joined.\\n\\n\\nARGUED: John E. Tangren, DICELLO LEVITT & CASEY LLC, Chicago, Illinois, for\\nAppellants. Jonathan D. Hacker, O’MELVENY & MYERS LLP, Washington, D.C., for\\nAppellee. ON BRIEF: Adam J. Levitt, John E. Tangren, DICELLO LEVITT & CASEY\\nLLC, Chicago, Illinois; Niall A. Paul, SPILMAN THOMAS & BATTLE, PLLC,\\nCharleston, West Virginia; Gregory M. Travalio, Mark H. Troutman, Shawn K. Judge,\\nISAAC WILES BURKHOLDER & TEETOR, LLC, Columbus, Ohio, for Appellants.\\nSarah Virginia Bondurant Price, MCGUIREWOODS LLP, Richmond, Virginia;\\nJonathan D. Hacker, Bradley N. Garcia, O’MELVENY & MYERS LLP, Washington,\\nD.C., for Appellee.\\n\\n\\n\\n\\n 2\\n\\fAGEE, Circuit Judge:\\n\\n A group of individuals and corporations sued Ford Motor Company for an alleged\\n\\ndefect in their purchased or leased Ford vehicles manufactured between 2002 and 2010.\\n\\nThe district court dismissed various claims of certain Plaintiffs, excluded the opinions of\\n\\nthe Plaintiffs’ three experts, and granted summary judgment to Ford on all claims.\\n\\nTwenty-seven individual and two corporate Plaintiffs1 now appeal and, for the reasons set\\n\\nout below, we affirm the judgment of the district court.\\n\\n\\n\\n I.\\n\\n In 2013, various individuals and corporations filed three related actions in the\\n\\nSouthern District of West Virginia, alleging that their Ford vehicles had a defective\\n\\nelectronic throttle control (“ETC”) system, which could lead to an unintended\\n\\nacceleration (“UIA”). They further alleged that to prevent a UIA, Ford should have\\n\\nequipped their vehicles with an alternative failsafe system such as a Brake Over\\n\\nAccelerator (“BOA”). Based on this theory of defect, the Plaintiffs asserted numerous\\n\\nstate and federal claims, including a violation of the Magnuson–Moss Warranty Act,\\n\\nbreach of implied and express warranty, unjust enrichment, and a violation of state\\n\\nconsumer protection statutes.\\n\\n\\n\\n1\\n Plaintiffs in the proceedings below included Appellants as well as fourteen other\\nindividuals and one corporation. These other Plaintiffs did not file a notice of appeal. For\\nconvenience and to avoid confusion, we will identify all plaintiffs below as “Plaintiffs,”\\nwhich includes Appellants.\\n\\n 3\\n\\f Despite the alleged defect, only sixteen Plaintiffs alleged that they actually\\n\\nexperienced UIAs, and none had suffered personal injury or property damage from the\\n\\nalleged defect. Nonetheless, all Plaintiffs sought economic damages arguing that the\\n\\nalleged defect made their vehicles worth less than their purchase or lease price.\\n\\nSpecifically, they requested “damages to recover for diminished value at the time of\\n\\npurchase,” Belville v. Ford Motor Co., 13 F. Supp. 3d 528, 535 (S.D.W. Va. 2014),\\n\\nwhich they posit on appeal is—for “many” Plaintiffs— “the market price to repair the\\n\\ndefective Class Vehicles.” Reply Br. 17.\\n\\n Ford filed motions to dismiss all three actions, which the district court granted in\\n\\npart and denied in part. Bellville, 13 F. Supp. 3d at 530. In 2014, the court dismissed,\\n\\namong other claims, the warranty and unjust enrichment claims of those Plaintiffs who\\n\\nhad not experienced a UIA because they “failed to demonstrate a plausible claim that\\n\\nthey paid more for their vehicles than their actual worth when they have used their\\n\\nvehicles without incident for many years.” Id. at 542. After the dismissal order was\\n\\nissued, the Plaintiffs twice attempted to amend their complaints. In considering the\\n\\nmotions to amend, the district court clarified which claims were dismissed, consolidated\\n\\nthe three actions into one, and directed the Plaintiffs to file a consolidated amended\\n\\ncomplaint consistent with the court’s orders.\\n\\n In December 2015, seventeen individuals and two corporations, as the Plaintiffs in\\n\\nthe consolidated action, filed a Second Amended Master Consolidated Class Action\\n\\n\\n\\n\\n 4\\n\\fComplaint, 2 which became the operative complaint. As distinguished from the initial\\n\\ncomplaints, all but two Plaintiffs 3 now alleged that they experienced a UIA due to a\\n\\ndefective ETC system in their Ford vehicles. Based on this alleged defect, the Plaintiffs\\n\\ncontinued to assert one federal claim—a violation of the Magnuson-Moss Warranty\\n\\nAct—and numerous state claims, including breach of express and implied warranty, fraud,\\n\\nand unjust enrichment claims.\\n\\n Ford moved to exclude the Plaintiffs’ expert witnesses and for summary judgment.\\n\\nBy order of February 27, 2018, the district court granted partial summary judgment to\\n\\nFord on the warranty and unjust enrichment claims, noting that because many factors\\n\\nunrelated to an ETC system may cause UIAs, the Plaintiffs’ mere allegations that they\\n\\nexperienced UIAs were not evidence of a defect. See Johnson v. Ford Motor Co., 310 F.\\n\\nSupp. 3d 699 (S.D.W. Va. 2018). It observed that to survive Ford’s motion for summary\\n\\njudgment, the Plaintiffs must establish “a causal link between their alleged [UIAs] and\\n\\n\\n\\n 2\\n The Plaintiffs moved for class certification in January 2018, but the district court\\ngranted summary judgment on all claims to Ford before ruling on this motion. Thus, the\\ncourt never certified a class.\\n 3\\n In the initial complaints, sixteen Plaintiffs, including Roofwerks, Inc., Greg Peet,\\nCarolyn Chase, Robert Agris, and John Grimaldi, alleged that they experienced UIAs.\\nWith the district court’s permission, Roofwerks, Peet, Chase, Agris and Grimaldi\\nvoluntarily dismissed their claims.\\n Nineteen of the Plaintiffs who survived the dismissal orders became the Plaintiffs\\nin the consolidated action. This group included eleven Plaintiffs who alleged in the initial\\ncomplaints that they experienced UIAs. The six other Plaintiffs changed their stance and\\nalleged in the amended complaint that they experienced UIAs. Two Plaintiffs, John\\nMcGee and Hasen Design Build & Development, Inc., did not allege that they\\nexperienced UIAs or assert any warranty or unjust enrichment claims. All Plaintiffs in the\\nconsolidated action are parties to this appeal.\\n\\n 5\\n\\fthe alleged defect.” Id. at 704. The district court held the Plaintiffs failed to produce\\n\\nevidence of causation, explaining:\\n\\n none of [Plaintiffs’ proposed] experts can say that, for those Plaintiffs who\\n alleged they experienced [a UIA], their events were the result of the alleged\\n defect with the ETC system. Quite simply, Plaintiffs produced no experts\\n who can testify that [their] alleged [UIAs] were proximately caused by the\\n alleged defect rather than some other known cause for such events.\\n\\nId. at 706–07. The court found, “this gap between Plaintiffs’ experts’ opinions and what\\n\\nallegedly occurred in Plaintiffs’ specific vehicles fatal to Plaintiffs’ warranty and unjust\\n\\nenrichment claims.” Id. at 707.\\n\\n By order of March 26, 2018, the district court resolved the Plaintiffs’ remaining\\n\\nclaims. Johnson v. Ford Motor Co., No. 3:13-6529, 2018 WL 1512377 (S.D.W. Va. Mar.\\n\\n26, 2018). The district court first granted Ford’s motion to exclude the opinions of the\\n\\nPlaintiffs’ three experts, Todd H. Hubing, Ph.D., Marthinus van Schoor, Ph.D., and Philip\\n\\nKoopman, Ph.D., holding that their opinions were inadmissible under Rule 702 of the\\n\\nFederal Rules of Evidence and Daubert v. Merrell Dow Pharmaceuticals, Inc., 509 U.S.\\n\\n579 (1993). And “the challenged expert opinions [were] critical to the remaining\\n\\nsummary judgment issues.” Id. at *1. Because the expert opinions failed to prove the\\n\\nPlaintiffs’ theory of defect, the theory was “largely hypothetical.” Id. at *2.\\n\\n As the district court explained, the Plaintiffs’ “theory is that many predictable\\n\\nflaws may occur with the pedal sensors. Plaintiffs theorize that these flawed sensors\\n\\nproduce faulty voltage signals that should trigger the ETC system’s failsafe modes.\\n\\nHowever, due to a defectively designed ETC system, the failsafe modes are not activated,\\n\\n\\n\\n 6\\n\\fresulting in [UIAs].” Id at *3. Thus, “testing of ETC systems was central to the experts’\\n\\nopinions.” Id at *2.\\n\\n The district court found that the experts’ “testing was flawed, and Plaintiffs have\\n\\nfailed to establish other means by which their experts can meet the reliability standard.”\\n\\nId. The district court noted, for example, that the only peer-reviewed publication relied on\\n\\nby the experts was a 2015 article by Dr. Hubing; however, the theory relied on in that\\n\\narticle had been discredited by two federal agencies, the National Highway Traffic Safety\\n\\nAdministration (“NHTSA”) and the National Aeronautics and Space Administration\\n\\n(“NASA”). In analyzing the experts’ testing evidence, the court noted the continuing\\n\\nfailure of proof establishing any causal link:\\n\\n Although Plaintiffs’ experts purport to test [Plaintiffs’ theory of defect],\\n they leave a gap between analytical possibility and actual proof of\\n occurrence. The experts attempt to excuse this gap by reporting that the\\n defect leaves no evidence of its effect. However, this position shifts the\\n burden to Ford to prove the negative. Furthermore, there is no “general\\n acceptance” within the automotive safety or engineering community that\\n underpins Plaintiffs’ theory. The causes of [UIA] are myriad. Some events\\n are attributable to driver error, while others are tied to different defects\\n from cruise control to mechanical issues. Even though many drivers’\\n complaints of [UIA] are credible and likely caused by some defects,\\n Plaintiffs’ theory here is still largely hypothetical . . . .\\n\\nId. at *3.\\n\\n The district court examined each of the three experts’ individual opinions to\\n\\ndetermine whether that opinion should be admitted into evidence. First, the court rejected\\n\\nthe opinion of Dr. Hubing 4 whose report was primarily based on the article noted above\\n\\n\\n 4\\n Dr. Hubing is an electrical engineer and a professor at Clemson University.\\n\\n 7\\n\\fand in which he examined five vehicles with ETC systems, including two Ford models, a\\n\\n2005 Mustang and a 2006 Explorer. After comparing accelerator pedal performance of\\n\\nthe five vehicles, Dr. Hubing concluded that “Ford’s Gen II ETC system fails to\\n\\nadequately mitigate accelerator pedal faults which can lead to” UIAs. J.A. 10873. In Dr.\\n\\nHubing’s opinion, this was “the most probable reason that Ford vehicles with this throttle\\n\\ncontrol system have high reported rates of” UIAs. J.A. 10873.\\n\\n The district court found Dr. Hubing’s testing unreliable for two reasons. First, his\\n\\ntesting required making separate accommodations for the Ford vehicles he tested because\\n\\nthe testing “was developed to test vehicles with ’two track’ pedal sensors,” but the Ford\\n\\nvehicles had “three track” pedal sensors. Johnson, 2018 WL 1512377, at *4. To\\n\\naccommodate this difference, Dr. Hubing arbitrarily assigned a set value to Ford’s third\\n\\npedal without knowing how this affected Ford’s computer source code or software\\n\\nprogram. In some cases, the set value he used for the third track intentionally caused the\\n\\nvehicles to accelerate if one of the other two sensors’ values matched this set value.\\n\\n Second, Dr. Hubing’s testing rested on questionable assumptions that lacked\\n\\nevidentiary foundations. The voltages he injected into the ETC system purportedly\\n\\nsimulated real-world circumstances and actual vehicle conditions. But the voltage values\\n\\nsimply reflected Dr. Hubing’s “assumptions of what would happen” if factors such as a\\n\\nworn sensor, loose connector, or tin whisker existed. Id. at *4 n.6. Furthermore, Dr.\\n\\nHubing’s testing revealed that UIAs occurred when two pedal sensors produced values of\\n\\na certain range, and those values were “close to the same . . . , as though each sensor was\\n\\nfaulting in the same way.” Id. at *4. But Dr. Hubing did not “offer any testing of sensors\\n\\n 8\\n\\fto verify the assumption that both sensors should be expected to fault and that they do so\\n\\nin the same way.” Id.\\n\\n The court found that the sources supporting Dr. Hubing’s sensor assumption were\\n\\ninsufficient to be reliable. Dr. Hubing’s assumption was based on two sources: “first, by\\n\\nreference to various documents, such as Ford’s CQIS database (complaints relating to\\n\\neither pedal faults and/or [UIA]) and Ford’s design and development phases for the Gen\\n\\nII ETC system; second, the inherent knowledge of the expert.” Id. The first source did\\n\\n“little” to support Dr. Hubing’s assumption because these documents were “brief,\\n\\nand very few reflect[ed] an inspection, testing, or analysis by a trained eye.” Id. As for\\n\\nDr. Hubing’s qualifications, those alone could not substitute for the lack of testing\\n\\nevidence.\\n\\n The district court found further problems with Dr. Hubing’s report, including that\\n\\n“degraded sensors are not the defect, nor are they the only precipitating cause of [UIA],\\n\\naccording to Plaintiffs’ claim. However, Dr. Hubing’s theory of defect rests significantly\\n\\non the system’s inability to properly recognize and mitigate faulty sensors.” Id. Dr.\\n\\nHubing also had never tested the Plaintiffs’ actual vehicles or attempted to produce\\n\\nvoltages that would cause a UIA instead of simply injecting these voltages. Finally, the\\n\\nNHTSA and NASA in 2011 had rejected his theory as lacking real-world evidence.\\n\\nBased on all these findings, the court excluded Dr. Hubing’s opinion.\\n\\n Next, the court considered the opinion of Dr. van Schoor who holds a Ph.D. in\\n\\naeronautics and astronautics. He opined that Ford’s accelerator pedal sensors are subject\\n\\nto wear or “gunk” buildup, either of which “can lead to failure and erratic vehicle\\n\\n 9\\n\\fbehavior.” J.A.10972. The district court found three problems with this theory: (1)\\n\\nPlaintiffs’ counsel “explicitly stated that Plaintiffs were not offering his opinion as to a\\n\\ndefect;” (2) Dr. van Schoor did not perform any inspections or surveys to support his\\n\\ntheory; and (3) he “did not attribute any of Plaintiffs’ [UIAs] to the problems he\\n\\nidentified in his report.” Johnson, 2018 WL 1512377, at *5. Thus, the court found his\\n\\ntheory irrelevant to the Plaintiffs’ theory of defect.\\n\\n Dr. van Schoor also offered an opinion on an alternative vehicle design with BOA,\\n\\nbut the court did not examine this in depth because the availability of an alternative\\n\\ndesign was not proof of the alleged defect.5 Based on these findings, the court excluded\\n\\nDr. van Schoor’s report.\\n\\n The third expert at issue was Dr. Koopman, 6 who opined that a design defect made\\n\\nFord’s Gen II ETC system vulnerable to allowing UIAs. In support, Dr. Koopman tested\\n\\ntwo Ford models, a 2005 Mustang and a 2006 Fusion, by injecting voltages into the\\n\\naccelerator wiring harness as a substitute for the three accelerator pedal sensors. Similar\\n\\nto Dr. Hubing’s testing, the injected voltages represented the voltages “likely produced\\n\\n 5\\n The district court’s holding is consistent with our precedent. See Sexton By and\\nThrough Sexton v. Bell Helmets, Inc., 926 F.2d 331, 338 (4th Cir. 1991) (holding that the\\nsimple availability of an alternative design at the time of trial “does not lead to the\\nconclusion that the design of the [product] was defective”); see also Edwards v. Bell\\nHelicopter Textron, Inc., 63 F. App’x 674, 680–81 (4th Cir. 2003) (per curiam)\\n(determining that the availability of an alternative design “was irrelevant to the proof” of\\nthe strict liability and negligent defective design claims because the existence of an\\nalternative design could not have contributed to the alleged injury and therefore did not\\nestablish that an alleged design defect in the product was a proximate cause of the alleged\\ninjuries).\\n 6\\n Dr. Koopman is a tenured Associate Professor in the Electrical and Computer\\nEngineering Department of Carnegie Mellon University.\\n\\n 10\\n\\fby sensors degraded in one or more ways, such as from wear and tear, loose wires, and\\n\\nwater intrusion.” Johnson, 2018 WL 1512377, at *5. Next, he evaluated “actual vehicle\\n\\nperformance” by repeating this testing on a dynamometer 7 that was designed to simulate\\n\\nan actual vehicle condition. Id. Based on the results of his testing, Dr. Koopman\\n\\nconcluded that a UIA occurs when two or more sensors produce voltages of a certain\\n\\nrange close to each other.\\n\\n The district court found Dr. Koopman’s approach unreliable for much the same\\n\\nreasons that it found Dr. Hubing’s opinion defective. The court noted that he did not test\\n\\nor prove his assumption that two or more degraded sensors have produced or would\\n\\nproduce the voltages he used for his testing. Furthermore, Dr. Koopman purposely chose\\n\\narbitrary voltage inputs that would instruct the system to accelerate. Thus, his “testing\\n\\nwas an artificial demonstration that essentially mimicked intentional acceleration.” Id. at\\n\\n*7, and was not a “realistic example of sensor faults” because it required multiple steps\\n\\n“in a sequence that ha[d] no ‘real-world’ support.” Id.\\n\\n Furthermore, the district court concluded “Dr. Koopman’s testimony, that\\n\\nPlaintiffs’ complaints are consistent with his design defect opinion, is inadequate to tie\\n\\nhis opinions to this case.” The court explained why this was so:\\n\\n First, [Dr. Koopman] relies on nothing more specific than the Consolidated\\n Complaint to understand Plaintiffs’ [UIAs]. Second, there are profound\\n inconsistencies between the general complaints and his opinions. Nearly\\n every Plaintiff described a failure of their brakes to counteract the [UIA],\\n\\n 7\\n Dynamometer is a “device for measuring mechanical force, or power, transmitted\\nby a rotating shaft.” Dynamometer, Encyc. Britannica (2018); see Maxwell Dynamometer\\nCo. v. United States, 386 F.2d 855, 859 (Ct. Cl. 1967).\\n\\n 11\\n\\f yet in Dr. Koopman’s own testing procedure, the brakes restrained the\\n acceleration. Further, some Plaintiffs reported that their gas pedals were\\n moving up and down without a foot-on-pedal, a circumstance not replicated\\n in any of the tests done by Plaintiffs’ experts. If these Plaintiffs were right,\\n this pedal problem likely would be mechanical, perhaps caused by the\\n return spring.\\n\\nId. at *8 (internal citation omitted). Because his testing was not “a reliable basis” for his\\n\\nopinions regarding the alleged defect, the district court excluded Dr. Koopman’s opinion.\\n\\nId.\\n\\n The district court also found problematic that none of the Plaintiffs’ experts had\\n\\ntested or inspected the Plaintiffs’ actual vehicles or attempted to connect their testing to\\n\\nany of those vehicles. Instead, the Plaintiffs asserted the alleged ETC defect and experts’\\n\\nopinions applied universally to all the thousands of vehicles in their purported class\\n\\ndespite Drs. Koopman’s and Hubing’s opinions that their testing results varied\\n\\nsignificantly between individual vehicles and that the pedal sensors differed among the\\n\\nclass vehicles.\\n\\n Once the expert opinions were excluded, the district court concluded that the\\n\\nPlaintiffs had “no evidence of their core allegation that there is a design defect in Ford’s\\n\\nGen II ETC system.” Id. Insomuch as the Plaintiffs’ theory of defect was without an\\n\\nevidentiary basis, they could not establish the existence of a defect and the necessary\\n\\nelement of causation. Accordingly, the district court granted summary judgment on all\\n\\nremaining claims to Ford.\\n\\n A group of the Plaintiffs now appeal, and this Court has jurisdiction under 28\\n\\nU.S.C. § 1291.\\n\\n\\n 12\\n\\f II.\\n\\n A.\\n\\n We review summary judgment decisions de novo, see Campbell v. Hewitt,\\n\\nColeman & Assocs., Inc., 21 F.3d 52, 53 (4th Cir. 1994), and Daubert decisions for abuse\\n\\nof discretion, see Nease v. Ford Motor Co., 848 F.3d 219, 228 (4th Cir. 2017). A district\\n\\ncourt abuses its discretion if it makes an error of law or clearly erroneous factual finding.\\n\\nSee id. at 228.\\n\\n The merits of the district court’s Daubert decision addressing the Plaintiffs’ proof\\n\\nof their defect theory is our initial focus because their entire case hinges on the allegedly\\n\\ndefective ETC system as the cause of UIAs. UIAs alone do not substantiate their theory\\n\\nbecause, as the Plaintiffs concede on appeal, many factors unrelated to an ETC system\\n\\ncould trigger UIAs. See, e.g., Opening Br. 31 (“[M]ultiple circumstances can initiate\\n\\nunintended acceleration signals.”). Thus, to establish the existence of the alleged defect\\n\\nand the requisite causal link between it and their UIAs, the Plaintiffs proffered the\\n\\nopinions of the three experts, Drs. Hubing, van Schoor, and Koopman. As the district\\n\\ncourt recognized, these experts’ opinions are “critical” to the Plaintiffs’ case because\\n\\ntheir theory of defect is “largely hypothetical” without them. Johnson, 2018 WL\\n\\n1512377, at *3. Accordingly, if the district court correctly excluded the expert opinions,\\n\\nthe Plaintiffs’ case fails because they would be “unable to prove the fundamental theory\\n\\nof their case.” Id. at *9.\\n\\n B.\\n\\n 13\\n\\f The district court excluded the expert opinions under the Supreme Court’s\\n\\nlandmark precedent in Daubert, which established that under the Federal Rules of\\n\\nEvidence “the admissibility of scientific evidence no longer was limited to knowledge or\\n\\nevidence ‘generally accepted’ as reliable in the relevant scientific community.” Nease,\\n\\n848 F.3d at 228 (citing Daubert, 509 U.S. at 588–89). Instead, Daubert held that courts\\n\\nmust evaluate proposed expert testimony according to Rule 702, which tasks a district\\n\\njudge with “ensuring that an expert’s testimony both rests on a reliable foundation and is\\n\\nrelevant to the task at hand.” 509 U.S. at 597. This rule requires trial judges to conduct “a\\n\\npreliminary assessment of whether the reasoning or methodology underlying the\\n\\ntestimony is scientifically valid and of whether that reasoning or methodology properly\\n\\ncan be applied to the facts in issue. . . . . Many factors will bear on the inquiry, and we do\\n\\nnot presume to set out a definitive checklist or test.” Id. at 592–93.\\n\\n Under Rule 702, an expert’s testimony is relevant if it has “a valid scientific\\n\\nconnection to the pertinent inquiry.” Id. at 592. To be reliable, the testimony “must be\\n\\nbased on scientific, technical, or other specialized knowledge and not on belief or\\n\\nspeculation, and inferences must be derived using scientific or other valid methods.”\\n\\nOglesby v. Gen. Motors Corp., 190 F.3d 244, 250 (4th Cir. 1999) (citing Daubert, 509\\n\\nU.S. at 590, 592–93).\\n\\n In determining whether expert testimony is “sufficiently reliable to be admissible,”\\n\\na district court generally considers several factors:\\n\\n First, “a key question to be answered in determining whether a theory or\\n technique is scientific knowledge that will assist the trier of fact will be\\n whether it can be (and has been) tested.” A second question . . . is “whether\\n\\n 14\\n\\f the theory or technique has been subjected to peer review and\\n publication.” Publication regarding the theory bears upon peer review; “the\\n fact of publication (or lack thereof) in a peer reviewed journal will be a\\n relevant, though not dispositive, consideration in assessing the scientific\\n validity of a particular technique or methodology on which an opinion is\\n premised.” Third, “in the case of a particular scientific technique, the court\\n ordinarily should consider the known or potential rate of error.” Fourth, . . .\\n “‘general acceptance’” is . . . relevant to the reliability inquiry.\\n “Widespread acceptance can be an important factor in ruling particular\\n evidence admissible, and a known technique which has been able to attract\\n only minimal support with the community may properly be viewed with\\n skepticism.”\\n\\nNease, 848 F.3d at 229 (quoting Daubert, 509 U.S. at 593–94) (internal citations and\\n\\nalterations omitted).\\n\\n This list, however, is “not exhaustive,” and “‘neither necessarily nor exclusively\\n\\napplies to all experts or in every case.’” Id. (quoting Kumho Tire Co. v. Carmichael, 526\\n\\nU.S. 137, 141 (1999)). “[A]t bottom, the court’s evaluation is always a flexible one, and\\n\\nthe court’s conclusions necessarily amount to an exercise of broad discretion guided by\\n\\nthe overarching criteria of relevance and reliability.” Oglesby, 190 F.3d at 250. Thus, the\\n\\ntrial court has “broad latitude” in determining whether “Daubert’s specific factors are, or\\n\\nare not, reasonable measures of reliability in a particular case.” Kumho Tire, 526 U.S. at\\n\\n153. Here, the district court properly considered appropriate factors and did not abuse its\\n\\ndiscretion in excluding the experts’ opinions based on their lack of relevance and\\n\\nreliability.\\n\\n C.\\n\\n The Plaintiffs fail to show that the district court made “a clearly erroneous factual\\n\\nfinding” or “error of law” by excluding their expert witnesses. See Nease, 848 F.3d at\\n\\n\\n 15\\n\\f228. They argue that the district court did not consider certain Daubert factors, such as\\n\\nthe known or potential rate of error, or considered Daubert factors, like peer review, in an\\n\\ninappropriate manner. This argument lacks merit, in part, because the Plaintiffs do not\\n\\nidentify a tangible error in the district court’s analysis. The district court was not under\\n\\nany obligation to consider a certain factor or weigh factors it did consider in a particular\\n\\nmanner. See id. at 229. As noted earlier, the trial court’s inquiry is a “flexible one,” and it\\n\\nexercises “broad discretion” in choosing which Daubert factors to apply and how to\\n\\nconsider them. Oglesby, 190 F.3d at 250; accord Nease, 848 F.3d at 229.\\n\\n The Plaintiffs further argue that the court made conclusory findings and wrongly\\n\\nassessed the expert opinions. We disagree. Contrary to the Plaintiffs’ assertion, our\\n\\nreview shows that the district court thoroughly reviewed the record, including the\\n\\nexperts’ reports and the depositions of these experts, to understand their testing, theories,\\n\\nand methodologies. The court then provided a well-reasoned analysis of the experts’\\n\\ntheories and testing based on its consideration of relevant Daubert factors such as general\\n\\nacceptance of a theory within a relevant field, peer review, and the scientific validity of\\n\\ntheir underlying methodologies.\\n\\n For example, the district court properly noted that Dr. Hubing’s testing method\\n\\nwas, at a minimum, suspect because it had been rejected by NASA and NHTSA. Further,\\n\\nas the court pointed out, Dr. Hubing never tested any vehicle in actual conditions so all\\n\\nhis projections were purely theoretical. His “testing,” at least in part, seemed artificially\\n\\ninduced to produce a desired result and did not reflect real-world results from any vehicle\\n\\nclaiming a UIA. In sum, Dr. Hubing’s opinion was partly ipse dixit.\\n\\n 16\\n\\f As for Dr. van Schoor, even without examining the merits of his testimony, the\\n\\nPlaintiffs effectively pled him out of the case. During the district court proceedings, the\\n\\nPlaintiffs stipulated “on the record that Dr. van Schoor will not offer defect opinions per\\n\\nse.” J.A. 11934. Even more to the point, Plaintiffs’ counsel admitted Dr. van Schoor\\n\\nfailed to meet the necessary threshold of evidentiary reliability: “candidly I will concede\\n\\nto the Court that he couches all of his conclusions in the form of a defect opinion.\\n\\nCandidly I’ll say to the Court that I don’t know that Dr. van Schoor in this case tested his\\n\\nopinions against the rigor that is required for Federal Rules of Evidence.” J.A. 11932.\\n\\n Regardless, we find no abuse of discretion in the district court’s merits analysis of\\n\\nDr. van Schoor’s testimony for the reasons it explained. We simply note two salient\\n\\npoints from that analysis: Dr. van Schoor “performed no inspections nor surveys to\\n\\nsupport his theory about contacting sensors” and “did not attribute any of Plaintiffs’\\n\\n[UIAs] to the problems he identified in his report.” Johnson, 2018 WL 1512377, at *5.\\n\\n Dr. Koopman’s testimony fares no better. As with the other experts, there is a\\n\\nconsiderable gap between Dr. Koopman’s theory and any evidentiary proof of causation\\n\\nrelated to an ETC defect and a UIA. The district court aptly recited the evidentiary failure\\n\\non Dr. Koopman’s part:\\n\\n Dr. Koopman admits that in many of his tests, he injected faults with\\n voltages designed to produce pedal angles consistent with acceleration.\\n . . . Yet, nowhere does he validate his hypothesis that degraded\\n sensors, presumably to be expected, will actually cause or, in fact, have\\n produced faulty voltages in the way he arranged for his testing. . . . The\\n testing was an artificial demonstration that essentially mimicked intentional\\n acceleration. Dr. Koopman offers no testing of Plaintiffs’ vehicles, or the\\n exemplars he chose, to demonstrate how degraded sensors or the other\\n\\n\\n 17\\n\\f circumstances can produce similar voltages that result in unintended open\\n throttle.\\n\\nId. at *7 (internal citation omitted).\\n\\n Further, the district court correctly observed that none of the experts tested any of\\n\\nthe Plaintiffs’ vehicles or any of the thousands of Ford vehicles in their purported class\\n\\nwhich they allege had a UIA. Of the multitude of vehicles the Plaintiffs claim to be\\n\\ndefective, the record does not reflect they attempted to test even one vehicle purported to\\n\\nhave had a UIA, much less conduct such a test under real-world conditions. Most\\n\\nimportantly, none of the proffered expert opinions purport to tie their testing to any\\n\\nalleged UIA so as to show the fundamental element of causation. To the contrary, the\\n\\nPlaintiffs’ experts disclaimed any finding or opinion as to the causation of any specific\\n\\nUIA. J.A. 1754 ([Counsel’s question to Dr. Hubing:] “But you can’t say that your\\n\\nvulnerabilities that you identify actually cause the event in the plaintiffs’ vehicles,\\n\\ncorrect? . . . [Answer:] In any one of those vehicles, no.”); J.A. 10196–97 ([Counsel’s\\n\\nquestion to Dr. van Schoor:] “Have you identified any alleged unwanted acceleration\\n\\nevent occurring in a Ford vehicle that you have determined resulted from any of the\\n\\nalleged defects or vulnerabilities that you have identified in your report? [Answer:] I have\\n\\nnot.”); see also J.A. 8922–23 ([Counsel’s question to Dr. Koopman:]“And then you don’t\\n\\ngo out to the vehicle to see if there are any other possible causes or explanation for their\\n\\nclaim; correct? . . . [Answer:] I have not physically examined the vehicles.”); J.A. 8925–\\n\\n26 ([Dr. Koopman:] “What I am saying is that I see explanations consistent with software\\n\\n\\n\\n\\n 18\\n\\fand hardware defects, and I see that that’s consistent with my report. That’s all I have\\n\\nbeen saying.”). 8\\n\\n The court’s well-articulated analysis clearly distinguishes this case from Nease in\\n\\nwhich the district court failed to act as a gatekeeper by not assessing the expert’s\\n\\nreliability but leaving that question to the jury. See 848 F.3d at 231. Instead, the court\\n\\nhere faithfully performed its duty as a “gatekeeper” in the manner we approved in In re\\n\\nLipitor (Atorvastatin Calcium) Marketing, Sales Practices and Products Liability\\n\\nLitigation (No II) MDL 2502, 892 F.3d 624, 631 (4th Cir. 2018). There, we upheld the\\n\\ndistrict court’s extensive analysis of the experts’ theories and testing, which formed the\\n\\nbasis of the court’s exclusion of several expert opinions, because that court, like the\\n\\ndistrict court here, properly “identified and articulated clear . . . concerns it had about the\\n\\nmanner in which [the expert] reached his conclusions.” Id. at 638. In approving the\\n\\ndistrict court’s analysis in In re Lipitor, we once more emphasized that “‘[m]any factors\\n\\nwill bear on the inquiry,’ and there is no ‘definitive checklist or test.’” Id. at 637 (quoting\\n\\nDaubert, 509 U.S. at 593).\\n\\n Having failed on their primary arguments, the Plaintiffs argue that the district\\n\\ncourt mischaracterizes the experts’ testimony during depositions, but this argument\\n\\n 8\\n The district court found, as do we, the anomaly of the Plaintiffs’ theory at trial\\nthat the ETC defect was universal to all the class vehicles, but that their experts own\\nlaboratory testing showed significant differences between vehicles. As the district court\\nnoted, “Dr. Hubing’s testing revealed significant differences between the two Ford\\nvehicles, which he asserts had identical ETC systems,” and yet, the Plaintiffs are\\n“inconsistent” because they “maintain the Gen II ETC system used by Ford is exactly the\\nsame in all vehicles, but then they excuse results when it is not.” Johnson, 2018 WL\\n1512377, at *8.\\n\\n 19\\n\\fsimply channels the Plaintiffs’ disagreement with the district court’s findings. The\\n\\nPlaintiffs essentially assert the district court erred by making findings that were favorable\\n\\nto Ford or reaching conclusions that contradicted their portrayal of the expert opinions.\\n\\nFor instance, the Plaintiffs challenge the district court’s finding that when Dr. Hubing\\n\\nwas asked whether “he ever saw ‘dual faults occur in the same resistive ranges’ in the\\n\\n‘real world,’ [he] ultimately answered no.” Johnson, 2018 WL 1512377, at *4. They\\n\\nassert that this finding is erroneous because Dr. Hubing answered “no” to an entirely\\n\\ndifferent question. Our review of the record reveals that the district court’s finding is\\n\\ncorrect. When Ford’s counsel asked Dr. Hubing whether he had ever “physically see[n] . .\\n\\n. dual faults occur in the same resistive range,” he answered, “. . . how would we do\\n\\nthat?” because “physical evidence of two simultaneous faults occurring [in the real\\n\\nworld] . . . would be basically impossible to find.” J.A. 09335–36. Similarly, the\\n\\nPlaintiffs’ other arguments related to the district court’s alleged mischaracterization\\n\\nreveal no more than their disagreement with the district court’s findings or contrary\\n\\ninterpretation, and do not show that the court committed any error.\\n\\n Once the opinions of the three experts were excluded, the district court necessarily\\n\\nconcluded that the Plaintiffs had “no evidence of their core allegation that there is a\\n\\ndesign defect in Ford’s Gen II ETC system.” Johnson, 2018 WL 1512377, at *8. As the\\n\\ncourt held, other evidence that the Plaintiffs recite, such as a software expert’s opinion\\n\\nand Ford’s internal documents, does not prove their defect theory.\\n\\n The Plaintiffs point to unverified reports of UIAs from Ford vehicle drivers, but,\\n\\nas noted above, UIA alone does not prove the existence of a defect. Similarly, the\\n\\n 20\\n\\favailability of an alternative vehicle design with BOA does not substantiate the Plaintiffs’\\n\\ntheory of defect because the alternative design’s mere availability does not prove that the\\n\\nexisting design is defective or could lead to a UIA. See Sexton, 926 F.2d at 337–38\\n\\n(remanding for new trial where district court improperly allowed expert testimony of a\\n\\npossible alternative design to substitute for evidence that was necessary to satisfy\\n\\nplaintiff’s burden of showing a design defect); Edwards, 63 F. App’x at 680–81\\n\\n(discussing the difference between the two types of evidence). The Plaintiffs further\\n\\ndirect our attention to Ford’s internal documents without discussing what these\\n\\ndocuments specifically contain or how they prove the missing element of causation.\\n\\nInstead, they generally argue that “the factual record in this case is rife with internal\\n\\ndocuments demonstrating Ford’s knowledge of the defect.” Reply Br. 14. Like the\\n\\nPlaintiffs’ other evidence, this generalized argument neither proves nor disproves their\\n\\ntheory of defect. Lastly, the Plaintiffs focus on the opinion of the software expert, Steve\\n\\nLoudon, but the district court could not have considered this opinion because the\\n\\nPlaintiffs admit that it was not available to the court and is not in the record. Thus, we\\n\\nagree with the district court that after the expert opinions were excluded, the Plaintiffs\\n\\nhad no proof of a defect in Ford’s ETC system.\\n\\n\\n\\n\\n 21\\n\\f Because the Plaintiffs could not prove their theory of defect and thus fail to meet\\n\\nthe essential element of causation, we affirm the district court’s grant of summary\\n\\njudgment on all claims to Ford. 9\\n\\n\\n\\n III.\\n\\n For the foregoing reasons, the district court’s Daubert and summary judgment\\n\\ndecisions are\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 9\\n We find it unnecessary to assess the merits of the Plaintiffs’ claims dismissed\\nunder Federal Rule of Civil Procedure 12(b)(6) because those claims are based on the\\nsame unsubstantiated theory and suffer from the same lack of proof, although the district\\ncourt dismissed them for additional reasons not discussed here. Thus, even if those claims\\nhad survived the Rule 12(b)(6) challenge, they would not have survived the district\\ncourt’s summary judgment rulings because all contain the same failure of proof.\\n Similarly, we find without merit the Plaintiffs’ argument that the district court\\nerred by granting summary judgment to Ford on their various state consumer protection\\nclaims because those claims also fail for the reasons stated herein. The Plaintiffs argue\\nthe court did not recognize that those claims simply require “the breach of a duty to warn\\nconsumers of a known risk or danger or violation of a prohibition against misleading the\\nconsumer.” Opening Br. 37. The Plaintiffs cannot establish the existence of a defect, let\\nalone its risk or danger. Ford does not have a duty to warn consumers of an unproven risk\\nor danger associated with a hypothetical and unproven defect.\\n\\n 22\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4380560/\", \"author_raw\": \"AGEE, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"AGEE"},"judge2":{"kind":"string","value":"HARRIS"},"judge3":{"kind":"string","value":"DUNCAN"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4603307/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Lance R. BELVILLE; Donald C. Carr; Mindi Stewart; Stanley Stewart; Charles Johnson; Jill Durant; Michael Antramgarza; Quintin Williams; ACA Legal Investigations, Inc. ; John McGee; David H. Patton; Inez A. Patton; Pamela D. Smith; Betty J. Trinque; Sharon Shaffer ; Robert Brandon; Daniel Gallegos ; Timothy Matthews; Samuel Hairston; Rhoda Jeffers; Mary Phippen; Jonathan Poma; Shelley Riley; Charles T. Burd; William S. Troutman; Shane Mayfield; Andrea Martin; Thomas Porter; Hasen Design Build & Development, Inc., Plaintiffs - Appellants, and Dean Richardson; Christine Salamone; Beverly Gorton; Josh Legato; Roofwerks, Inc. ; Mills Allison; Laura Elsinger, And; Gabriel Kletschka, Individually and on Behalf of All Others Similarly Situated; Carolyn Chase ; Greg Peet; Tony Burnett ; George Shaffer; Robert Agris; John E. Grimaldi; Jolene Harris, Plaintiffs, v. FORD MOTOR COMPANY, Defendant - Appellee.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-03-25\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-1470\n\n\nLANCE R. BELVILLE; DONALD C. CARR; MINDI STEWART; STANLEY\nSTEWART; CHARLES JOHNSON; JILL DURANT; MICHAEL ANTRAMGARZA;\nQUINTIN WILLIAMS; ACA LEGAL INVESTIGATIONS, INC.; JOHN MCGEE;\nDAVID H. PATTON; INEZ A. PATTON; PAMELA D. SMITH; BETTY J. TRINQUE;\nSHARON SHAFFER; ROBERT BRANDON; DANIEL GALLEGOS; TIMOTHY\nMATTHEWS; SAMUEL HAIRSTON; RHODA JEFFERS; MARY PHIPPEN;\nJONATHAN POMA; SHELLEY RILEY; CHARLES T. BURD; WILLIAM S.\nTROUTMAN; SHANE MAYFIELD; ANDREA MARTIN; THOMAS PORTER;\nHASEN DESIGN BUILD & DEVELOPMENT, INC.,\n\n Plaintiffs – Appellants,\n\nand\n\nDEAN RICHARDSON; CHRISTINE SALAMONE; BEVERLY GORTON; JOSH\nLEGATO; ROOFWERKS, INC.; MILLS ALLISON; LAURA ELSINGER, and;\nGABRIEL KLETSCHKA, Individually and on behalf of all others similarly situated;\nCAROLYN CHASE; GREG PEET; TONY BURNETT; GEORGE SHAFFER;\nROBERT AGRIS; JOHN E. GRIMALDI; JOLENE HARRIS,\n\n Plaintiffs,\n\nv.\n\nFORD MOTOR COMPANY,\n\n Defendant – Appellee.\n\n\nAppeal from the United States District Court for the Southern District of West Virginia,\nat Huntington. Robert C. Chambers, District Judge. (3:13-cv-06529)\n\n\nArgued: January 29, 2019 Decided: March 25, 2019\n\fBefore AGEE and HARRIS, Circuit Judges, and DUNCAN, Senior Circuit Judge.\n\n\nAffirmed by published opinion. Judge Agee wrote the opinion, in which Judge Harris\nand Senior Judge Duncan joined.\n\n\nARGUED: John E. Tangren, DICELLO LEVITT & CASEY LLC, Chicago, Illinois, for\nAppellants. Jonathan D. Hacker, O’MELVENY & MYERS LLP, Washington, D.C., for\nAppellee. ON BRIEF: Adam J. Levitt, John E. Tangren, DICELLO LEVITT & CASEY\nLLC, Chicago, Illinois; Niall A. Paul, SPILMAN THOMAS & BATTLE, PLLC,\nCharleston, West Virginia; Gregory M. Travalio, Mark H. Troutman, Shawn K. Judge,\nISAAC WILES BURKHOLDER & TEETOR, LLC, Columbus, Ohio, for Appellants.\nSarah Virginia Bondurant Price, MCGUIREWOODS LLP, Richmond, Virginia;\nJonathan D. Hacker, Bradley N. Garcia, O’MELVENY & MYERS LLP, Washington,\nD.C., for Appellee.\n\n\n\n\n 2\n\fAGEE, Circuit Judge:\n\n A group of individuals and corporations sued Ford Motor Company for an alleged\n\ndefect in their purchased or leased Ford vehicles manufactured between 2002 and 2010.\n\nThe district court dismissed various claims of certain Plaintiffs, excluded the opinions of\n\nthe Plaintiffs’ three experts, and granted summary judgment to Ford on all claims.\n\nTwenty-seven individual and two corporate Plaintiffs1 now appeal and, for the reasons set\n\nout below, we affirm the judgment of the district court.\n\n\n\n I.\n\n In 2013, various individuals and corporations filed three related actions in the\n\nSouthern District of West Virginia, alleging that their Ford vehicles had a defective\n\nelectronic throttle control (“ETC”) system, which could lead to an unintended\n\nacceleration (“UIA”). They further alleged that to prevent a UIA, Ford should have\n\nequipped their vehicles with an alternative failsafe system such as a Brake Over\n\nAccelerator (“BOA”). Based on this theory of defect, the Plaintiffs asserted numerous\n\nstate and federal claims, including a violation of the Magnuson–Moss Warranty Act,\n\nbreach of implied and express warranty, unjust enrichment, and a violation of state\n\nconsumer protection statutes.\n\n\n\n1\n Plaintiffs in the proceedings below included Appellants as well as fourteen other\nindividuals and one corporation. These other Plaintiffs did not file a notice of appeal. For\nconvenience and to avoid confusion, we will identify all plaintiffs below as “Plaintiffs,”\nwhich includes Appellants.\n\n 3\n\f Despite the alleged defect, only sixteen Plaintiffs alleged that they actually\n\nexperienced UIAs, and none had suffered personal injury or property damage from the\n\nalleged defect. Nonetheless, all Plaintiffs sought economic damages arguing that the\n\nalleged defect made their vehicles worth less than their purchase or lease price.\n\nSpecifically, they requested “damages to recover for diminished value at the time of\n\npurchase,” Belville v. Ford Motor Co., 13 F. Supp. 3d 528, 535 (S.D.W. Va. 2014),\n\nwhich they posit on appeal is—for “many” Plaintiffs— “the market price to repair the\n\ndefective Class Vehicles.” Reply Br. 17.\n\n Ford filed motions to dismiss all three actions, which the district court granted in\n\npart and denied in part. Bellville, 13 F. Supp. 3d at 530. In 2014, the court dismissed,\n\namong other claims, the warranty and unjust enrichment claims of those Plaintiffs who\n\nhad not experienced a UIA because they “failed to demonstrate a plausible claim that\n\nthey paid more for their vehicles than their actual worth when they have used their\n\nvehicles without incident for many years.” Id. at 542. After the dismissal order was\n\nissued, the Plaintiffs twice attempted to amend their complaints. In considering the\n\nmotions to amend, the district court clarified which claims were dismissed, consolidated\n\nthe three actions into one, and directed the Plaintiffs to file a consolidated amended\n\ncomplaint consistent with the court’s orders.\n\n In December 2015, seventeen individuals and two corporations, as the Plaintiffs in\n\nthe consolidated action, filed a Second Amended Master Consolidated Class Action\n\n\n\n\n 4\n\fComplaint, 2 which became the operative complaint. As distinguished from the initial\n\ncomplaints, all but two Plaintiffs 3 now alleged that they experienced a UIA due to a\n\ndefective ETC system in their Ford vehicles. Based on this alleged defect, the Plaintiffs\n\ncontinued to assert one federal claim—a violation of the Magnuson-Moss Warranty\n\nAct—and numerous state claims, including breach of express and implied warranty, fraud,\n\nand unjust enrichment claims.\n\n Ford moved to exclude the Plaintiffs’ expert witnesses and for summary judgment.\n\nBy order of February 27, 2018, the district court granted partial summary judgment to\n\nFord on the warranty and unjust enrichment claims, noting that because many factors\n\nunrelated to an ETC system may cause UIAs, the Plaintiffs’ mere allegations that they\n\nexperienced UIAs were not evidence of a defect. See Johnson v. Ford Motor Co., 310 F.\n\nSupp. 3d 699 (S.D.W. Va. 2018). It observed that to survive Ford’s motion for summary\n\njudgment, the Plaintiffs must establish “a causal link between their alleged [UIAs] and\n\n\n\n 2\n The Plaintiffs moved for class certification in January 2018, but the district court\ngranted summary judgment on all claims to Ford before ruling on this motion. Thus, the\ncourt never certified a class.\n 3\n In the initial complaints, sixteen Plaintiffs, including Roofwerks, Inc., Greg Peet,\nCarolyn Chase, Robert Agris, and John Grimaldi, alleged that they experienced UIAs.\nWith the district court’s permission, Roofwerks, Peet, Chase, Agris and Grimaldi\nvoluntarily dismissed their claims.\n Nineteen of the Plaintiffs who survived the dismissal orders became the Plaintiffs\nin the consolidated action. This group included eleven Plaintiffs who alleged in the initial\ncomplaints that they experienced UIAs. The six other Plaintiffs changed their stance and\nalleged in the amended complaint that they experienced UIAs. Two Plaintiffs, John\nMcGee and Hasen Design Build & Development, Inc., did not allege that they\nexperienced UIAs or assert any warranty or unjust enrichment claims. All Plaintiffs in the\nconsolidated action are parties to this appeal.\n\n 5\n\fthe alleged defect.” Id. at 704. The district court held the Plaintiffs failed to produce\n\nevidence of causation, explaining:\n\n none of [Plaintiffs’ proposed] experts can say that, for those Plaintiffs who\n alleged they experienced [a UIA], their events were the result of the alleged\n defect with the ETC system. Quite simply, Plaintiffs produced no experts\n who can testify that [their] alleged [UIAs] were proximately caused by the\n alleged defect rather than some other known cause for such events.\n\nId. at 706–07. The court found, “this gap between Plaintiffs’ experts’ opinions and what\n\nallegedly occurred in Plaintiffs’ specific vehicles fatal to Plaintiffs’ warranty and unjust\n\nenrichment claims.” Id. at 707.\n\n By order of March 26, 2018, the district court resolved the Plaintiffs’ remaining\n\nclaims. Johnson v. Ford Motor Co., No. 3:13-6529, 2018 WL 1512377 (S.D.W. Va. Mar.\n\n26, 2018). The district court first granted Ford’s motion to exclude the opinions of the\n\nPlaintiffs’ three experts, Todd H. Hubing, Ph.D., Marthinus van Schoor, Ph.D., and Philip\n\nKoopman, Ph.D., holding that their opinions were inadmissible under Rule 702 of the\n\nFederal Rules of Evidence and Daubert v. Merrell Dow Pharmaceuticals, Inc., 509 U.S.\n\n579 (1993). And “the challenged expert opinions [were] critical to the remaining\n\nsummary judgment issues.” Id. at *1. Because the expert opinions failed to prove the\n\nPlaintiffs’ theory of defect, the theory was “largely hypothetical.” Id. at *2.\n\n As the district court explained, the Plaintiffs’ “theory is that many predictable\n\nflaws may occur with the pedal sensors. Plaintiffs theorize that these flawed sensors\n\nproduce faulty voltage signals that should trigger the ETC system’s failsafe modes.\n\nHowever, due to a defectively designed ETC system, the failsafe modes are not activated,\n\n\n\n 6\n\fresulting in [UIAs].” Id at *3. Thus, “testing of ETC systems was central to the experts’\n\nopinions.” Id at *2.\n\n The district court found that the experts’ “testing was flawed, and Plaintiffs have\n\nfailed to establish other means by which their experts can meet the reliability standard.”\n\nId. The district court noted, for example, that the only peer-reviewed publication relied on\n\nby the experts was a 2015 article by Dr. Hubing; however, the theory relied on in that\n\narticle had been discredited by two federal agencies, the National Highway Traffic Safety\n\nAdministration (“NHTSA”) and the National Aeronautics and Space Administration\n\n(“NASA”). In analyzing the experts’ testing evidence, the court noted the continuing\n\nfailure of proof establishing any causal link:\n\n Although Plaintiffs’ experts purport to test [Plaintiffs’ theory of defect],\n they leave a gap between analytical possibility and actual proof of\n occurrence. The experts attempt to excuse this gap by reporting that the\n defect leaves no evidence of its effect. However, this position shifts the\n burden to Ford to prove the negative. Furthermore, there is no “general\n acceptance” within the automotive safety or engineering community that\n underpins Plaintiffs’ theory. The causes of [UIA] are myriad. Some events\n are attributable to driver error, while others are tied to different defects\n from cruise control to mechanical issues. Even though many drivers’\n complaints of [UIA] are credible and likely caused by some defects,\n Plaintiffs’ theory here is still largely hypothetical . . . .\n\nId. at *3.\n\n The district court examined each of the three experts’ individual opinions to\n\ndetermine whether that opinion should be admitted into evidence. First, the court rejected\n\nthe opinion of Dr. Hubing 4 whose report was primarily based on the article noted above\n\n\n 4\n Dr. Hubing is an electrical engineer and a professor at Clemson University.\n\n 7\n\fand in which he examined five vehicles with ETC systems, including two Ford models, a\n\n2005 Mustang and a 2006 Explorer. After comparing accelerator pedal performance of\n\nthe five vehicles, Dr. Hubing concluded that “Ford’s Gen II ETC system fails to\n\nadequately mitigate accelerator pedal faults which can lead to” UIAs. J.A. 10873. In Dr.\n\nHubing’s opinion, this was “the most probable reason that Ford vehicles with this throttle\n\ncontrol system have high reported rates of” UIAs. J.A. 10873.\n\n The district court found Dr. Hubing’s testing unreliable for two reasons. First, his\n\ntesting required making separate accommodations for the Ford vehicles he tested because\n\nthe testing “was developed to test vehicles with ’two track’ pedal sensors,” but the Ford\n\nvehicles had “three track” pedal sensors. Johnson, 2018 WL 1512377, at *4. To\n\naccommodate this difference, Dr. Hubing arbitrarily assigned a set value to Ford’s third\n\npedal without knowing how this affected Ford’s computer source code or software\n\nprogram. In some cases, the set value he used for the third track intentionally caused the\n\nvehicles to accelerate if one of the other two sensors’ values matched this set value.\n\n Second, Dr. Hubing’s testing rested on questionable assumptions that lacked\n\nevidentiary foundations. The voltages he injected into the ETC system purportedly\n\nsimulated real-world circumstances and actual vehicle conditions. But the voltage values\n\nsimply reflected Dr. Hubing’s “assumptions of what would happen” if factors such as a\n\nworn sensor, loose connector, or tin whisker existed. Id. at *4 n.6. Furthermore, Dr.\n\nHubing’s testing revealed that UIAs occurred when two pedal sensors produced values of\n\na certain range, and those values were “close to the same . . . , as though each sensor was\n\nfaulting in the same way.” Id. at *4. But Dr. Hubing did not “offer any testing of sensors\n\n 8\n\fto verify the assumption that both sensors should be expected to fault and that they do so\n\nin the same way.” Id.\n\n The court found that the sources supporting Dr. Hubing’s sensor assumption were\n\ninsufficient to be reliable. Dr. Hubing’s assumption was based on two sources: “first, by\n\nreference to various documents, such as Ford’s CQIS database (complaints relating to\n\neither pedal faults and/or [UIA]) and Ford’s design and development phases for the Gen\n\nII ETC system; second, the inherent knowledge of the expert.” Id. The first source did\n\n“little” to support Dr. Hubing’s assumption because these documents were “brief,\n\nand very few reflect[ed] an inspection, testing, or analysis by a trained eye.” Id. As for\n\nDr. Hubing’s qualifications, those alone could not substitute for the lack of testing\n\nevidence.\n\n The district court found further problems with Dr. Hubing’s report, including that\n\n“degraded sensors are not the defect, nor are they the only precipitating cause of [UIA],\n\naccording to Plaintiffs’ claim. However, Dr. Hubing’s theory of defect rests significantly\n\non the system’s inability to properly recognize and mitigate faulty sensors.” Id. Dr.\n\nHubing also had never tested the Plaintiffs’ actual vehicles or attempted to produce\n\nvoltages that would cause a UIA instead of simply injecting these voltages. Finally, the\n\nNHTSA and NASA in 2011 had rejected his theory as lacking real-world evidence.\n\nBased on all these findings, the court excluded Dr. Hubing’s opinion.\n\n Next, the court considered the opinion of Dr. van Schoor who holds a Ph.D. in\n\naeronautics and astronautics. He opined that Ford’s accelerator pedal sensors are subject\n\nto wear or “gunk” buildup, either of which “can lead to failure and erratic vehicle\n\n 9\n\fbehavior.” J.A.10972. The district court found three problems with this theory: (1)\n\nPlaintiffs’ counsel “explicitly stated that Plaintiffs were not offering his opinion as to a\n\ndefect;” (2) Dr. van Schoor did not perform any inspections or surveys to support his\n\ntheory; and (3) he “did not attribute any of Plaintiffs’ [UIAs] to the problems he\n\nidentified in his report.” Johnson, 2018 WL 1512377, at *5. Thus, the court found his\n\ntheory irrelevant to the Plaintiffs’ theory of defect.\n\n Dr. van Schoor also offered an opinion on an alternative vehicle design with BOA,\n\nbut the court did not examine this in depth because the availability of an alternative\n\ndesign was not proof of the alleged defect.5 Based on these findings, the court excluded\n\nDr. van Schoor’s report.\n\n The third expert at issue was Dr. Koopman, 6 who opined that a design defect made\n\nFord’s Gen II ETC system vulnerable to allowing UIAs. In support, Dr. Koopman tested\n\ntwo Ford models, a 2005 Mustang and a 2006 Fusion, by injecting voltages into the\n\naccelerator wiring harness as a substitute for the three accelerator pedal sensors. Similar\n\nto Dr. Hubing’s testing, the injected voltages represented the voltages “likely produced\n\n 5\n The district court’s holding is consistent with our precedent. See Sexton By and\nThrough Sexton v. Bell Helmets, Inc., 926 F.2d 331, 338 (4th Cir. 1991) (holding that the\nsimple availability of an alternative design at the time of trial “does not lead to the\nconclusion that the design of the [product] was defective”); see also Edwards v. Bell\nHelicopter Textron, Inc., 63 F. App’x 674, 680–81 (4th Cir. 2003) (per curiam)\n(determining that the availability of an alternative design “was irrelevant to the proof” of\nthe strict liability and negligent defective design claims because the existence of an\nalternative design could not have contributed to the alleged injury and therefore did not\nestablish that an alleged design defect in the product was a proximate cause of the alleged\ninjuries).\n 6\n Dr. Koopman is a tenured Associate Professor in the Electrical and Computer\nEngineering Department of Carnegie Mellon University.\n\n 10\n\fby sensors degraded in one or more ways, such as from wear and tear, loose wires, and\n\nwater intrusion.” Johnson, 2018 WL 1512377, at *5. Next, he evaluated “actual vehicle\n\nperformance” by repeating this testing on a dynamometer 7 that was designed to simulate\n\nan actual vehicle condition. Id. Based on the results of his testing, Dr. Koopman\n\nconcluded that a UIA occurs when two or more sensors produce voltages of a certain\n\nrange close to each other.\n\n The district court found Dr. Koopman’s approach unreliable for much the same\n\nreasons that it found Dr. Hubing’s opinion defective. The court noted that he did not test\n\nor prove his assumption that two or more degraded sensors have produced or would\n\nproduce the voltages he used for his testing. Furthermore, Dr. Koopman purposely chose\n\narbitrary voltage inputs that would instruct the system to accelerate. Thus, his “testing\n\nwas an artificial demonstration that essentially mimicked intentional acceleration.” Id. at\n\n*7, and was not a “realistic example of sensor faults” because it required multiple steps\n\n“in a sequence that ha[d] no ‘real-world’ support.” Id.\n\n Furthermore, the district court concluded “Dr. Koopman’s testimony, that\n\nPlaintiffs’ complaints are consistent with his design defect opinion, is inadequate to tie\n\nhis opinions to this case.” The court explained why this was so:\n\n First, [Dr. Koopman] relies on nothing more specific than the Consolidated\n Complaint to understand Plaintiffs’ [UIAs]. Second, there are profound\n inconsistencies between the general complaints and his opinions. Nearly\n every Plaintiff described a failure of their brakes to counteract the [UIA],\n\n 7\n Dynamometer is a “device for measuring mechanical force, or power, transmitted\nby a rotating shaft.” Dynamometer, Encyc. Britannica (2018); see Maxwell Dynamometer\nCo. v. United States, 386 F.2d 855, 859 (Ct. Cl. 1967).\n\n 11\n\f yet in Dr. Koopman’s own testing procedure, the brakes restrained the\n acceleration. Further, some Plaintiffs reported that their gas pedals were\n moving up and down without a foot-on-pedal, a circumstance not replicated\n in any of the tests done by Plaintiffs’ experts. If these Plaintiffs were right,\n this pedal problem likely would be mechanical, perhaps caused by the\n return spring.\n\nId. at *8 (internal citation omitted). Because his testing was not “a reliable basis” for his\n\nopinions regarding the alleged defect, the district court excluded Dr. Koopman’s opinion.\n\nId.\n\n The district court also found problematic that none of the Plaintiffs’ experts had\n\ntested or inspected the Plaintiffs’ actual vehicles or attempted to connect their testing to\n\nany of those vehicles. Instead, the Plaintiffs asserted the alleged ETC defect and experts’\n\nopinions applied universally to all the thousands of vehicles in their purported class\n\ndespite Drs. Koopman’s and Hubing’s opinions that their testing results varied\n\nsignificantly between individual vehicles and that the pedal sensors differed among the\n\nclass vehicles.\n\n Once the expert opinions were excluded, the district court concluded that the\n\nPlaintiffs had “no evidence of their core allegation that there is a design defect in Ford’s\n\nGen II ETC system.” Id. Insomuch as the Plaintiffs’ theory of defect was without an\n\nevidentiary basis, they could not establish the existence of a defect and the necessary\n\nelement of causation. Accordingly, the district court granted summary judgment on all\n\nremaining claims to Ford.\n\n A group of the Plaintiffs now appeal, and this Court has jurisdiction under 28\n\nU.S.C. § 1291.\n\n\n 12\n\f II.\n\n A.\n\n We review summary judgment decisions de novo, see Campbell v. Hewitt,\n\nColeman & Assocs., Inc., 21 F.3d 52, 53 (4th Cir. 1994), and Daubert decisions for abuse\n\nof discretion, see Nease v. Ford Motor Co., 848 F.3d 219, 228 (4th Cir. 2017). A district\n\ncourt abuses its discretion if it makes an error of law or clearly erroneous factual finding.\n\nSee id. at 228.\n\n The merits of the district court’s Daubert decision addressing the Plaintiffs’ proof\n\nof their defect theory is our initial focus because their entire case hinges on the allegedly\n\ndefective ETC system as the cause of UIAs. UIAs alone do not substantiate their theory\n\nbecause, as the Plaintiffs concede on appeal, many factors unrelated to an ETC system\n\ncould trigger UIAs. See, e.g., Opening Br. 31 (“[M]ultiple circumstances can initiate\n\nunintended acceleration signals.”). Thus, to establish the existence of the alleged defect\n\nand the requisite causal link between it and their UIAs, the Plaintiffs proffered the\n\nopinions of the three experts, Drs. Hubing, van Schoor, and Koopman. As the district\n\ncourt recognized, these experts’ opinions are “critical” to the Plaintiffs’ case because\n\ntheir theory of defect is “largely hypothetical” without them. Johnson, 2018 WL\n\n1512377, at *3. Accordingly, if the district court correctly excluded the expert opinions,\n\nthe Plaintiffs’ case fails because they would be “unable to prove the fundamental theory\n\nof their case.” Id. at *9.\n\n B.\n\n 13\n\f The district court excluded the expert opinions under the Supreme Court’s\n\nlandmark precedent in Daubert, which established that under the Federal Rules of\n\nEvidence “the admissibility of scientific evidence no longer was limited to knowledge or\n\nevidence ‘generally accepted’ as reliable in the relevant scientific community.” Nease,\n\n848 F.3d at 228 (citing Daubert, 509 U.S. at 588–89). Instead, Daubert held that courts\n\nmust evaluate proposed expert testimony according to Rule 702, which tasks a district\n\njudge with “ensuring that an expert’s testimony both rests on a reliable foundation and is\n\nrelevant to the task at hand.” 509 U.S. at 597. This rule requires trial judges to conduct “a\n\npreliminary assessment of whether the reasoning or methodology underlying the\n\ntestimony is scientifically valid and of whether that reasoning or methodology properly\n\ncan be applied to the facts in issue. . . . . Many factors will bear on the inquiry, and we do\n\nnot presume to set out a definitive checklist or test.” Id. at 592–93.\n\n Under Rule 702, an expert’s testimony is relevant if it has “a valid scientific\n\nconnection to the pertinent inquiry.” Id. at 592. To be reliable, the testimony “must be\n\nbased on scientific, technical, or other specialized knowledge and not on belief or\n\nspeculation, and inferences must be derived using scientific or other valid methods.”\n\nOglesby v. Gen. Motors Corp., 190 F.3d 244, 250 (4th Cir. 1999) (citing Daubert, 509\n\nU.S. at 590, 592–93).\n\n In determining whether expert testimony is “sufficiently reliable to be admissible,”\n\na district court generally considers several factors:\n\n First, “a key question to be answered in determining whether a theory or\n technique is scientific knowledge that will assist the trier of fact will be\n whether it can be (and has been) tested.” A second question . . . is “whether\n\n 14\n\f the theory or technique has been subjected to peer review and\n publication.” Publication regarding the theory bears upon peer review; “the\n fact of publication (or lack thereof) in a peer reviewed journal will be a\n relevant, though not dispositive, consideration in assessing the scientific\n validity of a particular technique or methodology on which an opinion is\n premised.” Third, “in the case of a particular scientific technique, the court\n ordinarily should consider the known or potential rate of error.” Fourth, . . .\n “‘general acceptance’” is . . . relevant to the reliability inquiry.\n “Widespread acceptance can be an important factor in ruling particular\n evidence admissible, and a known technique which has been able to attract\n only minimal support with the community may properly be viewed with\n skepticism.”\n\nNease, 848 F.3d at 229 (quoting Daubert, 509 U.S. at 593–94) (internal citations and\n\nalterations omitted).\n\n This list, however, is “not exhaustive,” and “‘neither necessarily nor exclusively\n\napplies to all experts or in every case.’” Id. (quoting Kumho Tire Co. v. Carmichael, 526\n\nU.S. 137, 141 (1999)). “[A]t bottom, the court’s evaluation is always a flexible one, and\n\nthe court’s conclusions necessarily amount to an exercise of broad discretion guided by\n\nthe overarching criteria of relevance and reliability.” Oglesby, 190 F.3d at 250. Thus, the\n\ntrial court has “broad latitude” in determining whether “Daubert’s specific factors are, or\n\nare not, reasonable measures of reliability in a particular case.” Kumho Tire, 526 U.S. at\n\n153. Here, the district court properly considered appropriate factors and did not abuse its\n\ndiscretion in excluding the experts’ opinions based on their lack of relevance and\n\nreliability.\n\n C.\n\n The Plaintiffs fail to show that the district court made “a clearly erroneous factual\n\nfinding” or “error of law” by excluding their expert witnesses. See Nease, 848 F.3d at\n\n\n 15\n\f228. They argue that the district court did not consider certain Daubert factors, such as\n\nthe known or potential rate of error, or considered Daubert factors, like peer review, in an\n\ninappropriate manner. This argument lacks merit, in part, because the Plaintiffs do not\n\nidentify a tangible error in the district court’s analysis. The district court was not under\n\nany obligation to consider a certain factor or weigh factors it did consider in a particular\n\nmanner. See id. at 229. As noted earlier, the trial court’s inquiry is a “flexible one,” and it\n\nexercises “broad discretion” in choosing which Daubert factors to apply and how to\n\nconsider them. Oglesby, 190 F.3d at 250; accord Nease, 848 F.3d at 229.\n\n The Plaintiffs further argue that the court made conclusory findings and wrongly\n\nassessed the expert opinions. We disagree. Contrary to the Plaintiffs’ assertion, our\n\nreview shows that the district court thoroughly reviewed the record, including the\n\nexperts’ reports and the depositions of these experts, to understand their testing, theories,\n\nand methodologies. The court then provided a well-reasoned analysis of the experts’\n\ntheories and testing based on its consideration of relevant Daubert factors such as general\n\nacceptance of a theory within a relevant field, peer review, and the scientific validity of\n\ntheir underlying methodologies.\n\n For example, the district court properly noted that Dr. Hubing’s testing method\n\nwas, at a minimum, suspect because it had been rejected by NASA and NHTSA. Further,\n\nas the court pointed out, Dr. Hubing never tested any vehicle in actual conditions so all\n\nhis projections were purely theoretical. His “testing,” at least in part, seemed artificially\n\ninduced to produce a desired result and did not reflect real-world results from any vehicle\n\nclaiming a UIA. In sum, Dr. Hubing’s opinion was partly ipse dixit.\n\n 16\n\f As for Dr. van Schoor, even without examining the merits of his testimony, the\n\nPlaintiffs effectively pled him out of the case. During the district court proceedings, the\n\nPlaintiffs stipulated “on the record that Dr. van Schoor will not offer defect opinions per\n\nse.” J.A. 11934. Even more to the point, Plaintiffs’ counsel admitted Dr. van Schoor\n\nfailed to meet the necessary threshold of evidentiary reliability: “candidly I will concede\n\nto the Court that he couches all of his conclusions in the form of a defect opinion.\n\nCandidly I’ll say to the Court that I don’t know that Dr. van Schoor in this case tested his\n\nopinions against the rigor that is required for Federal Rules of Evidence.” J.A. 11932.\n\n Regardless, we find no abuse of discretion in the district court’s merits analysis of\n\nDr. van Schoor’s testimony for the reasons it explained. We simply note two salient\n\npoints from that analysis: Dr. van Schoor “performed no inspections nor surveys to\n\nsupport his theory about contacting sensors” and “did not attribute any of Plaintiffs’\n\n[UIAs] to the problems he identified in his report.” Johnson, 2018 WL 1512377, at *5.\n\n Dr. Koopman’s testimony fares no better. As with the other experts, there is a\n\nconsiderable gap between Dr. Koopman’s theory and any evidentiary proof of causation\n\nrelated to an ETC defect and a UIA. The district court aptly recited the evidentiary failure\n\non Dr. Koopman’s part:\n\n Dr. Koopman admits that in many of his tests, he injected faults with\n voltages designed to produce pedal angles consistent with acceleration.\n . . . Yet, nowhere does he validate his hypothesis that degraded\n sensors, presumably to be expected, will actually cause or, in fact, have\n produced faulty voltages in the way he arranged for his testing. . . . The\n testing was an artificial demonstration that essentially mimicked intentional\n acceleration. Dr. Koopman offers no testing of Plaintiffs’ vehicles, or the\n exemplars he chose, to demonstrate how degraded sensors or the other\n\n\n 17\n\f circumstances can produce similar voltages that result in unintended open\n throttle.\n\nId. at *7 (internal citation omitted).\n\n Further, the district court correctly observed that none of the experts tested any of\n\nthe Plaintiffs’ vehicles or any of the thousands of Ford vehicles in their purported class\n\nwhich they allege had a UIA. Of the multitude of vehicles the Plaintiffs claim to be\n\ndefective, the record does not reflect they attempted to test even one vehicle purported to\n\nhave had a UIA, much less conduct such a test under real-world conditions. Most\n\nimportantly, none of the proffered expert opinions purport to tie their testing to any\n\nalleged UIA so as to show the fundamental element of causation. To the contrary, the\n\nPlaintiffs’ experts disclaimed any finding or opinion as to the causation of any specific\n\nUIA. J.A. 1754 ([Counsel’s question to Dr. Hubing:] “But you can’t say that your\n\nvulnerabilities that you identify actually cause the event in the plaintiffs’ vehicles,\n\ncorrect? . . . [Answer:] In any one of those vehicles, no.”); J.A. 10196–97 ([Counsel’s\n\nquestion to Dr. van Schoor:] “Have you identified any alleged unwanted acceleration\n\nevent occurring in a Ford vehicle that you have determined resulted from any of the\n\nalleged defects or vulnerabilities that you have identified in your report? [Answer:] I have\n\nnot.”); see also J.A. 8922–23 ([Counsel’s question to Dr. Koopman:]“And then you don’t\n\ngo out to the vehicle to see if there are any other possible causes or explanation for their\n\nclaim; correct? . . . [Answer:] I have not physically examined the vehicles.”); J.A. 8925–\n\n26 ([Dr. Koopman:] “What I am saying is that I see explanations consistent with software\n\n\n\n\n 18\n\fand hardware defects, and I see that that’s consistent with my report. That’s all I have\n\nbeen saying.”). 8\n\n The court’s well-articulated analysis clearly distinguishes this case from Nease in\n\nwhich the district court failed to act as a gatekeeper by not assessing the expert’s\n\nreliability but leaving that question to the jury. See 848 F.3d at 231. Instead, the court\n\nhere faithfully performed its duty as a “gatekeeper” in the manner we approved in In re\n\nLipitor (Atorvastatin Calcium) Marketing, Sales Practices and Products Liability\n\nLitigation (No II) MDL 2502, 892 F.3d 624, 631 (4th Cir. 2018). There, we upheld the\n\ndistrict court’s extensive analysis of the experts’ theories and testing, which formed the\n\nbasis of the court’s exclusion of several expert opinions, because that court, like the\n\ndistrict court here, properly “identified and articulated clear . . . concerns it had about the\n\nmanner in which [the expert] reached his conclusions.” Id. at 638. In approving the\n\ndistrict court’s analysis in In re Lipitor, we once more emphasized that “‘[m]any factors\n\nwill bear on the inquiry,’ and there is no ‘definitive checklist or test.’” Id. at 637 (quoting\n\nDaubert, 509 U.S. at 593).\n\n Having failed on their primary arguments, the Plaintiffs argue that the district\n\ncourt mischaracterizes the experts’ testimony during depositions, but this argument\n\n 8\n The district court found, as do we, the anomaly of the Plaintiffs’ theory at trial\nthat the ETC defect was universal to all the class vehicles, but that their experts own\nlaboratory testing showed significant differences between vehicles. As the district court\nnoted, “Dr. Hubing’s testing revealed significant differences between the two Ford\nvehicles, which he asserts had identical ETC systems,” and yet, the Plaintiffs are\n“inconsistent” because they “maintain the Gen II ETC system used by Ford is exactly the\nsame in all vehicles, but then they excuse results when it is not.” Johnson, 2018 WL\n1512377, at *8.\n\n 19\n\fsimply channels the Plaintiffs’ disagreement with the district court’s findings. The\n\nPlaintiffs essentially assert the district court erred by making findings that were favorable\n\nto Ford or reaching conclusions that contradicted their portrayal of the expert opinions.\n\nFor instance, the Plaintiffs challenge the district court’s finding that when Dr. Hubing\n\nwas asked whether “he ever saw ‘dual faults occur in the same resistive ranges’ in the\n\n‘real world,’ [he] ultimately answered no.” Johnson, 2018 WL 1512377, at *4. They\n\nassert that this finding is erroneous because Dr. Hubing answered “no” to an entirely\n\ndifferent question. Our review of the record reveals that the district court’s finding is\n\ncorrect. When Ford’s counsel asked Dr. Hubing whether he had ever “physically see[n] . .\n\n. dual faults occur in the same resistive range,” he answered, “. . . how would we do\n\nthat?” because “physical evidence of two simultaneous faults occurring [in the real\n\nworld] . . . would be basically impossible to find.” J.A. 09335–36. Similarly, the\n\nPlaintiffs’ other arguments related to the district court’s alleged mischaracterization\n\nreveal no more than their disagreement with the district court’s findings or contrary\n\ninterpretation, and do not show that the court committed any error.\n\n Once the opinions of the three experts were excluded, the district court necessarily\n\nconcluded that the Plaintiffs had “no evidence of their core allegation that there is a\n\ndesign defect in Ford’s Gen II ETC system.” Johnson, 2018 WL 1512377, at *8. As the\n\ncourt held, other evidence that the Plaintiffs recite, such as a software expert’s opinion\n\nand Ford’s internal documents, does not prove their defect theory.\n\n The Plaintiffs point to unverified reports of UIAs from Ford vehicle drivers, but,\n\nas noted above, UIA alone does not prove the existence of a defect. Similarly, the\n\n 20\n\favailability of an alternative vehicle design with BOA does not substantiate the Plaintiffs’\n\ntheory of defect because the alternative design’s mere availability does not prove that the\n\nexisting design is defective or could lead to a UIA. See Sexton, 926 F.2d at 337–38\n\n(remanding for new trial where district court improperly allowed expert testimony of a\n\npossible alternative design to substitute for evidence that was necessary to satisfy\n\nplaintiff’s burden of showing a design defect); Edwards, 63 F. App’x at 680–81\n\n(discussing the difference between the two types of evidence). The Plaintiffs further\n\ndirect our attention to Ford’s internal documents without discussing what these\n\ndocuments specifically contain or how they prove the missing element of causation.\n\nInstead, they generally argue that “the factual record in this case is rife with internal\n\ndocuments demonstrating Ford’s knowledge of the defect.” Reply Br. 14. Like the\n\nPlaintiffs’ other evidence, this generalized argument neither proves nor disproves their\n\ntheory of defect. Lastly, the Plaintiffs focus on the opinion of the software expert, Steve\n\nLoudon, but the district court could not have considered this opinion because the\n\nPlaintiffs admit that it was not available to the court and is not in the record. Thus, we\n\nagree with the district court that after the expert opinions were excluded, the Plaintiffs\n\nhad no proof of a defect in Ford’s ETC system.\n\n\n\n\n 21\n\f Because the Plaintiffs could not prove their theory of defect and thus fail to meet\n\nthe essential element of causation, we affirm the district court’s grant of summary\n\njudgment on all claims to Ford. 9\n\n\n\n III.\n\n For the foregoing reasons, the district court’s Daubert and summary judgment\n\ndecisions are\n\n AFFIRMED.\n\n\n\n\n 9\n We find it unnecessary to assess the merits of the Plaintiffs’ claims dismissed\nunder Federal Rule of Civil Procedure 12(b)(6) because those claims are based on the\nsame unsubstantiated theory and suffer from the same lack of proof, although the district\ncourt dismissed them for additional reasons not discussed here. Thus, even if those claims\nhad survived the Rule 12(b)(6) challenge, they would not have survived the district\ncourt’s summary judgment rulings because all contain the same failure of proof.\n Similarly, we find without merit the Plaintiffs’ argument that the district court\nerred by granting summary judgment to Ford on their various state consumer protection\nclaims because those claims also fail for the reasons stated herein. The Plaintiffs argue\nthe court did not recognize that those claims simply require “the breach of a duty to warn\nconsumers of a known risk or danger or violation of a prohibition against misleading the\nconsumer.” Opening Br. 37. The Plaintiffs cannot establish the existence of a defect, let\nalone its risk or danger. Ford does not have a duty to warn consumers of an unproven risk\nor danger associated with a hypothetical and unproven defect.\n\n 22\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Lance R. BELVILLE; Donald C. Carr; Mindi Stewart; Stanley Stewart; Charles Johnson; Jill Durant; Michael Antramgarza; Quintin Williams; ACA Legal Investigations, Inc. ; John McGee; David H. Patton; Inez A. Patton; Pamela D. Smith; Betty J. Trinque; Sharon Shaffer ; Robert Brandon; Daniel Gallegos ; Timothy Matthews; Samuel Hairston; Rhoda Jeffers; Mary Phippen; Jonathan Poma; Shelley Riley; Charles T. Burd; William S. Troutman; Shane Mayfield; Andrea Martin; Thomas Porter; Hasen Design Build & Development, Inc., Plaintiffs - Appellants, and Dean Richardson; Christine Salamone; Beverly Gorton; Josh Legato; Roofwerks, Inc. ; Mills Allison; Laura Elsinger, And; Gabriel Kletschka, Individually and on Behalf of All Others Similarly Situated; Carolyn Chase ; Greg Peet; Tony Burnett ; George Shaffer; Robert Agris; John E. Grimaldi; Jolene Harris, Plaintiffs, v. FORD MOTOR COMPANY, Defendant - Appellee.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-03-25\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-1470\\n\\n\\nLANCE R. BELVILLE; DONALD C. CARR; MINDI STEWART; STANLEY\\nSTEWART; CHARLES JOHNSON; JILL DURANT; MICHAEL ANTRAMGARZA;\\nQUINTIN WILLIAMS; ACA LEGAL INVESTIGATIONS, INC.; JOHN MCGEE;\\nDAVID H. PATTON; INEZ A. PATTON; PAMELA D. SMITH; BETTY J. TRINQUE;\\nSHARON SHAFFER; ROBERT BRANDON; DANIEL GALLEGOS; TIMOTHY\\nMATTHEWS; SAMUEL HAIRSTON; RHODA JEFFERS; MARY PHIPPEN;\\nJONATHAN POMA; SHELLEY RILEY; CHARLES T. BURD; WILLIAM S.\\nTROUTMAN; SHANE MAYFIELD; ANDREA MARTIN; THOMAS PORTER;\\nHASEN DESIGN BUILD & DEVELOPMENT, INC.,\\n\\n Plaintiffs – Appellants,\\n\\nand\\n\\nDEAN RICHARDSON; CHRISTINE SALAMONE; BEVERLY GORTON; JOSH\\nLEGATO; ROOFWERKS, INC.; MILLS ALLISON; LAURA ELSINGER, and;\\nGABRIEL KLETSCHKA, Individually and on behalf of all others similarly situated;\\nCAROLYN CHASE; GREG PEET; TONY BURNETT; GEORGE SHAFFER;\\nROBERT AGRIS; JOHN E. GRIMALDI; JOLENE HARRIS,\\n\\n Plaintiffs,\\n\\nv.\\n\\nFORD MOTOR COMPANY,\\n\\n Defendant – Appellee.\\n\\n\\nAppeal from the United States District Court for the Southern District of West Virginia,\\nat Huntington. Robert C. Chambers, District Judge. (3:13-cv-06529)\\n\\n\\nArgued: January 29, 2019 Decided: March 25, 2019\\n\\fBefore AGEE and HARRIS, Circuit Judges, and DUNCAN, Senior Circuit Judge.\\n\\n\\nAffirmed by published opinion. Judge Agee wrote the opinion, in which Judge Harris\\nand Senior Judge Duncan joined.\\n\\n\\nARGUED: John E. Tangren, DICELLO LEVITT & CASEY LLC, Chicago, Illinois, for\\nAppellants. Jonathan D. Hacker, O’MELVENY & MYERS LLP, Washington, D.C., for\\nAppellee. ON BRIEF: Adam J. Levitt, John E. Tangren, DICELLO LEVITT & CASEY\\nLLC, Chicago, Illinois; Niall A. Paul, SPILMAN THOMAS & BATTLE, PLLC,\\nCharleston, West Virginia; Gregory M. Travalio, Mark H. Troutman, Shawn K. Judge,\\nISAAC WILES BURKHOLDER & TEETOR, LLC, Columbus, Ohio, for Appellants.\\nSarah Virginia Bondurant Price, MCGUIREWOODS LLP, Richmond, Virginia;\\nJonathan D. Hacker, Bradley N. Garcia, O’MELVENY & MYERS LLP, Washington,\\nD.C., for Appellee.\\n\\n\\n\\n\\n 2\\n\\fAGEE, Circuit Judge:\\n\\n A group of individuals and corporations sued Ford Motor Company for an alleged\\n\\ndefect in their purchased or leased Ford vehicles manufactured between 2002 and 2010.\\n\\nThe district court dismissed various claims of certain Plaintiffs, excluded the opinions of\\n\\nthe Plaintiffs’ three experts, and granted summary judgment to Ford on all claims.\\n\\nTwenty-seven individual and two corporate Plaintiffs1 now appeal and, for the reasons set\\n\\nout below, we affirm the judgment of the district court.\\n\\n\\n\\n I.\\n\\n In 2013, various individuals and corporations filed three related actions in the\\n\\nSouthern District of West Virginia, alleging that their Ford vehicles had a defective\\n\\nelectronic throttle control (“ETC”) system, which could lead to an unintended\\n\\nacceleration (“UIA”). They further alleged that to prevent a UIA, Ford should have\\n\\nequipped their vehicles with an alternative failsafe system such as a Brake Over\\n\\nAccelerator (“BOA”). Based on this theory of defect, the Plaintiffs asserted numerous\\n\\nstate and federal claims, including a violation of the Magnuson–Moss Warranty Act,\\n\\nbreach of implied and express warranty, unjust enrichment, and a violation of state\\n\\nconsumer protection statutes.\\n\\n\\n\\n1\\n Plaintiffs in the proceedings below included Appellants as well as fourteen other\\nindividuals and one corporation. These other Plaintiffs did not file a notice of appeal. For\\nconvenience and to avoid confusion, we will identify all plaintiffs below as “Plaintiffs,”\\nwhich includes Appellants.\\n\\n 3\\n\\f Despite the alleged defect, only sixteen Plaintiffs alleged that they actually\\n\\nexperienced UIAs, and none had suffered personal injury or property damage from the\\n\\nalleged defect. Nonetheless, all Plaintiffs sought economic damages arguing that the\\n\\nalleged defect made their vehicles worth less than their purchase or lease price.\\n\\nSpecifically, they requested “damages to recover for diminished value at the time of\\n\\npurchase,” Belville v. Ford Motor Co., 13 F. Supp. 3d 528, 535 (S.D.W. Va. 2014),\\n\\nwhich they posit on appeal is—for “many” Plaintiffs— “the market price to repair the\\n\\ndefective Class Vehicles.” Reply Br. 17.\\n\\n Ford filed motions to dismiss all three actions, which the district court granted in\\n\\npart and denied in part. Bellville, 13 F. Supp. 3d at 530. In 2014, the court dismissed,\\n\\namong other claims, the warranty and unjust enrichment claims of those Plaintiffs who\\n\\nhad not experienced a UIA because they “failed to demonstrate a plausible claim that\\n\\nthey paid more for their vehicles than their actual worth when they have used their\\n\\nvehicles without incident for many years.” Id. at 542. After the dismissal order was\\n\\nissued, the Plaintiffs twice attempted to amend their complaints. In considering the\\n\\nmotions to amend, the district court clarified which claims were dismissed, consolidated\\n\\nthe three actions into one, and directed the Plaintiffs to file a consolidated amended\\n\\ncomplaint consistent with the court’s orders.\\n\\n In December 2015, seventeen individuals and two corporations, as the Plaintiffs in\\n\\nthe consolidated action, filed a Second Amended Master Consolidated Class Action\\n\\n\\n\\n\\n 4\\n\\fComplaint, 2 which became the operative complaint. As distinguished from the initial\\n\\ncomplaints, all but two Plaintiffs 3 now alleged that they experienced a UIA due to a\\n\\ndefective ETC system in their Ford vehicles. Based on this alleged defect, the Plaintiffs\\n\\ncontinued to assert one federal claim—a violation of the Magnuson-Moss Warranty\\n\\nAct—and numerous state claims, including breach of express and implied warranty, fraud,\\n\\nand unjust enrichment claims.\\n\\n Ford moved to exclude the Plaintiffs’ expert witnesses and for summary judgment.\\n\\nBy order of February 27, 2018, the district court granted partial summary judgment to\\n\\nFord on the warranty and unjust enrichment claims, noting that because many factors\\n\\nunrelated to an ETC system may cause UIAs, the Plaintiffs’ mere allegations that they\\n\\nexperienced UIAs were not evidence of a defect. See Johnson v. Ford Motor Co., 310 F.\\n\\nSupp. 3d 699 (S.D.W. Va. 2018). It observed that to survive Ford’s motion for summary\\n\\njudgment, the Plaintiffs must establish “a causal link between their alleged [UIAs] and\\n\\n\\n\\n 2\\n The Plaintiffs moved for class certification in January 2018, but the district court\\ngranted summary judgment on all claims to Ford before ruling on this motion. Thus, the\\ncourt never certified a class.\\n 3\\n In the initial complaints, sixteen Plaintiffs, including Roofwerks, Inc., Greg Peet,\\nCarolyn Chase, Robert Agris, and John Grimaldi, alleged that they experienced UIAs.\\nWith the district court’s permission, Roofwerks, Peet, Chase, Agris and Grimaldi\\nvoluntarily dismissed their claims.\\n Nineteen of the Plaintiffs who survived the dismissal orders became the Plaintiffs\\nin the consolidated action. This group included eleven Plaintiffs who alleged in the initial\\ncomplaints that they experienced UIAs. The six other Plaintiffs changed their stance and\\nalleged in the amended complaint that they experienced UIAs. Two Plaintiffs, John\\nMcGee and Hasen Design Build & Development, Inc., did not allege that they\\nexperienced UIAs or assert any warranty or unjust enrichment claims. All Plaintiffs in the\\nconsolidated action are parties to this appeal.\\n\\n 5\\n\\fthe alleged defect.” Id. at 704. The district court held the Plaintiffs failed to produce\\n\\nevidence of causation, explaining:\\n\\n none of [Plaintiffs’ proposed] experts can say that, for those Plaintiffs who\\n alleged they experienced [a UIA], their events were the result of the alleged\\n defect with the ETC system. Quite simply, Plaintiffs produced no experts\\n who can testify that [their] alleged [UIAs] were proximately caused by the\\n alleged defect rather than some other known cause for such events.\\n\\nId. at 706–07. The court found, “this gap between Plaintiffs’ experts’ opinions and what\\n\\nallegedly occurred in Plaintiffs’ specific vehicles fatal to Plaintiffs’ warranty and unjust\\n\\nenrichment claims.” Id. at 707.\\n\\n By order of March 26, 2018, the district court resolved the Plaintiffs’ remaining\\n\\nclaims. Johnson v. Ford Motor Co., No. 3:13-6529, 2018 WL 1512377 (S.D.W. Va. Mar.\\n\\n26, 2018). The district court first granted Ford’s motion to exclude the opinions of the\\n\\nPlaintiffs’ three experts, Todd H. Hubing, Ph.D., Marthinus van Schoor, Ph.D., and Philip\\n\\nKoopman, Ph.D., holding that their opinions were inadmissible under Rule 702 of the\\n\\nFederal Rules of Evidence and Daubert v. Merrell Dow Pharmaceuticals, Inc., 509 U.S.\\n\\n579 (1993). And “the challenged expert opinions [were] critical to the remaining\\n\\nsummary judgment issues.” Id. at *1. Because the expert opinions failed to prove the\\n\\nPlaintiffs’ theory of defect, the theory was “largely hypothetical.” Id. at *2.\\n\\n As the district court explained, the Plaintiffs’ “theory is that many predictable\\n\\nflaws may occur with the pedal sensors. Plaintiffs theorize that these flawed sensors\\n\\nproduce faulty voltage signals that should trigger the ETC system’s failsafe modes.\\n\\nHowever, due to a defectively designed ETC system, the failsafe modes are not activated,\\n\\n\\n\\n 6\\n\\fresulting in [UIAs].” Id at *3. Thus, “testing of ETC systems was central to the experts’\\n\\nopinions.” Id at *2.\\n\\n The district court found that the experts’ “testing was flawed, and Plaintiffs have\\n\\nfailed to establish other means by which their experts can meet the reliability standard.”\\n\\nId. The district court noted, for example, that the only peer-reviewed publication relied on\\n\\nby the experts was a 2015 article by Dr. Hubing; however, the theory relied on in that\\n\\narticle had been discredited by two federal agencies, the National Highway Traffic Safety\\n\\nAdministration (“NHTSA”) and the National Aeronautics and Space Administration\\n\\n(“NASA”). In analyzing the experts’ testing evidence, the court noted the continuing\\n\\nfailure of proof establishing any causal link:\\n\\n Although Plaintiffs’ experts purport to test [Plaintiffs’ theory of defect],\\n they leave a gap between analytical possibility and actual proof of\\n occurrence. The experts attempt to excuse this gap by reporting that the\\n defect leaves no evidence of its effect. However, this position shifts the\\n burden to Ford to prove the negative. Furthermore, there is no “general\\n acceptance” within the automotive safety or engineering community that\\n underpins Plaintiffs’ theory. The causes of [UIA] are myriad. Some events\\n are attributable to driver error, while others are tied to different defects\\n from cruise control to mechanical issues. Even though many drivers’\\n complaints of [UIA] are credible and likely caused by some defects,\\n Plaintiffs’ theory here is still largely hypothetical . . . .\\n\\nId. at *3.\\n\\n The district court examined each of the three experts’ individual opinions to\\n\\ndetermine whether that opinion should be admitted into evidence. First, the court rejected\\n\\nthe opinion of Dr. Hubing 4 whose report was primarily based on the article noted above\\n\\n\\n 4\\n Dr. Hubing is an electrical engineer and a professor at Clemson University.\\n\\n 7\\n\\fand in which he examined five vehicles with ETC systems, including two Ford models, a\\n\\n2005 Mustang and a 2006 Explorer. After comparing accelerator pedal performance of\\n\\nthe five vehicles, Dr. Hubing concluded that “Ford’s Gen II ETC system fails to\\n\\nadequately mitigate accelerator pedal faults which can lead to” UIAs. J.A. 10873. In Dr.\\n\\nHubing’s opinion, this was “the most probable reason that Ford vehicles with this throttle\\n\\ncontrol system have high reported rates of” UIAs. J.A. 10873.\\n\\n The district court found Dr. Hubing’s testing unreliable for two reasons. First, his\\n\\ntesting required making separate accommodations for the Ford vehicles he tested because\\n\\nthe testing “was developed to test vehicles with ’two track’ pedal sensors,” but the Ford\\n\\nvehicles had “three track” pedal sensors. Johnson, 2018 WL 1512377, at *4. To\\n\\naccommodate this difference, Dr. Hubing arbitrarily assigned a set value to Ford’s third\\n\\npedal without knowing how this affected Ford’s computer source code or software\\n\\nprogram. In some cases, the set value he used for the third track intentionally caused the\\n\\nvehicles to accelerate if one of the other two sensors’ values matched this set value.\\n\\n Second, Dr. Hubing’s testing rested on questionable assumptions that lacked\\n\\nevidentiary foundations. The voltages he injected into the ETC system purportedly\\n\\nsimulated real-world circumstances and actual vehicle conditions. But the voltage values\\n\\nsimply reflected Dr. Hubing’s “assumptions of what would happen” if factors such as a\\n\\nworn sensor, loose connector, or tin whisker existed. Id. at *4 n.6. Furthermore, Dr.\\n\\nHubing’s testing revealed that UIAs occurred when two pedal sensors produced values of\\n\\na certain range, and those values were “close to the same . . . , as though each sensor was\\n\\nfaulting in the same way.” Id. at *4. But Dr. Hubing did not “offer any testing of sensors\\n\\n 8\\n\\fto verify the assumption that both sensors should be expected to fault and that they do so\\n\\nin the same way.” Id.\\n\\n The court found that the sources supporting Dr. Hubing’s sensor assumption were\\n\\ninsufficient to be reliable. Dr. Hubing’s assumption was based on two sources: “first, by\\n\\nreference to various documents, such as Ford’s CQIS database (complaints relating to\\n\\neither pedal faults and/or [UIA]) and Ford’s design and development phases for the Gen\\n\\nII ETC system; second, the inherent knowledge of the expert.” Id. The first source did\\n\\n“little” to support Dr. Hubing’s assumption because these documents were “brief,\\n\\nand very few reflect[ed] an inspection, testing, or analysis by a trained eye.” Id. As for\\n\\nDr. Hubing’s qualifications, those alone could not substitute for the lack of testing\\n\\nevidence.\\n\\n The district court found further problems with Dr. Hubing’s report, including that\\n\\n“degraded sensors are not the defect, nor are they the only precipitating cause of [UIA],\\n\\naccording to Plaintiffs’ claim. However, Dr. Hubing’s theory of defect rests significantly\\n\\non the system’s inability to properly recognize and mitigate faulty sensors.” Id. Dr.\\n\\nHubing also had never tested the Plaintiffs’ actual vehicles or attempted to produce\\n\\nvoltages that would cause a UIA instead of simply injecting these voltages. Finally, the\\n\\nNHTSA and NASA in 2011 had rejected his theory as lacking real-world evidence.\\n\\nBased on all these findings, the court excluded Dr. Hubing’s opinion.\\n\\n Next, the court considered the opinion of Dr. van Schoor who holds a Ph.D. in\\n\\naeronautics and astronautics. He opined that Ford’s accelerator pedal sensors are subject\\n\\nto wear or “gunk” buildup, either of which “can lead to failure and erratic vehicle\\n\\n 9\\n\\fbehavior.” J.A.10972. The district court found three problems with this theory: (1)\\n\\nPlaintiffs’ counsel “explicitly stated that Plaintiffs were not offering his opinion as to a\\n\\ndefect;” (2) Dr. van Schoor did not perform any inspections or surveys to support his\\n\\ntheory; and (3) he “did not attribute any of Plaintiffs’ [UIAs] to the problems he\\n\\nidentified in his report.” Johnson, 2018 WL 1512377, at *5. Thus, the court found his\\n\\ntheory irrelevant to the Plaintiffs’ theory of defect.\\n\\n Dr. van Schoor also offered an opinion on an alternative vehicle design with BOA,\\n\\nbut the court did not examine this in depth because the availability of an alternative\\n\\ndesign was not proof of the alleged defect.5 Based on these findings, the court excluded\\n\\nDr. van Schoor’s report.\\n\\n The third expert at issue was Dr. Koopman, 6 who opined that a design defect made\\n\\nFord’s Gen II ETC system vulnerable to allowing UIAs. In support, Dr. Koopman tested\\n\\ntwo Ford models, a 2005 Mustang and a 2006 Fusion, by injecting voltages into the\\n\\naccelerator wiring harness as a substitute for the three accelerator pedal sensors. Similar\\n\\nto Dr. Hubing’s testing, the injected voltages represented the voltages “likely produced\\n\\n 5\\n The district court’s holding is consistent with our precedent. See Sexton By and\\nThrough Sexton v. Bell Helmets, Inc., 926 F.2d 331, 338 (4th Cir. 1991) (holding that the\\nsimple availability of an alternative design at the time of trial “does not lead to the\\nconclusion that the design of the [product] was defective”); see also Edwards v. Bell\\nHelicopter Textron, Inc., 63 F. App’x 674, 680–81 (4th Cir. 2003) (per curiam)\\n(determining that the availability of an alternative design “was irrelevant to the proof” of\\nthe strict liability and negligent defective design claims because the existence of an\\nalternative design could not have contributed to the alleged injury and therefore did not\\nestablish that an alleged design defect in the product was a proximate cause of the alleged\\ninjuries).\\n 6\\n Dr. Koopman is a tenured Associate Professor in the Electrical and Computer\\nEngineering Department of Carnegie Mellon University.\\n\\n 10\\n\\fby sensors degraded in one or more ways, such as from wear and tear, loose wires, and\\n\\nwater intrusion.” Johnson, 2018 WL 1512377, at *5. Next, he evaluated “actual vehicle\\n\\nperformance” by repeating this testing on a dynamometer 7 that was designed to simulate\\n\\nan actual vehicle condition. Id. Based on the results of his testing, Dr. Koopman\\n\\nconcluded that a UIA occurs when two or more sensors produce voltages of a certain\\n\\nrange close to each other.\\n\\n The district court found Dr. Koopman’s approach unreliable for much the same\\n\\nreasons that it found Dr. Hubing’s opinion defective. The court noted that he did not test\\n\\nor prove his assumption that two or more degraded sensors have produced or would\\n\\nproduce the voltages he used for his testing. Furthermore, Dr. Koopman purposely chose\\n\\narbitrary voltage inputs that would instruct the system to accelerate. Thus, his “testing\\n\\nwas an artificial demonstration that essentially mimicked intentional acceleration.” Id. at\\n\\n*7, and was not a “realistic example of sensor faults” because it required multiple steps\\n\\n“in a sequence that ha[d] no ‘real-world’ support.” Id.\\n\\n Furthermore, the district court concluded “Dr. Koopman’s testimony, that\\n\\nPlaintiffs’ complaints are consistent with his design defect opinion, is inadequate to tie\\n\\nhis opinions to this case.” The court explained why this was so:\\n\\n First, [Dr. Koopman] relies on nothing more specific than the Consolidated\\n Complaint to understand Plaintiffs’ [UIAs]. Second, there are profound\\n inconsistencies between the general complaints and his opinions. Nearly\\n every Plaintiff described a failure of their brakes to counteract the [UIA],\\n\\n 7\\n Dynamometer is a “device for measuring mechanical force, or power, transmitted\\nby a rotating shaft.” Dynamometer, Encyc. Britannica (2018); see Maxwell Dynamometer\\nCo. v. United States, 386 F.2d 855, 859 (Ct. Cl. 1967).\\n\\n 11\\n\\f yet in Dr. Koopman’s own testing procedure, the brakes restrained the\\n acceleration. Further, some Plaintiffs reported that their gas pedals were\\n moving up and down without a foot-on-pedal, a circumstance not replicated\\n in any of the tests done by Plaintiffs’ experts. If these Plaintiffs were right,\\n this pedal problem likely would be mechanical, perhaps caused by the\\n return spring.\\n\\nId. at *8 (internal citation omitted). Because his testing was not “a reliable basis” for his\\n\\nopinions regarding the alleged defect, the district court excluded Dr. Koopman’s opinion.\\n\\nId.\\n\\n The district court also found problematic that none of the Plaintiffs’ experts had\\n\\ntested or inspected the Plaintiffs’ actual vehicles or attempted to connect their testing to\\n\\nany of those vehicles. Instead, the Plaintiffs asserted the alleged ETC defect and experts’\\n\\nopinions applied universally to all the thousands of vehicles in their purported class\\n\\ndespite Drs. Koopman’s and Hubing’s opinions that their testing results varied\\n\\nsignificantly between individual vehicles and that the pedal sensors differed among the\\n\\nclass vehicles.\\n\\n Once the expert opinions were excluded, the district court concluded that the\\n\\nPlaintiffs had “no evidence of their core allegation that there is a design defect in Ford’s\\n\\nGen II ETC system.” Id. Insomuch as the Plaintiffs’ theory of defect was without an\\n\\nevidentiary basis, they could not establish the existence of a defect and the necessary\\n\\nelement of causation. Accordingly, the district court granted summary judgment on all\\n\\nremaining claims to Ford.\\n\\n A group of the Plaintiffs now appeal, and this Court has jurisdiction under 28\\n\\nU.S.C. § 1291.\\n\\n\\n 12\\n\\f II.\\n\\n A.\\n\\n We review summary judgment decisions de novo, see Campbell v. Hewitt,\\n\\nColeman & Assocs., Inc., 21 F.3d 52, 53 (4th Cir. 1994), and Daubert decisions for abuse\\n\\nof discretion, see Nease v. Ford Motor Co., 848 F.3d 219, 228 (4th Cir. 2017). A district\\n\\ncourt abuses its discretion if it makes an error of law or clearly erroneous factual finding.\\n\\nSee id. at 228.\\n\\n The merits of the district court’s Daubert decision addressing the Plaintiffs’ proof\\n\\nof their defect theory is our initial focus because their entire case hinges on the allegedly\\n\\ndefective ETC system as the cause of UIAs. UIAs alone do not substantiate their theory\\n\\nbecause, as the Plaintiffs concede on appeal, many factors unrelated to an ETC system\\n\\ncould trigger UIAs. See, e.g., Opening Br. 31 (“[M]ultiple circumstances can initiate\\n\\nunintended acceleration signals.”). Thus, to establish the existence of the alleged defect\\n\\nand the requisite causal link between it and their UIAs, the Plaintiffs proffered the\\n\\nopinions of the three experts, Drs. Hubing, van Schoor, and Koopman. As the district\\n\\ncourt recognized, these experts’ opinions are “critical” to the Plaintiffs’ case because\\n\\ntheir theory of defect is “largely hypothetical” without them. Johnson, 2018 WL\\n\\n1512377, at *3. Accordingly, if the district court correctly excluded the expert opinions,\\n\\nthe Plaintiffs’ case fails because they would be “unable to prove the fundamental theory\\n\\nof their case.” Id. at *9.\\n\\n B.\\n\\n 13\\n\\f The district court excluded the expert opinions under the Supreme Court’s\\n\\nlandmark precedent in Daubert, which established that under the Federal Rules of\\n\\nEvidence “the admissibility of scientific evidence no longer was limited to knowledge or\\n\\nevidence ‘generally accepted’ as reliable in the relevant scientific community.” Nease,\\n\\n848 F.3d at 228 (citing Daubert, 509 U.S. at 588–89). Instead, Daubert held that courts\\n\\nmust evaluate proposed expert testimony according to Rule 702, which tasks a district\\n\\njudge with “ensuring that an expert’s testimony both rests on a reliable foundation and is\\n\\nrelevant to the task at hand.” 509 U.S. at 597. This rule requires trial judges to conduct “a\\n\\npreliminary assessment of whether the reasoning or methodology underlying the\\n\\ntestimony is scientifically valid and of whether that reasoning or methodology properly\\n\\ncan be applied to the facts in issue. . . . . Many factors will bear on the inquiry, and we do\\n\\nnot presume to set out a definitive checklist or test.” Id. at 592–93.\\n\\n Under Rule 702, an expert’s testimony is relevant if it has “a valid scientific\\n\\nconnection to the pertinent inquiry.” Id. at 592. To be reliable, the testimony “must be\\n\\nbased on scientific, technical, or other specialized knowledge and not on belief or\\n\\nspeculation, and inferences must be derived using scientific or other valid methods.”\\n\\nOglesby v. Gen. Motors Corp., 190 F.3d 244, 250 (4th Cir. 1999) (citing Daubert, 509\\n\\nU.S. at 590, 592–93).\\n\\n In determining whether expert testimony is “sufficiently reliable to be admissible,”\\n\\na district court generally considers several factors:\\n\\n First, “a key question to be answered in determining whether a theory or\\n technique is scientific knowledge that will assist the trier of fact will be\\n whether it can be (and has been) tested.” A second question . . . is “whether\\n\\n 14\\n\\f the theory or technique has been subjected to peer review and\\n publication.” Publication regarding the theory bears upon peer review; “the\\n fact of publication (or lack thereof) in a peer reviewed journal will be a\\n relevant, though not dispositive, consideration in assessing the scientific\\n validity of a particular technique or methodology on which an opinion is\\n premised.” Third, “in the case of a particular scientific technique, the court\\n ordinarily should consider the known or potential rate of error.” Fourth, . . .\\n “‘general acceptance’” is . . . relevant to the reliability inquiry.\\n “Widespread acceptance can be an important factor in ruling particular\\n evidence admissible, and a known technique which has been able to attract\\n only minimal support with the community may properly be viewed with\\n skepticism.”\\n\\nNease, 848 F.3d at 229 (quoting Daubert, 509 U.S. at 593–94) (internal citations and\\n\\nalterations omitted).\\n\\n This list, however, is “not exhaustive,” and “‘neither necessarily nor exclusively\\n\\napplies to all experts or in every case.’” Id. (quoting Kumho Tire Co. v. Carmichael, 526\\n\\nU.S. 137, 141 (1999)). “[A]t bottom, the court’s evaluation is always a flexible one, and\\n\\nthe court’s conclusions necessarily amount to an exercise of broad discretion guided by\\n\\nthe overarching criteria of relevance and reliability.” Oglesby, 190 F.3d at 250. Thus, the\\n\\ntrial court has “broad latitude” in determining whether “Daubert’s specific factors are, or\\n\\nare not, reasonable measures of reliability in a particular case.” Kumho Tire, 526 U.S. at\\n\\n153. Here, the district court properly considered appropriate factors and did not abuse its\\n\\ndiscretion in excluding the experts’ opinions based on their lack of relevance and\\n\\nreliability.\\n\\n C.\\n\\n The Plaintiffs fail to show that the district court made “a clearly erroneous factual\\n\\nfinding” or “error of law” by excluding their expert witnesses. See Nease, 848 F.3d at\\n\\n\\n 15\\n\\f228. They argue that the district court did not consider certain Daubert factors, such as\\n\\nthe known or potential rate of error, or considered Daubert factors, like peer review, in an\\n\\ninappropriate manner. This argument lacks merit, in part, because the Plaintiffs do not\\n\\nidentify a tangible error in the district court’s analysis. The district court was not under\\n\\nany obligation to consider a certain factor or weigh factors it did consider in a particular\\n\\nmanner. See id. at 229. As noted earlier, the trial court’s inquiry is a “flexible one,” and it\\n\\nexercises “broad discretion” in choosing which Daubert factors to apply and how to\\n\\nconsider them. Oglesby, 190 F.3d at 250; accord Nease, 848 F.3d at 229.\\n\\n The Plaintiffs further argue that the court made conclusory findings and wrongly\\n\\nassessed the expert opinions. We disagree. Contrary to the Plaintiffs’ assertion, our\\n\\nreview shows that the district court thoroughly reviewed the record, including the\\n\\nexperts’ reports and the depositions of these experts, to understand their testing, theories,\\n\\nand methodologies. The court then provided a well-reasoned analysis of the experts’\\n\\ntheories and testing based on its consideration of relevant Daubert factors such as general\\n\\nacceptance of a theory within a relevant field, peer review, and the scientific validity of\\n\\ntheir underlying methodologies.\\n\\n For example, the district court properly noted that Dr. Hubing’s testing method\\n\\nwas, at a minimum, suspect because it had been rejected by NASA and NHTSA. Further,\\n\\nas the court pointed out, Dr. Hubing never tested any vehicle in actual conditions so all\\n\\nhis projections were purely theoretical. His “testing,” at least in part, seemed artificially\\n\\ninduced to produce a desired result and did not reflect real-world results from any vehicle\\n\\nclaiming a UIA. In sum, Dr. Hubing’s opinion was partly ipse dixit.\\n\\n 16\\n\\f As for Dr. van Schoor, even without examining the merits of his testimony, the\\n\\nPlaintiffs effectively pled him out of the case. During the district court proceedings, the\\n\\nPlaintiffs stipulated “on the record that Dr. van Schoor will not offer defect opinions per\\n\\nse.” J.A. 11934. Even more to the point, Plaintiffs’ counsel admitted Dr. van Schoor\\n\\nfailed to meet the necessary threshold of evidentiary reliability: “candidly I will concede\\n\\nto the Court that he couches all of his conclusions in the form of a defect opinion.\\n\\nCandidly I’ll say to the Court that I don’t know that Dr. van Schoor in this case tested his\\n\\nopinions against the rigor that is required for Federal Rules of Evidence.” J.A. 11932.\\n\\n Regardless, we find no abuse of discretion in the district court’s merits analysis of\\n\\nDr. van Schoor’s testimony for the reasons it explained. We simply note two salient\\n\\npoints from that analysis: Dr. van Schoor “performed no inspections nor surveys to\\n\\nsupport his theory about contacting sensors” and “did not attribute any of Plaintiffs’\\n\\n[UIAs] to the problems he identified in his report.” Johnson, 2018 WL 1512377, at *5.\\n\\n Dr. Koopman’s testimony fares no better. As with the other experts, there is a\\n\\nconsiderable gap between Dr. Koopman’s theory and any evidentiary proof of causation\\n\\nrelated to an ETC defect and a UIA. The district court aptly recited the evidentiary failure\\n\\non Dr. Koopman’s part:\\n\\n Dr. Koopman admits that in many of his tests, he injected faults with\\n voltages designed to produce pedal angles consistent with acceleration.\\n . . . Yet, nowhere does he validate his hypothesis that degraded\\n sensors, presumably to be expected, will actually cause or, in fact, have\\n produced faulty voltages in the way he arranged for his testing. . . . The\\n testing was an artificial demonstration that essentially mimicked intentional\\n acceleration. Dr. Koopman offers no testing of Plaintiffs’ vehicles, or the\\n exemplars he chose, to demonstrate how degraded sensors or the other\\n\\n\\n 17\\n\\f circumstances can produce similar voltages that result in unintended open\\n throttle.\\n\\nId. at *7 (internal citation omitted).\\n\\n Further, the district court correctly observed that none of the experts tested any of\\n\\nthe Plaintiffs’ vehicles or any of the thousands of Ford vehicles in their purported class\\n\\nwhich they allege had a UIA. Of the multitude of vehicles the Plaintiffs claim to be\\n\\ndefective, the record does not reflect they attempted to test even one vehicle purported to\\n\\nhave had a UIA, much less conduct such a test under real-world conditions. Most\\n\\nimportantly, none of the proffered expert opinions purport to tie their testing to any\\n\\nalleged UIA so as to show the fundamental element of causation. To the contrary, the\\n\\nPlaintiffs’ experts disclaimed any finding or opinion as to the causation of any specific\\n\\nUIA. J.A. 1754 ([Counsel’s question to Dr. Hubing:] “But you can’t say that your\\n\\nvulnerabilities that you identify actually cause the event in the plaintiffs’ vehicles,\\n\\ncorrect? . . . [Answer:] In any one of those vehicles, no.”); J.A. 10196–97 ([Counsel’s\\n\\nquestion to Dr. van Schoor:] “Have you identified any alleged unwanted acceleration\\n\\nevent occurring in a Ford vehicle that you have determined resulted from any of the\\n\\nalleged defects or vulnerabilities that you have identified in your report? [Answer:] I have\\n\\nnot.”); see also J.A. 8922–23 ([Counsel’s question to Dr. Koopman:]“And then you don’t\\n\\ngo out to the vehicle to see if there are any other possible causes or explanation for their\\n\\nclaim; correct? . . . [Answer:] I have not physically examined the vehicles.”); J.A. 8925–\\n\\n26 ([Dr. Koopman:] “What I am saying is that I see explanations consistent with software\\n\\n\\n\\n\\n 18\\n\\fand hardware defects, and I see that that’s consistent with my report. That’s all I have\\n\\nbeen saying.”). 8\\n\\n The court’s well-articulated analysis clearly distinguishes this case from Nease in\\n\\nwhich the district court failed to act as a gatekeeper by not assessing the expert’s\\n\\nreliability but leaving that question to the jury. See 848 F.3d at 231. Instead, the court\\n\\nhere faithfully performed its duty as a “gatekeeper” in the manner we approved in In re\\n\\nLipitor (Atorvastatin Calcium) Marketing, Sales Practices and Products Liability\\n\\nLitigation (No II) MDL 2502, 892 F.3d 624, 631 (4th Cir. 2018). There, we upheld the\\n\\ndistrict court’s extensive analysis of the experts’ theories and testing, which formed the\\n\\nbasis of the court’s exclusion of several expert opinions, because that court, like the\\n\\ndistrict court here, properly “identified and articulated clear . . . concerns it had about the\\n\\nmanner in which [the expert] reached his conclusions.” Id. at 638. In approving the\\n\\ndistrict court’s analysis in In re Lipitor, we once more emphasized that “‘[m]any factors\\n\\nwill bear on the inquiry,’ and there is no ‘definitive checklist or test.’” Id. at 637 (quoting\\n\\nDaubert, 509 U.S. at 593).\\n\\n Having failed on their primary arguments, the Plaintiffs argue that the district\\n\\ncourt mischaracterizes the experts’ testimony during depositions, but this argument\\n\\n 8\\n The district court found, as do we, the anomaly of the Plaintiffs’ theory at trial\\nthat the ETC defect was universal to all the class vehicles, but that their experts own\\nlaboratory testing showed significant differences between vehicles. As the district court\\nnoted, “Dr. Hubing’s testing revealed significant differences between the two Ford\\nvehicles, which he asserts had identical ETC systems,” and yet, the Plaintiffs are\\n“inconsistent” because they “maintain the Gen II ETC system used by Ford is exactly the\\nsame in all vehicles, but then they excuse results when it is not.” Johnson, 2018 WL\\n1512377, at *8.\\n\\n 19\\n\\fsimply channels the Plaintiffs’ disagreement with the district court’s findings. The\\n\\nPlaintiffs essentially assert the district court erred by making findings that were favorable\\n\\nto Ford or reaching conclusions that contradicted their portrayal of the expert opinions.\\n\\nFor instance, the Plaintiffs challenge the district court’s finding that when Dr. Hubing\\n\\nwas asked whether “he ever saw ‘dual faults occur in the same resistive ranges’ in the\\n\\n‘real world,’ [he] ultimately answered no.” Johnson, 2018 WL 1512377, at *4. They\\n\\nassert that this finding is erroneous because Dr. Hubing answered “no” to an entirely\\n\\ndifferent question. Our review of the record reveals that the district court’s finding is\\n\\ncorrect. When Ford’s counsel asked Dr. Hubing whether he had ever “physically see[n] . .\\n\\n. dual faults occur in the same resistive range,” he answered, “. . . how would we do\\n\\nthat?” because “physical evidence of two simultaneous faults occurring [in the real\\n\\nworld] . . . would be basically impossible to find.” J.A. 09335–36. Similarly, the\\n\\nPlaintiffs’ other arguments related to the district court’s alleged mischaracterization\\n\\nreveal no more than their disagreement with the district court’s findings or contrary\\n\\ninterpretation, and do not show that the court committed any error.\\n\\n Once the opinions of the three experts were excluded, the district court necessarily\\n\\nconcluded that the Plaintiffs had “no evidence of their core allegation that there is a\\n\\ndesign defect in Ford’s Gen II ETC system.” Johnson, 2018 WL 1512377, at *8. As the\\n\\ncourt held, other evidence that the Plaintiffs recite, such as a software expert’s opinion\\n\\nand Ford’s internal documents, does not prove their defect theory.\\n\\n The Plaintiffs point to unverified reports of UIAs from Ford vehicle drivers, but,\\n\\nas noted above, UIA alone does not prove the existence of a defect. Similarly, the\\n\\n 20\\n\\favailability of an alternative vehicle design with BOA does not substantiate the Plaintiffs’\\n\\ntheory of defect because the alternative design’s mere availability does not prove that the\\n\\nexisting design is defective or could lead to a UIA. See Sexton, 926 F.2d at 337–38\\n\\n(remanding for new trial where district court improperly allowed expert testimony of a\\n\\npossible alternative design to substitute for evidence that was necessary to satisfy\\n\\nplaintiff’s burden of showing a design defect); Edwards, 63 F. App’x at 680–81\\n\\n(discussing the difference between the two types of evidence). The Plaintiffs further\\n\\ndirect our attention to Ford’s internal documents without discussing what these\\n\\ndocuments specifically contain or how they prove the missing element of causation.\\n\\nInstead, they generally argue that “the factual record in this case is rife with internal\\n\\ndocuments demonstrating Ford’s knowledge of the defect.” Reply Br. 14. Like the\\n\\nPlaintiffs’ other evidence, this generalized argument neither proves nor disproves their\\n\\ntheory of defect. Lastly, the Plaintiffs focus on the opinion of the software expert, Steve\\n\\nLoudon, but the district court could not have considered this opinion because the\\n\\nPlaintiffs admit that it was not available to the court and is not in the record. Thus, we\\n\\nagree with the district court that after the expert opinions were excluded, the Plaintiffs\\n\\nhad no proof of a defect in Ford’s ETC system.\\n\\n\\n\\n\\n 21\\n\\f Because the Plaintiffs could not prove their theory of defect and thus fail to meet\\n\\nthe essential element of causation, we affirm the district court’s grant of summary\\n\\njudgment on all claims to Ford. 9\\n\\n\\n\\n III.\\n\\n For the foregoing reasons, the district court’s Daubert and summary judgment\\n\\ndecisions are\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 9\\n We find it unnecessary to assess the merits of the Plaintiffs’ claims dismissed\\nunder Federal Rule of Civil Procedure 12(b)(6) because those claims are based on the\\nsame unsubstantiated theory and suffer from the same lack of proof, although the district\\ncourt dismissed them for additional reasons not discussed here. Thus, even if those claims\\nhad survived the Rule 12(b)(6) challenge, they would not have survived the district\\ncourt’s summary judgment rulings because all contain the same failure of proof.\\n Similarly, we find without merit the Plaintiffs’ argument that the district court\\nerred by granting summary judgment to Ford on their various state consumer protection\\nclaims because those claims also fail for the reasons stated herein. The Plaintiffs argue\\nthe court did not recognize that those claims simply require “the breach of a duty to warn\\nconsumers of a known risk or danger or violation of a prohibition against misleading the\\nconsumer.” Opening Br. 37. The Plaintiffs cannot establish the existence of a defect, let\\nalone its risk or danger. Ford does not have a duty to warn consumers of an unproven risk\\nor danger associated with a hypothetical and unproven defect.\\n\\n 22\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1068,"cells":{"id":{"kind":"number","value":4603788,"string":"4,603,788"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"Zoe Spencer v. Virginia State University"},"decision_date":{"kind":"string","value":"2019-03-26"},"docket_number":{"kind":"string","value":"17-2453"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before WILKINSON, FLOYD, and RICHARDSON, Circuit Judges.\", \"parties\": \"\", \"opinions\": [{\"author\": \"RICHARDSON, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 17-2453\\n\\n\\nZOE SPENCER,\\n\\n Plaintiff - Appellant,\\n\\n v.\\n\\nVIRGINIA STATE UNIVERSITY; KEITH T. MILLER,\\n\\n Defendants - Appellees.\\n\\n\\nAppeal from the United States District Court for the Eastern District of Virginia, at\\nRichmond. Henry E. Hudson, Senior District Judge. (3:16-cv-00989-HEH-RCY)\\n\\n\\nArgued: October 31, 2018 Decided: March 18, 2019\\n Amended: March 26, 2019\\n\\n\\nBefore WILKINSON, FLOYD, and RICHARDSON, Circuit Judges.\\n\\n\\nAffirmed by published opinion. Judge Richardson wrote the opinion, in which Judge\\nWilkinson and Judge Floyd concurred.\\n\\n\\nARGUED: Noah Barnett Peters, NOAH PETERS LAW, Washington, D.C., for\\nAppellant. Jimmy F. Robinson, Jr., OGLETREE DEAKINS NASH SMOAK &\\nSTEWART, PC, Richmond, Virginia, for Appellees. ON BRIEF: Christopher C.\\nMurray, Indianapolis, Indiana, Elizabeth Ebanks, Kyle R. Elliott, OGLETREE\\nDEAKINS NASH SMOAK & STEWART, PC, Richmond, Virginia, for Appellees.\\n\\fRICHARDSON, Circuit Judge:\\n\\n Dr. Zoe Spencer, a sociology professor at Virginia State University, sued the\\n\\nUniversity under the Equal Pay Act and Title VII for paying her less than two male\\n\\nprofessors, allegedly because she is a woman.\\n\\n Spencer earned about $70,000 per year—a median salary when compared to the\\n\\nmen who were also full professors in the Department of Sociology, Social Work, and\\n\\nCriminal Justice. But Spencer’s lawsuit proposes comparing her pay to that of two\\n\\nformer University administrators, Drs. Michael Shackleford and Cortez Dial, who each\\n\\nearned over $100,000 per year as professors in other departments. While Spencer asserts\\n\\nthat the difference in pay was due to her sex, the University provides a different\\n\\nexplanation: Shackleford’s and Dial’s jobs differed from Spencer’s and, as former\\n\\nadministrators, their pay was set as a prorated portion of their previous salaries.\\n\\n After discovery, the district court granted summary judgment for the University\\n\\n(and its former president, Dr. Keith Miller). We affirm. Though Spencer establishes a\\n\\npay disparity, she fails to present evidence that creates a genuine issue of material fact\\n\\nthat Shackleford and Dial are appropriate comparators. In any event, unrebutted evidence\\n\\nshows that the University based Shackleford’s and Dial’s higher pay on their prior\\n\\nservice as University administrators, not their sex. 1\\n\\n\\n 1\\n We review the district court’s grant of summary judgment de novo. In re Lipitor\\n(Atorvastatin Calcium) Mktg., Sales Practices & Prods. Liab. Litig. (No II), 892 F.3d\\n624, 645 (4th Cir. 2018). After considering the evidence and all fair inferences in the\\nlight most favorable to the nonmovant, summary judgment is appropriate “if the movant\\nshows that there is no genuine dispute as to any material fact.” Fed. R. Civ. P. 56(a).\\n(Continued)\\n 2\\n\\f I. Equal Pay Act\\n\\n Spencer first claims that the disparity between her salary and her chosen\\n\\ncomparators’ violates the Equal Pay Act. The statute forbids the University (like other\\n\\nemployers) from:\\n\\n Discriminat[ing] . . . between employees on the basis of sex by paying\\n wages to employees . . . at a rate less than the rate at which [the employer]\\n pays wages to employees of the opposite sex . . . for equal work on jobs the\\n performance of which requires equal skill, effort, and responsibility, and\\n which are performed under similar working conditions, except where such\\n payment is made pursuant to (i) a seniority system; (ii) a merit system; (iii)\\n a system which measures earnings by quantity or quality of production; or\\n (iv) a differential based on any other factor other than sex . . . .\\n\\n29 U.S.C. § 206(d)(1). To prove a violation of the Act, Spencer must make an initial\\n\\n(i.e., prima facie) showing of three elements: (1) the University paid higher wages to an\\n\\nemployee of the opposite sex who (2) performed equal work on jobs requiring equal skill,\\n\\neffort, and responsibility (3) under similar working conditions. EEOC v. Maryland Ins.\\n\\nAdmin., 879 F.3d 114, 120 (4th Cir. 2018) (citing Corning Glass Works v. Brennan, 417\\n\\nU.S. 188, 195 (1974)).\\n\\n This initial showing permits an inference that a pay disparity was based on sex\\n\\ndiscrimination. Maryland Ins. Admin., 879 F.3d at 120. The inference of discrimination\\n\\nstands even without the support of any evidence of discriminatory intent. Id. Only once\\n\\n\\n\\n\\n“To survive summary judgment, ‘there must be evidence on which the jury could\\nreasonably find for the nonmovant.’” Lee v. Town of Seaboard, 863 F.3d 323, 327 (4th\\nCir. 2017) (quoting Anderson v. Liberty Lobby, Inc., 477 U.S. 242, 252 (1986)).\\n\\n\\n 3\\n\\fthis inference exists does the burden shift to the employer to show that the pay\\n\\ndifferential was based on a factor other than sex. Id.\\n\\n Spencer’s choice of Shackleford and Dial as comparators establishes the first\\n\\nelement of her initial showing—the existence of a wage differential. By choosing two of\\n\\nthe highest-paid professors at the University, Spencer ensured that her wages were much\\n\\nlower. Yet that same decision to pick Shackleford and Dial precludes her from\\n\\nestablishing, as the second element requires, that she and they performed “equal” work\\n\\nrequiring “equal skill, effort, and responsibility.”\\n\\n Equality under the Act is a demanding threshold requirement. It requires a\\n\\ncomparator to have performed work “virtually identical” (or the apparent synonym,\\n\\n“substantially equal”) to the plaintiff’s in skill, effort, and responsibility. Wheatley v.\\n\\nWicomico Cty., 390 F.3d 328, 332–33 (4th Cir. 2004). Similarity of work is not enough;\\n\\nthe Act explicitly distinguishes between the work itself (which must be “equal”) and the\\n\\nconditions of work (which need only be “similar”). 29 U.S.C. § 206(d)(1). The Act does\\n\\nnot provide courts with a way of evaluating whether distinct work might have\\n\\n“comparable” value to the work the plaintiff performed. See Wheatley, 390 F.3d at 333;\\n\\nsee also Sims-Fingers v. City of Indianapolis, 493 F.3d 768, 771 (7th Cir. 2007) (Posner,\\n\\nJ.) (explaining that, when trying to identify “comparable” pay for unequal work, there are\\n\\n“no good answers that are within the competence of judges to give”). Instead, the Act’s\\n\\ninference of discrimination may arise only when the comparator’s work is equal to the\\n\\nplaintiff’s.\\n\\n\\n\\n 4\\n\\f In alleging this necessary equality, a plaintiff may not rely on broad\\n\\ngeneralizations at a high level of abstraction. Wheatley, 390 F.3d at 332. But Spencer\\n\\nattempts just such an impermissibly general comparison. In Spencer’s view, all\\n\\nUniversity professors perform equal work because they all perform the same essential\\n\\ntasks: preparing syllabi and lessons, instructing students, tracking student progress,\\n\\nmanaging the classroom, providing feedback, and inputting grades. See Appellant’s Brief\\n\\nat 9. The performance of these tasks, Spencer posits, requires the same skills: studying,\\n\\npreparing, presenting, discussing, and so forth. See id. at 9–10. But these tasks and skills\\n\\nare shared by middle-school teachers and law-school professors, pre-algebra teachers and\\n\\nbiomedical-engineering professors.\\n\\n This attempted comparison ultimately relies on the common title of “professor”\\n\\nplus some generalized responsibilities (e.g., teaching students). Yet we have rejected an\\n\\nanalogous claim that jobs with the same title and only vaguely corresponding\\n\\nresponsibilities can be considered equal. In Wheatley we concluded that the plaintiffs,\\n\\nsupervisors in a county’s emergency-services department, failed to meet their burden to\\n\\nshow that supervisors in different departments performed equal work because they could\\n\\nnot demonstrate that the different jobs were equal in skill and responsibility. 390 F.3d at\\n\\n334; see also Sims-Fingers, 493 F.3d at 771. Spencer’s case suffers from a near-identical\\n\\nflaw.\\n\\n Spencer’s bird’s-eye view is particularly unpersuasive given the inherent features\\n\\nof academia. Professors are not interchangeable like widgets. Various considerations\\n\\ninfluence the hiring, promotion, and compensation of different professorial jobs. Cf.\\n\\n 5\\n\\fZahorik v. Cornell Univ., 729 F.2d 85, 93 (2d Cir. 1984) (discussing the tenure process).\\n\\nAs a result, faculty salary decisions require a complex balancing of factors. Among other\\n\\nthings, those decisions account for the differences in skill and responsibility attendant to\\n\\ndifferent jobs. For instance, an engineering professorship requires different skills, effort,\\n\\nand responsibility than professorships in other fields, such as sociology. Evidence\\n\\noffered by Spencer proves this very point: The University systematically pays\\n\\nengineering professors more than humanities professors. J.A. at 136. This reflects\\n\\ndifferences in skill along with market forces that compensate engineers more highly.\\n\\nThis market reality confirms that Spencer’s broad generalizations about tasks and skills,\\n\\nwhich apply to virtually all teachers, fail to satisfy her burden to show equal work.\\n\\n In contrast to Spencer’s generalized tasks and skills, a litany of concrete\\n\\ndifferences underscore that Spencer does not perform work equal to that of Shackleford\\n\\nand Dial. First, Shackleford and Dial taught in different departments than Spencer did.\\n\\nWhile comparisons might be drawn between some departments, any such comparison\\n\\nrequires the plaintiff to articulate with specificity why the work performed and skills\\n\\nneeded by a professor in one department are virtually identical—and not just generally\\n\\nrelated or of comparable worth—to those in another. As our precedents recognize, the\\n\\ndifferences between academic departments generally involve differences in skill and\\n\\nresponsibility. See Strag v. Bd. of Trustees, Craven Cmty. Coll., 55 F.3d 943, 950 (4th\\n\\nCir. 1995) (finding that the Biology and Mathematics departments required instructors to\\n\\nhave different skills and responsibilities); Soble v. Univ. of Maryland, 778 F.2d 164, 167\\n\\n(4th Cir. 1985) (finding that the specialized nature of certain university departments\\n\\n 6\\n\\fcalled for distinct skills); cf. Wheatley, 390 F.3d at 332–33 (recognizing job-related\\n\\ndifferences for directors of different county government departments).\\n\\n There are still more differences. Along with serving in different departments, the\\n\\nthree professors taught at different class levels at the University. Spencer taught mainly\\n\\nundergraduate courses, while Shackleford and Dial taught more graduate courses. And\\n\\nShackleford also supervised doctoral dissertations. Contrary to Spencer’s assertion, the\\n\\nfact that the University credited hours spent supervising dissertations in a similar manner\\n\\nto hours spent teaching regular courses does nothing to establish the equivalency of\\n\\nsupervising dissertations and teaching undergraduates. Nor did the professors work equal\\n\\nhours, as the record shows that Shackleford and Dial worked more than Spencer did week\\n\\nto week. 2\\n\\n None of this is to say that the Equal Pay Act cannot apply in the higher-education\\n\\ncontext. But in that context—one where the work is an exercise in intellectual creativity\\n\\nthat can be judged only according to intricate, field-specific, and often subjective\\n\\ncriteria—Spencer must provide the court with more than broad generalities to meet her\\n\\nburden. She must present evidence on which a jury could rely to decide that she,\\n\\nShackleford, and Dial had equal jobs, not just that they all performed vaguely related\\n\\n\\n 2\\n Spencer paradoxically argues that other differences between her work and that of\\nher chosen comparators render her work equal. For example, Spencer asserts that she\\nconducted research and published while Shackleford and Dial did not. This evidence\\ncannot save her claim given the differences already discussed. Piling on differences—\\neven those suggesting that Spencer did better or more work—does nothing to prove\\nequality of work.\\n\\n\\n 7\\n\\ftasks using nominally comparable skills. That is, there must be evidence showing the\\n\\njobs were equal in the strict sense of involving “virtually identical” work, skill, effort,\\n\\nand responsibility, not in the loose sense of having some comparative value. Wheatley,\\n\\n390 F.3d at 333.\\n\\n Despite all of these issues, Spencer claims her expert, Joseph Rosenberg, found\\n\\n“that Shackleford and Dial were significantly overpaid in comparison to Spencer.”\\n\\nAppellant’s Brief at 44 (emphasis added). Not only is this irrelevant to establishing equal\\n\\nwork, this claim is a bit misleading: Rosenberg asserted that Shackleford and Dial were\\n\\noverpaid relative to all other professors, both men and women. 3\\n\\n In addition to looking at her chosen comparators, Spencer’s expert tried to identify\\n\\na general disparity between the pay of men and women at the University. But his efforts\\n\\n 3\\n Spencer’s brief asserts that Rosenberg:\\n used four independent variables to account for the skill, effort, and\\n responsibility required of professors at [the University], taking into account\\n experience, departmental affiliation, faculty rank, and whether the professor\\n was a Chair or Dean. Rosenberg found, at a 97.5% confidence interval,\\n that Shackleford and Dial were significantly overpaid in comparison to\\n Spencer even when accounting for the different departments in which they\\n taught.\\n\\nAppellant’s Brief at 44 (citations and emphasis omitted). Contrary to Spencer’s\\ncharacterization, Rosenberg’s report does not appear to take departmental affiliation into\\naccount, instead only accounting for the broader category of “school,” each of which\\nencompasses several departments. And there is another flaw, though immaterial given\\nthe report’s other shortcomings: Rosenberg’s expert report does not account for\\nSpencer’s comparators’ prior work in the administration, even though everyone appears\\nto agree that their prior administrative experience determined their salaries. Cf. Smith v.\\nVirginia Commonwealth Univ., 84 F.3d 672, 675 (4th Cir. 1996) (noting that\\nadministrators are generally paid higher salaries than teachers and that these higher\\nsalaries persist when administrators move back to teaching).\\n\\n 8\\n\\frevealed no statistically significant disparity within each “school.” If anything, this\\n\\nevidence undermines Spencer’s claimed inference of discrimination. See Strag, 55 F.3d\\n\\nat 950 (suggesting that “isolated incidents or random comparisons demonstrating\\n\\ndisparities in treatment may be insufficient to draw a prima facie inference of\\n\\ndiscrimination without additional evidence that the alleged phenomenon of inequality\\n\\nalso exists with respect to the entire relevant group of employees” (quoting Houck v.\\n\\nVirginia Polytechnic Ins., 10 F.3d 204, 206–07 (4th Cir. 1993)).\\n\\n Despite her expert’s efforts, Spencer’s generalized claims cannot establish that she\\n\\nengaged in equal work, which categorically dooms her attempt to establish wage\\n\\ndiscrimination under the Equal Pay Act. Cf. Wheatley, 390 F.3d at 334 (a plaintiff may\\n\\nnot “indiscriminately aim at all department supervisors collectively, and then expect to\\n\\nmeet the EPA standard” for equal work).\\n\\n But even if Spencer could meet her initial burden, her claim would still fail\\n\\nbecause the University established that the salary difference was based on a “factor other\\n\\nthan sex.” 29 U.S.C. § 206(d)(1)(iv). As the defendant, the University bore the burden\\n\\nof establishing this affirmative defense. Maryland Ins. Admin., 879 F.3d at 120.\\n\\nGranting summary judgment on this ground required the district court to find that the\\n\\nproffered reason did in fact explain the wage disparity, not merely that it could. Id. at\\n\\n121.\\n\\n Here, there is no dispute that the wage difference at issue resulted from the\\n\\nUniversity setting Shackleford’s and Dial’s pay at 75% of their previous salaries as\\n\\nadministrators. In practice, the University generally paid former administrators who\\n\\n 9\\n\\fbecame professors “9/12ths” of their administrator salary. This practice appears to rest\\n\\non the theory that professors work nine months out of the year, while administrators work\\n\\nyear-round. Indeed, Spencer admits that her comparators’ pay during their short stints as\\n\\nUniversity professors was set according to the 9/12ths practice. Appellant’s Reply Brief\\n\\nat 16 (“Shackleford and Dial’s salaries were set entirely on their prior salaries as\\n\\nadministrators.”).\\n\\n In response to the University’s explanation, Spencer claims that the 9/12ths\\n\\npractice should not have been used to calculate Shackleford’s and Dial’s salaries.\\n\\nAccording to her, the University’s historical practice only applied to administrators who\\n\\nwere previously tenured faculty. But even if the University erroneously applied its\\n\\n9/12ths practice to overpay Shackleford and Dial, such an imprudent decision would still\\n\\nserve as a non-sex-based explanation for the pay disparity. See Anderson v.\\n\\nWestinghouse Savannah River Co., 406 F.3d 248, 272 (4th Cir. 2005) (“We do not sit as\\n\\na ‘super-personnel department weighing the prudence of employment decisions’ made by\\n\\nthe defendants.” (quoting DeJarnette v. Corning, Inc., 133 F.3d 293, 299 (4th Cir.\\n\\n1998)); Smith v. Univ. of North Carolina, 632 F.2d 316, 346 (4th Cir. 1980) (“[The] law\\n\\ndoes not require, in the first instance, that employment be rational, wise, or well-\\n\\nconsidered—only that it be nondiscriminatory.” (quoting Powell v. Syracuse Univ., 580\\n\\nF.2d 1150, 1156–57 (2d Cir. 1978)).\\n\\n The Equal Pay Act is a powerful tool, permitting an employee to prevail on a wage\\n\\ndiscrimination claim with no evidence of intentional discrimination. But this tool must\\n\\nbe tempered by adherence to its provisions. Doing so requires that the work performed\\n\\n 10\\n\\fby the plaintiff and her comparators be equal and that the wage disparity not be based on\\n\\na factor other than sex. Spencer’s claim fails on both requirements.\\n\\n II. Title VII\\n\\n Having rejected Spencer’s Equal Pay Act claim, we must separately consider her\\n\\nclaim of Title VII sex-based wage discrimination. Under Title VII of the Civil Rights\\n\\nAct of 1964, an employer cannot “discriminate against any individual with respect to\\n\\n[her] compensation . . . because of such individual’s . . . sex.” 42 U.S.C. § 2000e-2(a)(1).\\n\\nTitle VII, in contrast to the Equal Pay Act, requires establishing intentional\\n\\ndiscrimination. A Title VII plaintiff may make this showing of intentional discrimination\\n\\nusing direct or circumstantial evidence. Alternatively, the plaintiff may use the burden-\\n\\nshifting framework of McDonnell Douglas Corp. v. Green, 411 U.S. 792 (1973), “to\\n\\ndevelop an inferential case” of discriminatory intent. Chalmers v. Tulon Co. of\\n\\nRichmond, 101 F.3d 1012, 1017 (4th Cir. 1996).\\n\\n A prima facie pay-disparity case under McDonnell Douglas requires a plaintiff to\\n\\nestablish (1) she is a member of a protected class, (2) she was performing her job\\n\\nsatisfactorily, (3) an adverse employment action occurred, and (4) the circumstances\\n\\nsuggest an unlawfully discriminatory motive. See McDonnell Douglas, 411 U.S. at 802;\\n\\nTexas Dep’t of Cmty. Affairs v. Burdine, 450 U.S. 248, 253 (1981). Where, as here, the\\n\\nprima facie case of wage discrimination is based on comparators, the plaintiff must show\\n\\nthat she is paid less than men in similar jobs. See Brinkley-Obu v. Hughes Training, Inc.,\\n\\n36 F.3d 336, 343 (4th Cir. 1994).\\n\\n\\n\\n 11\\n\\f Title VII requires the compared jobs to be only “similar” rather than “equal,” as\\n\\nrequired under the Equal Pay Act. See id. While there is no bright-line rule for what\\n\\nmakes two jobs “similar” under Title VII, courts consider “whether the employees (i)\\n\\nheld the same job description, (ii) were subject to the same standards, (iii) were\\n\\nsubordinate to the same supervisor, and (iv) had comparable experience, education, and\\n\\nother qualifications—provided the employer considered these latter factors in making the\\n\\npersonnel decision.” Bio v. Fed. Express Corp., 424 F.3d 593, 597 (7th Cir. 2005)\\n\\n(internal quotation marks omitted); see also Herster v. Bd. of Supervisors of Louisiana\\n\\nState Univ., 887 F.3d 177, 185 (5th Cir. 2018) (stating that a “variety of factors are\\n\\nconsidered when determining whether a comparator is similarly situated, including job\\n\\nresponsibility, experience, and qualifications.”). While Title VII’s “similarity”\\n\\nrequirement demands less of plaintiffs than the Equal Pay Act’s “equality” requirement,\\n\\nit is not toothless: the plaintiff must provide evidence that the proposed comparators are\\n\\nnot just similar in some respects, but “similarly-situated in all respects.” Mitchell v.\\n\\nToledo Hosp., 964 F.2d 577, 583 (6th Cir. 1992). For the same reasons we discussed\\n\\nabove, Spencer’s broad generalizations cannot even show sufficient similarity to meet her\\n\\nburden under Title VII. 4\\n\\n\\n\\n\\n 4\\n Just as in the Equal Pay Act context, Spencer’s expert does not help her to\\nestablish a prima facie case here. While a plaintiff may use statistics to suggest a\\ndiscriminatory motive, Spencer’s expert found no statistical evidence that the University\\npaid women less than men.\\n\\n\\n 12\\n\\f Even if we concluded that Spencer had established a prima facie case of Title VII\\n\\nwage discrimination, her case still could not withstand summary judgment. Once a\\n\\nplaintiff establishes a prima facie case, the burden of production shifts to the employer to\\n\\nproffer a legitimate, nondiscriminatory explanation for the wage disparity. Guessous v.\\n\\nFairview Prop. Investments, LLC, 828 F.3d 208, 216–17 (4th Cir. 2016); Maryland Ins.\\n\\nAdmin., 879 F.3d at 120 n.7. Here, the University satisfies this requirement through its\\n\\npractice of paying administrators 9/12ths of their previous salary. Just as this practice\\n\\nsatisfies the Equal Pay Act’s “factor other than sex” affirmative defense, it qualifies as a\\n\\nlegitimate, nondiscriminatory explanation under Title VII. Cf. Cty. of Washington v.\\n\\nGunther, 452 U.S. 161, 169 (1981) (recognizing that the Bennett Amendment to Title VII\\n\\nincorporates the four affirmative defenses from the Equal Pay Act).\\n\\n Having proffered a nondiscriminatory explanation, the University shifts the burden\\n\\nback to Spencer to prove that the explanation is merely pretextual for invidious\\n\\ndiscrimination. Guessous, 828 F.3d at 216. Spencer cannot supply any evidence of this.\\n\\nSince the touchstone of discrimination is treating two groups differently based on\\n\\ncharacteristics only one possesses, it is vital for Spencer to provide evidence that the\\n\\nUniversity has used the 9/12ths policy to pay men more than women. Instead, Spencer\\n\\nmerely argues that the University misapplied the 9/12ths policy to Shackleford and Dial.\\n\\nBut again, even if the University “erroneously or even purposely misapplied the . . .\\n\\npolicy, it is not proof of unlawful discrimination.” Dugan v. Albemarle Cty. Sch. Bd.,\\n\\n293 F.3d 716, 722 (4th Cir. 2002).\\n\\n\\n\\n 13\\n\\f As a final note, Spencer also alleges that the University, and its former provost,\\n\\nengaged in unlawful retaliation because of her complaints about pay disparities. As the\\n\\ndistrict court noted, the facts supporting most of these allegations are exceedingly weak,\\n\\nand the allegations themselves are mostly conclusory. See Spencer v. Virginia State\\n\\nUniv., No. 3:16-cv-989, 2018 WL 627558, at *14–17 (E.D. Va. Jan. 30, 2018). Even if\\n\\nSpencer’s characterization of the behavior is accurate, Spencer offers insufficient\\n\\nevidence that each action was both material and undertaken because of her complaints\\n\\nabout salary equity. See Burlington N. & Santa Fe Ry. Co. v. White, 548 U.S. 53, 68\\n\\n(2006) (holding that “a plaintiff must show that a reasonable employee would have found\\n\\nthe challenged action materially adverse . . . [meaning] it might have ‘dissuaded a\\n\\nreasonable worker from making or supporting a charge of discrimination’”). That is not\\n\\nto say no one harbored animus toward Spencer, but a personal conflict alone does not\\n\\nconstitute retaliation. Cf. Hawkins v. PepsiCo, Inc., 203 F.3d 274, 281 (4th Cir. 2000)\\n\\n(“But Hawkins presents no facts that tend to show this allegedly disparate treatment was\\n\\ndue to race rather than Price’s admittedly low regard for Hawkins’ individual\\n\\nperformance.”). Because the district court correctly found that Spencer cannot establish a\\n\\nprima facie case of retaliation, we do not address the merits of the University’s defenses.\\n\\n Accordingly, the judgment of the district court is\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 14\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4381041/\", \"author_raw\": \"RICHARDSON, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"WILKINSON"},"judge2":{"kind":"string","value":"FLOYD"},"judge3":{"kind":"string","value":"RICHARDSON"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"WILKINSON\": \", Circuit\", \"FLOYD\": \", Circuit\", \"RICHARDSON\": \", Circuit\"}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4603788/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Zoe Spencer v. Virginia State University\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-03-26\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 17-2453\n\n\nZOE SPENCER,\n\n Plaintiff - Appellant,\n\n v.\n\nVIRGINIA STATE UNIVERSITY; KEITH T. MILLER,\n\n Defendants - Appellees.\n\n\nAppeal from the United States District Court for the Eastern District of Virginia, at\nRichmond. Henry E. Hudson, Senior District Judge. (3:16-cv-00989-HEH-RCY)\n\n\nArgued: October 31, 2018 Decided: March 18, 2019\n Amended: March 26, 2019\n\n\nBefore WILKINSON, FLOYD, and RICHARDSON, Circuit Judges.\n\n\nAffirmed by published opinion. Judge Richardson wrote the opinion, in which Judge\nWilkinson and Judge Floyd concurred.\n\n\nARGUED: Noah Barnett Peters, NOAH PETERS LAW, Washington, D.C., for\nAppellant. Jimmy F. Robinson, Jr., OGLETREE DEAKINS NASH SMOAK &\nSTEWART, PC, Richmond, Virginia, for Appellees. ON BRIEF: Christopher C.\nMurray, Indianapolis, Indiana, Elizabeth Ebanks, Kyle R. Elliott, OGLETREE\nDEAKINS NASH SMOAK & STEWART, PC, Richmond, Virginia, for Appellees.\n\fRICHARDSON, Circuit Judge:\n\n Dr. Zoe Spencer, a sociology professor at Virginia State University, sued the\n\nUniversity under the Equal Pay Act and Title VII for paying her less than two male\n\nprofessors, allegedly because she is a woman.\n\n Spencer earned about $70,000 per year—a median salary when compared to the\n\nmen who were also full professors in the Department of Sociology, Social Work, and\n\nCriminal Justice. But Spencer’s lawsuit proposes comparing her pay to that of two\n\nformer University administrators, Drs. Michael Shackleford and Cortez Dial, who each\n\nearned over $100,000 per year as professors in other departments. While Spencer asserts\n\nthat the difference in pay was due to her sex, the University provides a different\n\nexplanation: Shackleford’s and Dial’s jobs differed from Spencer’s and, as former\n\nadministrators, their pay was set as a prorated portion of their previous salaries.\n\n After discovery, the district court granted summary judgment for the University\n\n(and its former president, Dr. Keith Miller). We affirm. Though Spencer establishes a\n\npay disparity, she fails to present evidence that creates a genuine issue of material fact\n\nthat Shackleford and Dial are appropriate comparators. In any event, unrebutted evidence\n\nshows that the University based Shackleford’s and Dial’s higher pay on their prior\n\nservice as University administrators, not their sex. 1\n\n\n 1\n We review the district court’s grant of summary judgment de novo. In re Lipitor\n(Atorvastatin Calcium) Mktg., Sales Practices & Prods. Liab. Litig. (No II), 892 F.3d\n624, 645 (4th Cir. 2018). After considering the evidence and all fair inferences in the\nlight most favorable to the nonmovant, summary judgment is appropriate “if the movant\nshows that there is no genuine dispute as to any material fact.” Fed. R. Civ. P. 56(a).\n(Continued)\n 2\n\f I. Equal Pay Act\n\n Spencer first claims that the disparity between her salary and her chosen\n\ncomparators’ violates the Equal Pay Act. The statute forbids the University (like other\n\nemployers) from:\n\n Discriminat[ing] . . . between employees on the basis of sex by paying\n wages to employees . . . at a rate less than the rate at which [the employer]\n pays wages to employees of the opposite sex . . . for equal work on jobs the\n performance of which requires equal skill, effort, and responsibility, and\n which are performed under similar working conditions, except where such\n payment is made pursuant to (i) a seniority system; (ii) a merit system; (iii)\n a system which measures earnings by quantity or quality of production; or\n (iv) a differential based on any other factor other than sex . . . .\n\n29 U.S.C. § 206(d)(1). To prove a violation of the Act, Spencer must make an initial\n\n(i.e., prima facie) showing of three elements: (1) the University paid higher wages to an\n\nemployee of the opposite sex who (2) performed equal work on jobs requiring equal skill,\n\neffort, and responsibility (3) under similar working conditions. EEOC v. Maryland Ins.\n\nAdmin., 879 F.3d 114, 120 (4th Cir. 2018) (citing Corning Glass Works v. Brennan, 417\n\nU.S. 188, 195 (1974)).\n\n This initial showing permits an inference that a pay disparity was based on sex\n\ndiscrimination. Maryland Ins. Admin., 879 F.3d at 120. The inference of discrimination\n\nstands even without the support of any evidence of discriminatory intent. Id. Only once\n\n\n\n\n“To survive summary judgment, ‘there must be evidence on which the jury could\nreasonably find for the nonmovant.’” Lee v. Town of Seaboard, 863 F.3d 323, 327 (4th\nCir. 2017) (quoting Anderson v. Liberty Lobby, Inc., 477 U.S. 242, 252 (1986)).\n\n\n 3\n\fthis inference exists does the burden shift to the employer to show that the pay\n\ndifferential was based on a factor other than sex. Id.\n\n Spencer’s choice of Shackleford and Dial as comparators establishes the first\n\nelement of her initial showing—the existence of a wage differential. By choosing two of\n\nthe highest-paid professors at the University, Spencer ensured that her wages were much\n\nlower. Yet that same decision to pick Shackleford and Dial precludes her from\n\nestablishing, as the second element requires, that she and they performed “equal” work\n\nrequiring “equal skill, effort, and responsibility.”\n\n Equality under the Act is a demanding threshold requirement. It requires a\n\ncomparator to have performed work “virtually identical” (or the apparent synonym,\n\n“substantially equal”) to the plaintiff’s in skill, effort, and responsibility. Wheatley v.\n\nWicomico Cty., 390 F.3d 328, 332–33 (4th Cir. 2004). Similarity of work is not enough;\n\nthe Act explicitly distinguishes between the work itself (which must be “equal”) and the\n\nconditions of work (which need only be “similar”). 29 U.S.C. § 206(d)(1). The Act does\n\nnot provide courts with a way of evaluating whether distinct work might have\n\n“comparable” value to the work the plaintiff performed. See Wheatley, 390 F.3d at 333;\n\nsee also Sims-Fingers v. City of Indianapolis, 493 F.3d 768, 771 (7th Cir. 2007) (Posner,\n\nJ.) (explaining that, when trying to identify “comparable” pay for unequal work, there are\n\n“no good answers that are within the competence of judges to give”). Instead, the Act’s\n\ninference of discrimination may arise only when the comparator’s work is equal to the\n\nplaintiff’s.\n\n\n\n 4\n\f In alleging this necessary equality, a plaintiff may not rely on broad\n\ngeneralizations at a high level of abstraction. Wheatley, 390 F.3d at 332. But Spencer\n\nattempts just such an impermissibly general comparison. In Spencer’s view, all\n\nUniversity professors perform equal work because they all perform the same essential\n\ntasks: preparing syllabi and lessons, instructing students, tracking student progress,\n\nmanaging the classroom, providing feedback, and inputting grades. See Appellant’s Brief\n\nat 9. The performance of these tasks, Spencer posits, requires the same skills: studying,\n\npreparing, presenting, discussing, and so forth. See id. at 9–10. But these tasks and skills\n\nare shared by middle-school teachers and law-school professors, pre-algebra teachers and\n\nbiomedical-engineering professors.\n\n This attempted comparison ultimately relies on the common title of “professor”\n\nplus some generalized responsibilities (e.g., teaching students). Yet we have rejected an\n\nanalogous claim that jobs with the same title and only vaguely corresponding\n\nresponsibilities can be considered equal. In Wheatley we concluded that the plaintiffs,\n\nsupervisors in a county’s emergency-services department, failed to meet their burden to\n\nshow that supervisors in different departments performed equal work because they could\n\nnot demonstrate that the different jobs were equal in skill and responsibility. 390 F.3d at\n\n334; see also Sims-Fingers, 493 F.3d at 771. Spencer’s case suffers from a near-identical\n\nflaw.\n\n Spencer’s bird’s-eye view is particularly unpersuasive given the inherent features\n\nof academia. Professors are not interchangeable like widgets. Various considerations\n\ninfluence the hiring, promotion, and compensation of different professorial jobs. Cf.\n\n 5\n\fZahorik v. Cornell Univ., 729 F.2d 85, 93 (2d Cir. 1984) (discussing the tenure process).\n\nAs a result, faculty salary decisions require a complex balancing of factors. Among other\n\nthings, those decisions account for the differences in skill and responsibility attendant to\n\ndifferent jobs. For instance, an engineering professorship requires different skills, effort,\n\nand responsibility than professorships in other fields, such as sociology. Evidence\n\noffered by Spencer proves this very point: The University systematically pays\n\nengineering professors more than humanities professors. J.A. at 136. This reflects\n\ndifferences in skill along with market forces that compensate engineers more highly.\n\nThis market reality confirms that Spencer’s broad generalizations about tasks and skills,\n\nwhich apply to virtually all teachers, fail to satisfy her burden to show equal work.\n\n In contrast to Spencer’s generalized tasks and skills, a litany of concrete\n\ndifferences underscore that Spencer does not perform work equal to that of Shackleford\n\nand Dial. First, Shackleford and Dial taught in different departments than Spencer did.\n\nWhile comparisons might be drawn between some departments, any such comparison\n\nrequires the plaintiff to articulate with specificity why the work performed and skills\n\nneeded by a professor in one department are virtually identical—and not just generally\n\nrelated or of comparable worth—to those in another. As our precedents recognize, the\n\ndifferences between academic departments generally involve differences in skill and\n\nresponsibility. See Strag v. Bd. of Trustees, Craven Cmty. Coll., 55 F.3d 943, 950 (4th\n\nCir. 1995) (finding that the Biology and Mathematics departments required instructors to\n\nhave different skills and responsibilities); Soble v. Univ. of Maryland, 778 F.2d 164, 167\n\n(4th Cir. 1985) (finding that the specialized nature of certain university departments\n\n 6\n\fcalled for distinct skills); cf. Wheatley, 390 F.3d at 332–33 (recognizing job-related\n\ndifferences for directors of different county government departments).\n\n There are still more differences. Along with serving in different departments, the\n\nthree professors taught at different class levels at the University. Spencer taught mainly\n\nundergraduate courses, while Shackleford and Dial taught more graduate courses. And\n\nShackleford also supervised doctoral dissertations. Contrary to Spencer’s assertion, the\n\nfact that the University credited hours spent supervising dissertations in a similar manner\n\nto hours spent teaching regular courses does nothing to establish the equivalency of\n\nsupervising dissertations and teaching undergraduates. Nor did the professors work equal\n\nhours, as the record shows that Shackleford and Dial worked more than Spencer did week\n\nto week. 2\n\n None of this is to say that the Equal Pay Act cannot apply in the higher-education\n\ncontext. But in that context—one where the work is an exercise in intellectual creativity\n\nthat can be judged only according to intricate, field-specific, and often subjective\n\ncriteria—Spencer must provide the court with more than broad generalities to meet her\n\nburden. She must present evidence on which a jury could rely to decide that she,\n\nShackleford, and Dial had equal jobs, not just that they all performed vaguely related\n\n\n 2\n Spencer paradoxically argues that other differences between her work and that of\nher chosen comparators render her work equal. For example, Spencer asserts that she\nconducted research and published while Shackleford and Dial did not. This evidence\ncannot save her claim given the differences already discussed. Piling on differences—\neven those suggesting that Spencer did better or more work—does nothing to prove\nequality of work.\n\n\n 7\n\ftasks using nominally comparable skills. That is, there must be evidence showing the\n\njobs were equal in the strict sense of involving “virtually identical” work, skill, effort,\n\nand responsibility, not in the loose sense of having some comparative value. Wheatley,\n\n390 F.3d at 333.\n\n Despite all of these issues, Spencer claims her expert, Joseph Rosenberg, found\n\n“that Shackleford and Dial were significantly overpaid in comparison to Spencer.”\n\nAppellant’s Brief at 44 (emphasis added). Not only is this irrelevant to establishing equal\n\nwork, this claim is a bit misleading: Rosenberg asserted that Shackleford and Dial were\n\noverpaid relative to all other professors, both men and women. 3\n\n In addition to looking at her chosen comparators, Spencer’s expert tried to identify\n\na general disparity between the pay of men and women at the University. But his efforts\n\n 3\n Spencer’s brief asserts that Rosenberg:\n used four independent variables to account for the skill, effort, and\n responsibility required of professors at [the University], taking into account\n experience, departmental affiliation, faculty rank, and whether the professor\n was a Chair or Dean. Rosenberg found, at a 97.5% confidence interval,\n that Shackleford and Dial were significantly overpaid in comparison to\n Spencer even when accounting for the different departments in which they\n taught.\n\nAppellant’s Brief at 44 (citations and emphasis omitted). Contrary to Spencer’s\ncharacterization, Rosenberg’s report does not appear to take departmental affiliation into\naccount, instead only accounting for the broader category of “school,” each of which\nencompasses several departments. And there is another flaw, though immaterial given\nthe report’s other shortcomings: Rosenberg’s expert report does not account for\nSpencer’s comparators’ prior work in the administration, even though everyone appears\nto agree that their prior administrative experience determined their salaries. Cf. Smith v.\nVirginia Commonwealth Univ., 84 F.3d 672, 675 (4th Cir. 1996) (noting that\nadministrators are generally paid higher salaries than teachers and that these higher\nsalaries persist when administrators move back to teaching).\n\n 8\n\frevealed no statistically significant disparity within each “school.” If anything, this\n\nevidence undermines Spencer’s claimed inference of discrimination. See Strag, 55 F.3d\n\nat 950 (suggesting that “isolated incidents or random comparisons demonstrating\n\ndisparities in treatment may be insufficient to draw a prima facie inference of\n\ndiscrimination without additional evidence that the alleged phenomenon of inequality\n\nalso exists with respect to the entire relevant group of employees” (quoting Houck v.\n\nVirginia Polytechnic Ins., 10 F.3d 204, 206–07 (4th Cir. 1993)).\n\n Despite her expert’s efforts, Spencer’s generalized claims cannot establish that she\n\nengaged in equal work, which categorically dooms her attempt to establish wage\n\ndiscrimination under the Equal Pay Act. Cf. Wheatley, 390 F.3d at 334 (a plaintiff may\n\nnot “indiscriminately aim at all department supervisors collectively, and then expect to\n\nmeet the EPA standard” for equal work).\n\n But even if Spencer could meet her initial burden, her claim would still fail\n\nbecause the University established that the salary difference was based on a “factor other\n\nthan sex.” 29 U.S.C. § 206(d)(1)(iv). As the defendant, the University bore the burden\n\nof establishing this affirmative defense. Maryland Ins. Admin., 879 F.3d at 120.\n\nGranting summary judgment on this ground required the district court to find that the\n\nproffered reason did in fact explain the wage disparity, not merely that it could. Id. at\n\n121.\n\n Here, there is no dispute that the wage difference at issue resulted from the\n\nUniversity setting Shackleford’s and Dial’s pay at 75% of their previous salaries as\n\nadministrators. In practice, the University generally paid former administrators who\n\n 9\n\fbecame professors “9/12ths” of their administrator salary. This practice appears to rest\n\non the theory that professors work nine months out of the year, while administrators work\n\nyear-round. Indeed, Spencer admits that her comparators’ pay during their short stints as\n\nUniversity professors was set according to the 9/12ths practice. Appellant’s Reply Brief\n\nat 16 (“Shackleford and Dial’s salaries were set entirely on their prior salaries as\n\nadministrators.”).\n\n In response to the University’s explanation, Spencer claims that the 9/12ths\n\npractice should not have been used to calculate Shackleford’s and Dial’s salaries.\n\nAccording to her, the University’s historical practice only applied to administrators who\n\nwere previously tenured faculty. But even if the University erroneously applied its\n\n9/12ths practice to overpay Shackleford and Dial, such an imprudent decision would still\n\nserve as a non-sex-based explanation for the pay disparity. See Anderson v.\n\nWestinghouse Savannah River Co., 406 F.3d 248, 272 (4th Cir. 2005) (“We do not sit as\n\na ‘super-personnel department weighing the prudence of employment decisions’ made by\n\nthe defendants.” (quoting DeJarnette v. Corning, Inc., 133 F.3d 293, 299 (4th Cir.\n\n1998)); Smith v. Univ. of North Carolina, 632 F.2d 316, 346 (4th Cir. 1980) (“[The] law\n\ndoes not require, in the first instance, that employment be rational, wise, or well-\n\nconsidered—only that it be nondiscriminatory.” (quoting Powell v. Syracuse Univ., 580\n\nF.2d 1150, 1156–57 (2d Cir. 1978)).\n\n The Equal Pay Act is a powerful tool, permitting an employee to prevail on a wage\n\ndiscrimination claim with no evidence of intentional discrimination. But this tool must\n\nbe tempered by adherence to its provisions. Doing so requires that the work performed\n\n 10\n\fby the plaintiff and her comparators be equal and that the wage disparity not be based on\n\na factor other than sex. Spencer’s claim fails on both requirements.\n\n II. Title VII\n\n Having rejected Spencer’s Equal Pay Act claim, we must separately consider her\n\nclaim of Title VII sex-based wage discrimination. Under Title VII of the Civil Rights\n\nAct of 1964, an employer cannot “discriminate against any individual with respect to\n\n[her] compensation . . . because of such individual’s . . . sex.” 42 U.S.C. § 2000e-2(a)(1).\n\nTitle VII, in contrast to the Equal Pay Act, requires establishing intentional\n\ndiscrimination. A Title VII plaintiff may make this showing of intentional discrimination\n\nusing direct or circumstantial evidence. Alternatively, the plaintiff may use the burden-\n\nshifting framework of McDonnell Douglas Corp. v. Green, 411 U.S. 792 (1973), “to\n\ndevelop an inferential case” of discriminatory intent. Chalmers v. Tulon Co. of\n\nRichmond, 101 F.3d 1012, 1017 (4th Cir. 1996).\n\n A prima facie pay-disparity case under McDonnell Douglas requires a plaintiff to\n\nestablish (1) she is a member of a protected class, (2) she was performing her job\n\nsatisfactorily, (3) an adverse employment action occurred, and (4) the circumstances\n\nsuggest an unlawfully discriminatory motive. See McDonnell Douglas, 411 U.S. at 802;\n\nTexas Dep’t of Cmty. Affairs v. Burdine, 450 U.S. 248, 253 (1981). Where, as here, the\n\nprima facie case of wage discrimination is based on comparators, the plaintiff must show\n\nthat she is paid less than men in similar jobs. See Brinkley-Obu v. Hughes Training, Inc.,\n\n36 F.3d 336, 343 (4th Cir. 1994).\n\n\n\n 11\n\f Title VII requires the compared jobs to be only “similar” rather than “equal,” as\n\nrequired under the Equal Pay Act. See id. While there is no bright-line rule for what\n\nmakes two jobs “similar” under Title VII, courts consider “whether the employees (i)\n\nheld the same job description, (ii) were subject to the same standards, (iii) were\n\nsubordinate to the same supervisor, and (iv) had comparable experience, education, and\n\nother qualifications—provided the employer considered these latter factors in making the\n\npersonnel decision.” Bio v. Fed. Express Corp., 424 F.3d 593, 597 (7th Cir. 2005)\n\n(internal quotation marks omitted); see also Herster v. Bd. of Supervisors of Louisiana\n\nState Univ., 887 F.3d 177, 185 (5th Cir. 2018) (stating that a “variety of factors are\n\nconsidered when determining whether a comparator is similarly situated, including job\n\nresponsibility, experience, and qualifications.”). While Title VII’s “similarity”\n\nrequirement demands less of plaintiffs than the Equal Pay Act’s “equality” requirement,\n\nit is not toothless: the plaintiff must provide evidence that the proposed comparators are\n\nnot just similar in some respects, but “similarly-situated in all respects.” Mitchell v.\n\nToledo Hosp., 964 F.2d 577, 583 (6th Cir. 1992). For the same reasons we discussed\n\nabove, Spencer’s broad generalizations cannot even show sufficient similarity to meet her\n\nburden under Title VII. 4\n\n\n\n\n 4\n Just as in the Equal Pay Act context, Spencer’s expert does not help her to\nestablish a prima facie case here. While a plaintiff may use statistics to suggest a\ndiscriminatory motive, Spencer’s expert found no statistical evidence that the University\npaid women less than men.\n\n\n 12\n\f Even if we concluded that Spencer had established a prima facie case of Title VII\n\nwage discrimination, her case still could not withstand summary judgment. Once a\n\nplaintiff establishes a prima facie case, the burden of production shifts to the employer to\n\nproffer a legitimate, nondiscriminatory explanation for the wage disparity. Guessous v.\n\nFairview Prop. Investments, LLC, 828 F.3d 208, 216–17 (4th Cir. 2016); Maryland Ins.\n\nAdmin., 879 F.3d at 120 n.7. Here, the University satisfies this requirement through its\n\npractice of paying administrators 9/12ths of their previous salary. Just as this practice\n\nsatisfies the Equal Pay Act’s “factor other than sex” affirmative defense, it qualifies as a\n\nlegitimate, nondiscriminatory explanation under Title VII. Cf. Cty. of Washington v.\n\nGunther, 452 U.S. 161, 169 (1981) (recognizing that the Bennett Amendment to Title VII\n\nincorporates the four affirmative defenses from the Equal Pay Act).\n\n Having proffered a nondiscriminatory explanation, the University shifts the burden\n\nback to Spencer to prove that the explanation is merely pretextual for invidious\n\ndiscrimination. Guessous, 828 F.3d at 216. Spencer cannot supply any evidence of this.\n\nSince the touchstone of discrimination is treating two groups differently based on\n\ncharacteristics only one possesses, it is vital for Spencer to provide evidence that the\n\nUniversity has used the 9/12ths policy to pay men more than women. Instead, Spencer\n\nmerely argues that the University misapplied the 9/12ths policy to Shackleford and Dial.\n\nBut again, even if the University “erroneously or even purposely misapplied the . . .\n\npolicy, it is not proof of unlawful discrimination.” Dugan v. Albemarle Cty. Sch. Bd.,\n\n293 F.3d 716, 722 (4th Cir. 2002).\n\n\n\n 13\n\f As a final note, Spencer also alleges that the University, and its former provost,\n\nengaged in unlawful retaliation because of her complaints about pay disparities. As the\n\ndistrict court noted, the facts supporting most of these allegations are exceedingly weak,\n\nand the allegations themselves are mostly conclusory. See Spencer v. Virginia State\n\nUniv., No. 3:16-cv-989, 2018 WL 627558, at *14–17 (E.D. Va. Jan. 30, 2018). Even if\n\nSpencer’s characterization of the behavior is accurate, Spencer offers insufficient\n\nevidence that each action was both material and undertaken because of her complaints\n\nabout salary equity. See Burlington N. & Santa Fe Ry. Co. v. White, 548 U.S. 53, 68\n\n(2006) (holding that “a plaintiff must show that a reasonable employee would have found\n\nthe challenged action materially adverse . . . [meaning] it might have ‘dissuaded a\n\nreasonable worker from making or supporting a charge of discrimination’”). That is not\n\nto say no one harbored animus toward Spencer, but a personal conflict alone does not\n\nconstitute retaliation. Cf. Hawkins v. PepsiCo, Inc., 203 F.3d 274, 281 (4th Cir. 2000)\n\n(“But Hawkins presents no facts that tend to show this allegedly disparate treatment was\n\ndue to race rather than Price’s admittedly low regard for Hawkins’ individual\n\nperformance.”). Because the district court correctly found that Spencer cannot establish a\n\nprima facie case of retaliation, we do not address the merits of the University’s defenses.\n\n Accordingly, the judgment of the district court is\n\n AFFIRMED.\n\n\n\n\n 14\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Zoe Spencer v. Virginia State University\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-03-26\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 17-2453\\n\\n\\nZOE SPENCER,\\n\\n Plaintiff - Appellant,\\n\\n v.\\n\\nVIRGINIA STATE UNIVERSITY; KEITH T. MILLER,\\n\\n Defendants - Appellees.\\n\\n\\nAppeal from the United States District Court for the Eastern District of Virginia, at\\nRichmond. Henry E. Hudson, Senior District Judge. (3:16-cv-00989-HEH-RCY)\\n\\n\\nArgued: October 31, 2018 Decided: March 18, 2019\\n Amended: March 26, 2019\\n\\n\\nBefore WILKINSON, FLOYD, and RICHARDSON, Circuit Judges.\\n\\n\\nAffirmed by published opinion. Judge Richardson wrote the opinion, in which Judge\\nWilkinson and Judge Floyd concurred.\\n\\n\\nARGUED: Noah Barnett Peters, NOAH PETERS LAW, Washington, D.C., for\\nAppellant. Jimmy F. Robinson, Jr., OGLETREE DEAKINS NASH SMOAK &\\nSTEWART, PC, Richmond, Virginia, for Appellees. ON BRIEF: Christopher C.\\nMurray, Indianapolis, Indiana, Elizabeth Ebanks, Kyle R. Elliott, OGLETREE\\nDEAKINS NASH SMOAK & STEWART, PC, Richmond, Virginia, for Appellees.\\n\\fRICHARDSON, Circuit Judge:\\n\\n Dr. Zoe Spencer, a sociology professor at Virginia State University, sued the\\n\\nUniversity under the Equal Pay Act and Title VII for paying her less than two male\\n\\nprofessors, allegedly because she is a woman.\\n\\n Spencer earned about $70,000 per year—a median salary when compared to the\\n\\nmen who were also full professors in the Department of Sociology, Social Work, and\\n\\nCriminal Justice. But Spencer’s lawsuit proposes comparing her pay to that of two\\n\\nformer University administrators, Drs. Michael Shackleford and Cortez Dial, who each\\n\\nearned over $100,000 per year as professors in other departments. While Spencer asserts\\n\\nthat the difference in pay was due to her sex, the University provides a different\\n\\nexplanation: Shackleford’s and Dial’s jobs differed from Spencer’s and, as former\\n\\nadministrators, their pay was set as a prorated portion of their previous salaries.\\n\\n After discovery, the district court granted summary judgment for the University\\n\\n(and its former president, Dr. Keith Miller). We affirm. Though Spencer establishes a\\n\\npay disparity, she fails to present evidence that creates a genuine issue of material fact\\n\\nthat Shackleford and Dial are appropriate comparators. In any event, unrebutted evidence\\n\\nshows that the University based Shackleford’s and Dial’s higher pay on their prior\\n\\nservice as University administrators, not their sex. 1\\n\\n\\n 1\\n We review the district court’s grant of summary judgment de novo. In re Lipitor\\n(Atorvastatin Calcium) Mktg., Sales Practices & Prods. Liab. Litig. (No II), 892 F.3d\\n624, 645 (4th Cir. 2018). After considering the evidence and all fair inferences in the\\nlight most favorable to the nonmovant, summary judgment is appropriate “if the movant\\nshows that there is no genuine dispute as to any material fact.” Fed. R. Civ. P. 56(a).\\n(Continued)\\n 2\\n\\f I. Equal Pay Act\\n\\n Spencer first claims that the disparity between her salary and her chosen\\n\\ncomparators’ violates the Equal Pay Act. The statute forbids the University (like other\\n\\nemployers) from:\\n\\n Discriminat[ing] . . . between employees on the basis of sex by paying\\n wages to employees . . . at a rate less than the rate at which [the employer]\\n pays wages to employees of the opposite sex . . . for equal work on jobs the\\n performance of which requires equal skill, effort, and responsibility, and\\n which are performed under similar working conditions, except where such\\n payment is made pursuant to (i) a seniority system; (ii) a merit system; (iii)\\n a system which measures earnings by quantity or quality of production; or\\n (iv) a differential based on any other factor other than sex . . . .\\n\\n29 U.S.C. § 206(d)(1). To prove a violation of the Act, Spencer must make an initial\\n\\n(i.e., prima facie) showing of three elements: (1) the University paid higher wages to an\\n\\nemployee of the opposite sex who (2) performed equal work on jobs requiring equal skill,\\n\\neffort, and responsibility (3) under similar working conditions. EEOC v. Maryland Ins.\\n\\nAdmin., 879 F.3d 114, 120 (4th Cir. 2018) (citing Corning Glass Works v. Brennan, 417\\n\\nU.S. 188, 195 (1974)).\\n\\n This initial showing permits an inference that a pay disparity was based on sex\\n\\ndiscrimination. Maryland Ins. Admin., 879 F.3d at 120. The inference of discrimination\\n\\nstands even without the support of any evidence of discriminatory intent. Id. Only once\\n\\n\\n\\n\\n“To survive summary judgment, ‘there must be evidence on which the jury could\\nreasonably find for the nonmovant.’” Lee v. Town of Seaboard, 863 F.3d 323, 327 (4th\\nCir. 2017) (quoting Anderson v. Liberty Lobby, Inc., 477 U.S. 242, 252 (1986)).\\n\\n\\n 3\\n\\fthis inference exists does the burden shift to the employer to show that the pay\\n\\ndifferential was based on a factor other than sex. Id.\\n\\n Spencer’s choice of Shackleford and Dial as comparators establishes the first\\n\\nelement of her initial showing—the existence of a wage differential. By choosing two of\\n\\nthe highest-paid professors at the University, Spencer ensured that her wages were much\\n\\nlower. Yet that same decision to pick Shackleford and Dial precludes her from\\n\\nestablishing, as the second element requires, that she and they performed “equal” work\\n\\nrequiring “equal skill, effort, and responsibility.”\\n\\n Equality under the Act is a demanding threshold requirement. It requires a\\n\\ncomparator to have performed work “virtually identical” (or the apparent synonym,\\n\\n“substantially equal”) to the plaintiff’s in skill, effort, and responsibility. Wheatley v.\\n\\nWicomico Cty., 390 F.3d 328, 332–33 (4th Cir. 2004). Similarity of work is not enough;\\n\\nthe Act explicitly distinguishes between the work itself (which must be “equal”) and the\\n\\nconditions of work (which need only be “similar”). 29 U.S.C. § 206(d)(1). The Act does\\n\\nnot provide courts with a way of evaluating whether distinct work might have\\n\\n“comparable” value to the work the plaintiff performed. See Wheatley, 390 F.3d at 333;\\n\\nsee also Sims-Fingers v. City of Indianapolis, 493 F.3d 768, 771 (7th Cir. 2007) (Posner,\\n\\nJ.) (explaining that, when trying to identify “comparable” pay for unequal work, there are\\n\\n“no good answers that are within the competence of judges to give”). Instead, the Act’s\\n\\ninference of discrimination may arise only when the comparator’s work is equal to the\\n\\nplaintiff’s.\\n\\n\\n\\n 4\\n\\f In alleging this necessary equality, a plaintiff may not rely on broad\\n\\ngeneralizations at a high level of abstraction. Wheatley, 390 F.3d at 332. But Spencer\\n\\nattempts just such an impermissibly general comparison. In Spencer’s view, all\\n\\nUniversity professors perform equal work because they all perform the same essential\\n\\ntasks: preparing syllabi and lessons, instructing students, tracking student progress,\\n\\nmanaging the classroom, providing feedback, and inputting grades. See Appellant’s Brief\\n\\nat 9. The performance of these tasks, Spencer posits, requires the same skills: studying,\\n\\npreparing, presenting, discussing, and so forth. See id. at 9–10. But these tasks and skills\\n\\nare shared by middle-school teachers and law-school professors, pre-algebra teachers and\\n\\nbiomedical-engineering professors.\\n\\n This attempted comparison ultimately relies on the common title of “professor”\\n\\nplus some generalized responsibilities (e.g., teaching students). Yet we have rejected an\\n\\nanalogous claim that jobs with the same title and only vaguely corresponding\\n\\nresponsibilities can be considered equal. In Wheatley we concluded that the plaintiffs,\\n\\nsupervisors in a county’s emergency-services department, failed to meet their burden to\\n\\nshow that supervisors in different departments performed equal work because they could\\n\\nnot demonstrate that the different jobs were equal in skill and responsibility. 390 F.3d at\\n\\n334; see also Sims-Fingers, 493 F.3d at 771. Spencer’s case suffers from a near-identical\\n\\nflaw.\\n\\n Spencer’s bird’s-eye view is particularly unpersuasive given the inherent features\\n\\nof academia. Professors are not interchangeable like widgets. Various considerations\\n\\ninfluence the hiring, promotion, and compensation of different professorial jobs. Cf.\\n\\n 5\\n\\fZahorik v. Cornell Univ., 729 F.2d 85, 93 (2d Cir. 1984) (discussing the tenure process).\\n\\nAs a result, faculty salary decisions require a complex balancing of factors. Among other\\n\\nthings, those decisions account for the differences in skill and responsibility attendant to\\n\\ndifferent jobs. For instance, an engineering professorship requires different skills, effort,\\n\\nand responsibility than professorships in other fields, such as sociology. Evidence\\n\\noffered by Spencer proves this very point: The University systematically pays\\n\\nengineering professors more than humanities professors. J.A. at 136. This reflects\\n\\ndifferences in skill along with market forces that compensate engineers more highly.\\n\\nThis market reality confirms that Spencer’s broad generalizations about tasks and skills,\\n\\nwhich apply to virtually all teachers, fail to satisfy her burden to show equal work.\\n\\n In contrast to Spencer’s generalized tasks and skills, a litany of concrete\\n\\ndifferences underscore that Spencer does not perform work equal to that of Shackleford\\n\\nand Dial. First, Shackleford and Dial taught in different departments than Spencer did.\\n\\nWhile comparisons might be drawn between some departments, any such comparison\\n\\nrequires the plaintiff to articulate with specificity why the work performed and skills\\n\\nneeded by a professor in one department are virtually identical—and not just generally\\n\\nrelated or of comparable worth—to those in another. As our precedents recognize, the\\n\\ndifferences between academic departments generally involve differences in skill and\\n\\nresponsibility. See Strag v. Bd. of Trustees, Craven Cmty. Coll., 55 F.3d 943, 950 (4th\\n\\nCir. 1995) (finding that the Biology and Mathematics departments required instructors to\\n\\nhave different skills and responsibilities); Soble v. Univ. of Maryland, 778 F.2d 164, 167\\n\\n(4th Cir. 1985) (finding that the specialized nature of certain university departments\\n\\n 6\\n\\fcalled for distinct skills); cf. Wheatley, 390 F.3d at 332–33 (recognizing job-related\\n\\ndifferences for directors of different county government departments).\\n\\n There are still more differences. Along with serving in different departments, the\\n\\nthree professors taught at different class levels at the University. Spencer taught mainly\\n\\nundergraduate courses, while Shackleford and Dial taught more graduate courses. And\\n\\nShackleford also supervised doctoral dissertations. Contrary to Spencer’s assertion, the\\n\\nfact that the University credited hours spent supervising dissertations in a similar manner\\n\\nto hours spent teaching regular courses does nothing to establish the equivalency of\\n\\nsupervising dissertations and teaching undergraduates. Nor did the professors work equal\\n\\nhours, as the record shows that Shackleford and Dial worked more than Spencer did week\\n\\nto week. 2\\n\\n None of this is to say that the Equal Pay Act cannot apply in the higher-education\\n\\ncontext. But in that context—one where the work is an exercise in intellectual creativity\\n\\nthat can be judged only according to intricate, field-specific, and often subjective\\n\\ncriteria—Spencer must provide the court with more than broad generalities to meet her\\n\\nburden. She must present evidence on which a jury could rely to decide that she,\\n\\nShackleford, and Dial had equal jobs, not just that they all performed vaguely related\\n\\n\\n 2\\n Spencer paradoxically argues that other differences between her work and that of\\nher chosen comparators render her work equal. For example, Spencer asserts that she\\nconducted research and published while Shackleford and Dial did not. This evidence\\ncannot save her claim given the differences already discussed. Piling on differences—\\neven those suggesting that Spencer did better or more work—does nothing to prove\\nequality of work.\\n\\n\\n 7\\n\\ftasks using nominally comparable skills. That is, there must be evidence showing the\\n\\njobs were equal in the strict sense of involving “virtually identical” work, skill, effort,\\n\\nand responsibility, not in the loose sense of having some comparative value. Wheatley,\\n\\n390 F.3d at 333.\\n\\n Despite all of these issues, Spencer claims her expert, Joseph Rosenberg, found\\n\\n“that Shackleford and Dial were significantly overpaid in comparison to Spencer.”\\n\\nAppellant’s Brief at 44 (emphasis added). Not only is this irrelevant to establishing equal\\n\\nwork, this claim is a bit misleading: Rosenberg asserted that Shackleford and Dial were\\n\\noverpaid relative to all other professors, both men and women. 3\\n\\n In addition to looking at her chosen comparators, Spencer’s expert tried to identify\\n\\na general disparity between the pay of men and women at the University. But his efforts\\n\\n 3\\n Spencer’s brief asserts that Rosenberg:\\n used four independent variables to account for the skill, effort, and\\n responsibility required of professors at [the University], taking into account\\n experience, departmental affiliation, faculty rank, and whether the professor\\n was a Chair or Dean. Rosenberg found, at a 97.5% confidence interval,\\n that Shackleford and Dial were significantly overpaid in comparison to\\n Spencer even when accounting for the different departments in which they\\n taught.\\n\\nAppellant’s Brief at 44 (citations and emphasis omitted). Contrary to Spencer’s\\ncharacterization, Rosenberg’s report does not appear to take departmental affiliation into\\naccount, instead only accounting for the broader category of “school,” each of which\\nencompasses several departments. And there is another flaw, though immaterial given\\nthe report’s other shortcomings: Rosenberg’s expert report does not account for\\nSpencer’s comparators’ prior work in the administration, even though everyone appears\\nto agree that their prior administrative experience determined their salaries. Cf. Smith v.\\nVirginia Commonwealth Univ., 84 F.3d 672, 675 (4th Cir. 1996) (noting that\\nadministrators are generally paid higher salaries than teachers and that these higher\\nsalaries persist when administrators move back to teaching).\\n\\n 8\\n\\frevealed no statistically significant disparity within each “school.” If anything, this\\n\\nevidence undermines Spencer’s claimed inference of discrimination. See Strag, 55 F.3d\\n\\nat 950 (suggesting that “isolated incidents or random comparisons demonstrating\\n\\ndisparities in treatment may be insufficient to draw a prima facie inference of\\n\\ndiscrimination without additional evidence that the alleged phenomenon of inequality\\n\\nalso exists with respect to the entire relevant group of employees” (quoting Houck v.\\n\\nVirginia Polytechnic Ins., 10 F.3d 204, 206–07 (4th Cir. 1993)).\\n\\n Despite her expert’s efforts, Spencer’s generalized claims cannot establish that she\\n\\nengaged in equal work, which categorically dooms her attempt to establish wage\\n\\ndiscrimination under the Equal Pay Act. Cf. Wheatley, 390 F.3d at 334 (a plaintiff may\\n\\nnot “indiscriminately aim at all department supervisors collectively, and then expect to\\n\\nmeet the EPA standard” for equal work).\\n\\n But even if Spencer could meet her initial burden, her claim would still fail\\n\\nbecause the University established that the salary difference was based on a “factor other\\n\\nthan sex.” 29 U.S.C. § 206(d)(1)(iv). As the defendant, the University bore the burden\\n\\nof establishing this affirmative defense. Maryland Ins. Admin., 879 F.3d at 120.\\n\\nGranting summary judgment on this ground required the district court to find that the\\n\\nproffered reason did in fact explain the wage disparity, not merely that it could. Id. at\\n\\n121.\\n\\n Here, there is no dispute that the wage difference at issue resulted from the\\n\\nUniversity setting Shackleford’s and Dial’s pay at 75% of their previous salaries as\\n\\nadministrators. In practice, the University generally paid former administrators who\\n\\n 9\\n\\fbecame professors “9/12ths” of their administrator salary. This practice appears to rest\\n\\non the theory that professors work nine months out of the year, while administrators work\\n\\nyear-round. Indeed, Spencer admits that her comparators’ pay during their short stints as\\n\\nUniversity professors was set according to the 9/12ths practice. Appellant’s Reply Brief\\n\\nat 16 (“Shackleford and Dial’s salaries were set entirely on their prior salaries as\\n\\nadministrators.”).\\n\\n In response to the University’s explanation, Spencer claims that the 9/12ths\\n\\npractice should not have been used to calculate Shackleford’s and Dial’s salaries.\\n\\nAccording to her, the University’s historical practice only applied to administrators who\\n\\nwere previously tenured faculty. But even if the University erroneously applied its\\n\\n9/12ths practice to overpay Shackleford and Dial, such an imprudent decision would still\\n\\nserve as a non-sex-based explanation for the pay disparity. See Anderson v.\\n\\nWestinghouse Savannah River Co., 406 F.3d 248, 272 (4th Cir. 2005) (“We do not sit as\\n\\na ‘super-personnel department weighing the prudence of employment decisions’ made by\\n\\nthe defendants.” (quoting DeJarnette v. Corning, Inc., 133 F.3d 293, 299 (4th Cir.\\n\\n1998)); Smith v. Univ. of North Carolina, 632 F.2d 316, 346 (4th Cir. 1980) (“[The] law\\n\\ndoes not require, in the first instance, that employment be rational, wise, or well-\\n\\nconsidered—only that it be nondiscriminatory.” (quoting Powell v. Syracuse Univ., 580\\n\\nF.2d 1150, 1156–57 (2d Cir. 1978)).\\n\\n The Equal Pay Act is a powerful tool, permitting an employee to prevail on a wage\\n\\ndiscrimination claim with no evidence of intentional discrimination. But this tool must\\n\\nbe tempered by adherence to its provisions. Doing so requires that the work performed\\n\\n 10\\n\\fby the plaintiff and her comparators be equal and that the wage disparity not be based on\\n\\na factor other than sex. Spencer’s claim fails on both requirements.\\n\\n II. Title VII\\n\\n Having rejected Spencer’s Equal Pay Act claim, we must separately consider her\\n\\nclaim of Title VII sex-based wage discrimination. Under Title VII of the Civil Rights\\n\\nAct of 1964, an employer cannot “discriminate against any individual with respect to\\n\\n[her] compensation . . . because of such individual’s . . . sex.” 42 U.S.C. § 2000e-2(a)(1).\\n\\nTitle VII, in contrast to the Equal Pay Act, requires establishing intentional\\n\\ndiscrimination. A Title VII plaintiff may make this showing of intentional discrimination\\n\\nusing direct or circumstantial evidence. Alternatively, the plaintiff may use the burden-\\n\\nshifting framework of McDonnell Douglas Corp. v. Green, 411 U.S. 792 (1973), “to\\n\\ndevelop an inferential case” of discriminatory intent. Chalmers v. Tulon Co. of\\n\\nRichmond, 101 F.3d 1012, 1017 (4th Cir. 1996).\\n\\n A prima facie pay-disparity case under McDonnell Douglas requires a plaintiff to\\n\\nestablish (1) she is a member of a protected class, (2) she was performing her job\\n\\nsatisfactorily, (3) an adverse employment action occurred, and (4) the circumstances\\n\\nsuggest an unlawfully discriminatory motive. See McDonnell Douglas, 411 U.S. at 802;\\n\\nTexas Dep’t of Cmty. Affairs v. Burdine, 450 U.S. 248, 253 (1981). Where, as here, the\\n\\nprima facie case of wage discrimination is based on comparators, the plaintiff must show\\n\\nthat she is paid less than men in similar jobs. See Brinkley-Obu v. Hughes Training, Inc.,\\n\\n36 F.3d 336, 343 (4th Cir. 1994).\\n\\n\\n\\n 11\\n\\f Title VII requires the compared jobs to be only “similar” rather than “equal,” as\\n\\nrequired under the Equal Pay Act. See id. While there is no bright-line rule for what\\n\\nmakes two jobs “similar” under Title VII, courts consider “whether the employees (i)\\n\\nheld the same job description, (ii) were subject to the same standards, (iii) were\\n\\nsubordinate to the same supervisor, and (iv) had comparable experience, education, and\\n\\nother qualifications—provided the employer considered these latter factors in making the\\n\\npersonnel decision.” Bio v. Fed. Express Corp., 424 F.3d 593, 597 (7th Cir. 2005)\\n\\n(internal quotation marks omitted); see also Herster v. Bd. of Supervisors of Louisiana\\n\\nState Univ., 887 F.3d 177, 185 (5th Cir. 2018) (stating that a “variety of factors are\\n\\nconsidered when determining whether a comparator is similarly situated, including job\\n\\nresponsibility, experience, and qualifications.”). While Title VII’s “similarity”\\n\\nrequirement demands less of plaintiffs than the Equal Pay Act’s “equality” requirement,\\n\\nit is not toothless: the plaintiff must provide evidence that the proposed comparators are\\n\\nnot just similar in some respects, but “similarly-situated in all respects.” Mitchell v.\\n\\nToledo Hosp., 964 F.2d 577, 583 (6th Cir. 1992). For the same reasons we discussed\\n\\nabove, Spencer’s broad generalizations cannot even show sufficient similarity to meet her\\n\\nburden under Title VII. 4\\n\\n\\n\\n\\n 4\\n Just as in the Equal Pay Act context, Spencer’s expert does not help her to\\nestablish a prima facie case here. While a plaintiff may use statistics to suggest a\\ndiscriminatory motive, Spencer’s expert found no statistical evidence that the University\\npaid women less than men.\\n\\n\\n 12\\n\\f Even if we concluded that Spencer had established a prima facie case of Title VII\\n\\nwage discrimination, her case still could not withstand summary judgment. Once a\\n\\nplaintiff establishes a prima facie case, the burden of production shifts to the employer to\\n\\nproffer a legitimate, nondiscriminatory explanation for the wage disparity. Guessous v.\\n\\nFairview Prop. Investments, LLC, 828 F.3d 208, 216–17 (4th Cir. 2016); Maryland Ins.\\n\\nAdmin., 879 F.3d at 120 n.7. Here, the University satisfies this requirement through its\\n\\npractice of paying administrators 9/12ths of their previous salary. Just as this practice\\n\\nsatisfies the Equal Pay Act’s “factor other than sex” affirmative defense, it qualifies as a\\n\\nlegitimate, nondiscriminatory explanation under Title VII. Cf. Cty. of Washington v.\\n\\nGunther, 452 U.S. 161, 169 (1981) (recognizing that the Bennett Amendment to Title VII\\n\\nincorporates the four affirmative defenses from the Equal Pay Act).\\n\\n Having proffered a nondiscriminatory explanation, the University shifts the burden\\n\\nback to Spencer to prove that the explanation is merely pretextual for invidious\\n\\ndiscrimination. Guessous, 828 F.3d at 216. Spencer cannot supply any evidence of this.\\n\\nSince the touchstone of discrimination is treating two groups differently based on\\n\\ncharacteristics only one possesses, it is vital for Spencer to provide evidence that the\\n\\nUniversity has used the 9/12ths policy to pay men more than women. Instead, Spencer\\n\\nmerely argues that the University misapplied the 9/12ths policy to Shackleford and Dial.\\n\\nBut again, even if the University “erroneously or even purposely misapplied the . . .\\n\\npolicy, it is not proof of unlawful discrimination.” Dugan v. Albemarle Cty. Sch. Bd.,\\n\\n293 F.3d 716, 722 (4th Cir. 2002).\\n\\n\\n\\n 13\\n\\f As a final note, Spencer also alleges that the University, and its former provost,\\n\\nengaged in unlawful retaliation because of her complaints about pay disparities. As the\\n\\ndistrict court noted, the facts supporting most of these allegations are exceedingly weak,\\n\\nand the allegations themselves are mostly conclusory. See Spencer v. Virginia State\\n\\nUniv., No. 3:16-cv-989, 2018 WL 627558, at *14–17 (E.D. Va. Jan. 30, 2018). Even if\\n\\nSpencer’s characterization of the behavior is accurate, Spencer offers insufficient\\n\\nevidence that each action was both material and undertaken because of her complaints\\n\\nabout salary equity. See Burlington N. & Santa Fe Ry. Co. v. White, 548 U.S. 53, 68\\n\\n(2006) (holding that “a plaintiff must show that a reasonable employee would have found\\n\\nthe challenged action materially adverse . . . [meaning] it might have ‘dissuaded a\\n\\nreasonable worker from making or supporting a charge of discrimination’”). That is not\\n\\nto say no one harbored animus toward Spencer, but a personal conflict alone does not\\n\\nconstitute retaliation. Cf. Hawkins v. PepsiCo, Inc., 203 F.3d 274, 281 (4th Cir. 2000)\\n\\n(“But Hawkins presents no facts that tend to show this allegedly disparate treatment was\\n\\ndue to race rather than Price’s admittedly low regard for Hawkins’ individual\\n\\nperformance.”). Because the district court correctly found that Spencer cannot establish a\\n\\nprima facie case of retaliation, we do not address the merits of the University’s defenses.\\n\\n Accordingly, the judgment of the district court is\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 14\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1069,"cells":{"id":{"kind":"number","value":4603789,"string":"4,603,789"},"name":{"kind":"string","value":"UNITED STATES of America, Plaintiff - Appellee, v. Justin Tyme HAWLEY, Defendant - Appellant."},"name_abbreviation":{"kind":"string","value":"United States v. Justin Hawley"},"decision_date":{"kind":"string","value":"2019-03-26"},"docket_number":{"kind":"string","value":"18-4167"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Wynn, Diaz, Richardson\", \"parties\": \"\", \"opinions\": [{\"author\": \"WYNN, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-4167\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\nv.\\n\\nJUSTIN TYME HAWLEY,\\n\\n Defendant - Appellant.\\n\\n\\nAppeal from the United States District Court for the Eastern District of North Carolina, at\\nRaleigh. Malcolm J. Howard, Senior District Judge. (5:17-cr-00219-H-1)\\n\\n\\nArgued: January 31, 2019 Decided: March 26, 2019\\n\\n\\nBefore WYNN, DIAZ, and RICHARDSON, Circuit Judges.\\n\\n\\nAffirmed by published opinion. Judge Wynn wrote the opinion, in which Judge Diaz\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4381042/\", \"author_raw\": \"WYNN, Circuit Judge:\"}, {\"author\": \"joined. Judge Richardson wrote an opinion concurring\", \"type\": \"concurrence\", \"text\": \"joined. Judge Richardson wrote an opinion concurring in part and concurring in the\\njudgment.\\n\\n\\nARGUED: Jaclyn L. DiLauro, OFFICE OF THE FEDERAL PUBLIC DEFENDER,\\nRaleigh, North Carolina, for Appellant. Kristine L. Fritz, OFFICE OF THE UNITED\\nSTATES ATTORNEY, Raleigh, North Carolina, for Appellee. ON BRIEF: G. Alan\\nDuBois, Federal Public Defender, OFFICE OF THE FEDERAL PUBLIC DEFENDER,\\nRaleigh, North Carolina, for Appellant. Robert J. Higdon, Jr., United States Attorney,\\nJennifer P. May-Parker, Assistant United States Attorney, OFFICE OF THE UNITED\\nSTATES ATTORNEY, Raleigh, North Carolina, for Appellee.\\n\\nWYNN, Circuit Judge:\\n\\n Defendant Justin Hawley pleaded guilty to two counts of being a felon in\\n\\npossession of a firearm and two counts of distributing heroin. The district court\\n\\nsentenced him to fifty-seven months’ imprisonment, in part because his criminal history\\n\\nincluded a prior sentence of thirty days’ imprisonment for an uncounseled misdemeanor\\n\\noffense. Defendant argues that the district court contravened the Sentencing Guidelines\\n\\nin calculating his criminal history by counting the prior uncounseled misdemeanor that\\n\\nresulted in imprisonment. Finding no reversible error, we affirm Defendant’s sentence.\\n\\n I.\\n\\n On August 8, 2017, a federal grand jury in the Eastern District of North Carolina\\n\\nreturned a superseding four-count indictment charging Defendant with: (1) two counts of\\n\\npossessing a firearm after being convicted of a crime punishable by imprisonment for a\\n\\nterm exceeding one year, in violation of 18 U.S.C. §§ 922(g)(1) & 924; and (2) two\\n\\ncounts of distributing heroin, a Schedule I controlled substance, in violation of 21 U.S.C.\\n\\n§ 841(a)(1). Thereafter, on November 6, 2017, Defendant pleaded guilty to all four\\n\\ncounts.\\n\\n On March 7, 2018, the district court conducted a sentencing hearing. Before\\n\\nsentencing, the United States Probation Office prepared a presentence report that\\n\\ncalculated the Defendant’s offense level and criminal history category. The Probation\\n\\nOffice first determined that Defendant had an offense level of 19. Next, considering\\n\\nDefendant’s prior offenses, the Probation Office determined that Defendant had a\\n\\ncriminal history score of 10, and thus Defendant had a criminal history category of V. As\\n\\n 2\\n\\nrelevant here, the Probation Office added one point to Defendant’s criminal history score\\n\\nbecause Defendant pleaded guilty in April 2015 to the misdemeanor offense of providing\\n\\nfalse information to a police officer and failure to wear a seatbelt. Defendant did not\\n\\ndispute—and therefore conceded for purposes of this appeal—that he validly waived his\\n\\nright to counsel in the proceedings giving rise to that conviction and that he was\\n\\nimprisoned for thirty days. Because Defendant had an offense level of 19 and a criminal\\n\\nhistory category of V, the Guidelines’ advisory sentencing range was fifty-seven to\\n\\nseventy-one months’ imprisonment for each of the four counts.\\n\\n At his sentencing hearing, Defendant objected to adding a criminal history point\\n\\nfor the misdemeanor offense of providing false information to a police officer.\\n\\nDefendant argued that because he was uncounseled—albeit voluntarily—and was\\n\\nimprisoned, the Guidelines precluded the district court from adding a point for that\\n\\noffense. To support this position, Defendant relied upon the Guidelines background\\n\\ncommentary, which provides: “[p]rior sentences, not otherwise excluded, are to be\\n\\ncounted in the criminal history score, including uncounseled misdemeanor sentences\\n\\nwhere imprisonment was not imposed.” U.S.S.G. § 4A1.2 (background) (emphasis\\n\\nadded). Without this additional point, Defendant would have had a criminal history score\\n\\nof 9 and a criminal history category of IV, and the Guidelines’ advisory sentencing range\\n\\nwould be forty-six to fifty-seven months’ imprisonment.\\n\\n At sentencing, the district court adopted the Probation Office’s recommendation\\n\\nand rejected Defendant’s reading of the background commentary. The court reasoned\\n\\nthat the Guidelines required it to count the offense of providing false information to a\\n\\n 3\\n\\npolice officer because Defendant was sentenced to a term of imprisonment of at least\\n\\nthirty days. See U.S.S.G. § 4A1.2(c)(1). And though the background commentary\\n\\nexplicitly contemplates counting prior uncounseled misdemeanors for which\\n\\n“imprisonment was not imposed,” this reference is preceded by the word “including,”\\n\\nindicating that the Guidelines do not exclude counting other valid convictions, like\\n\\nDefendant’s voluntarily uncounseled misdemeanor which resulted in imprisonment.\\n\\nThus, because Defendant was imprisoned for thirty days after pleading guilty to\\n\\nproviding false information to a police officer, the court added one point for that offense.\\n\\nThereafter, the court concurrently sentenced Defendant on all four counts to fifty-seven\\n\\nmonths’ imprisonment—the bottom of the Guidelines’ advisory range. Defendant timely\\n\\nappealed.\\n\\n II.\\n\\n Before this Court, Defendant solely contends * that the district court misapplied the\\n\\nGuidelines in calculating his criminal history by counting his prior uncounseled\\n\\nmisdemeanor that resulted in 30-days imprisonment.\\n\\n\\n\\n\\n *\\n In his brief, Defendant also argued that the district court erred by adding three\\ncriminal history points for each of Defendant’s prior state convictions of possessing a\\nstolen firearm and of breaking or entering and conspiracy to commit breaking or entering\\nof a building with intent to commit a felony or larceny. According to Defendant, the\\ncourt erroneously considered the statutory post-supervisory release period in determining\\nwhether a conviction constitutes a term of imprisonment exceeding one year. U.S.S.G.\\n§§ 4A1.1 & 4A1.2. But Defendant recognized that this position was foreclosed by\\nUnited States v. Barlow, 811 F.3d 133 (4th Cir. 2015), and thus withdrew this contention\\nat oral argument. Oral Argument at 8:50–9:00.\\n\\n 4\\n\\n “On a challenge to a district court’s application of the Guidelines, we review\\n\\nquestions of law de novo and findings of fact for clear error.” United States v. Allen, 909\\n\\nF.3d 671, 677 (4th Cir. 2018) (citation omitted). In doing so, we discern the Guidelines’\\n\\n“plain meaning, as determined by examination of its language, structure, and purpose.”\\n\\nUnited States v. Strieper, 666 F.3d 288, 293–94 (4th Cir. 2012) (citations and alterations\\n\\nomitted). “As in all cases of statutory interpretation, our inquiry begins with the text of\\n\\nthe statute.” United States v. Ashford, 718 F.3d 377, 382 (4th Cir. 2013) (citation\\n\\nomitted). We consider not only the Guidelines’ text, but also the “commentary [which]\\n\\nexplains the guidelines and provides concrete guidance as to how even unambiguous\\n\\nguidelines are to be applied in practice.” Stinson v. United States, 508 U.S. 36, 44\\n\\n(1993). And when the Guidelines provide “commentary [that] interprets a guideline\\n\\nprovision or explains how a guideline is to be applied, the commentary is controlling . . .\\n\\nunless it: [1] violates the Constitution or a federal statute; [2] is inconsistent with the\\n\\nGuidelines; or [3] constitutes a plainly erroneous reading of the Guidelines.” Allen, 909\\n\\nF.3d at 674 (internal quotation marks omitted) (quoting Stinson, 508 U.S. at 37–38).\\n\\n When computing a defendant’s criminal history for sentencing, the Guidelines\\n\\nrequire the district court to count certain prior misdemeanor offenses, including\\n\\nDefendant’s prior offense of providing false information to a police officer, “only if (A)\\n\\nthe sentence was a term of probation of more than one year or a term of imprisonment of\\n\\nat least thirty days, or (B) the prior offense was similar to an instant offense.” U.S.S.G.\\n\\n§ 4A1.2(c)(1). Defendant does not dispute that he was imprisoned for thirty days after\\n\\npleading guilty to the misdemeanor offense of providing false information to a police\\n\\n 5\\n\\nofficer. Thus, under the plain language of Guideline 4A1.2(c)(1), Defendant’s offense\\n\\nshould be counted in calculating Defendant’s prior criminal history. See id.\\n\\n Nevertheless, Defendant argues that the district court erred in counting his\\n\\nuncounseled misdemeanor offense resulting in 30-days imprisonment because a\\n\\n“background” statement in the Guidelines commentary states that when courts count\\n\\nprior offenses, “[p]rior sentences, not otherwise excluded, are to be counted in the\\n\\ncriminal history score, including uncounseled misdemeanor sentences where\\n\\nimprisonment was not imposed.” U.S.S.G. § 4A1.2 (background) (emphases added).\\n\\nAppealing to the interpretive canon expressio unius est exclusio alterius, Defendant\\n\\nmaintains that the negative implication of Guideline 4A1.2’s background commentary\\n\\nbarred the district court from counting prior uncounseled misdemeanor convictions for\\n\\nwhich imprisonment was imposed—even when, as here, a defendant validly waives his\\n\\nright to counsel.\\n\\n Under the expressio unius canon, “expressing one item of an associated group or\\n\\nseries excludes another left unmentioned.” N.L.R.B. v. SW Gen., Inc., 137 S. Ct. 929, 940\\n\\n(2017) (citation and alterations omitted). Though this canon can be an instructive tool for\\n\\ndiscerning legislative intent, the “force of any negative implication . . . depends on\\n\\ncontext.” Id. (citation omitted). Therefore, the “expressio unius canon applies only when\\n\\ncircumstances support a sensible inference that the term left out must have been meant to\\n\\nbe excluded.” Id. (citation and alterations omitted). The Guidelines do not support such\\n\\nan inference in this case.\\n\\n\\n\\n 6\\n\\n Here, the background commentary provides a general rule that prior sentences are\\n\\nto be counted if they are “not otherwise excluded.” U.S.S.G. § 4A1.2 (background).\\n\\nAlthough the background commentary identifies a specific application of this general\\n\\nrule—that uncounseled misdemeanors for which imprisonment was not imposed are to be\\n\\ncounted—that specific application is preceded by the word “including.” Id. (emphasis\\n\\nadded). And “the term ‘including’ is not one of all-embracing definition, but connotes\\n\\nsimply an illustrative application of the general principle.” Fed. Land Bank of St. Paul v.\\n\\nBismarck Lumber Co., 314 U.S. 95, 100 (1941) (quoting Phelps Dodge Corp. v. N.L.R.B.,\\n\\n313 U.S. 177, 189 (1941)). In other words, the term “including” as used here is an\\n\\n“introductory term for an incomplete list of examples.” Adams v. Dole, 927 F.2d 771,\\n\\n776 (4th Cir. 1991) (emphasis added); see Include, Black’s Law Dictionary 880 (10th ed.\\n\\n2009) (“The participle including typically indicates a partial list . . . .”). Because the\\n\\nbackground commentary, by its plain language, contemplates that it is providing a non-\\n\\nexhaustive list, an inference of negative implication is inappropriate. See Jones v. Am.\\n\\nPostal Workers Union, 192 F.3d 417, 426 (4th Cir. 1999) (“When ‘include’ is utilized in\\n\\na statute, it is generally improper to conclude that entities not specifically enumerated are\\n\\nexcluded.” (alterations omitted) (quoting 2A Norman J. Singer, Sutherland Stat. Const.\\n\\n§ 47.23 (5th ed. 1992))).\\n\\n It is interesting to note that the regulatory history of the Sentencing Commission\\n\\nsupports our determination of this issue. In February 1990, when the Sentencing\\n\\nCommission first proposed including background commentary to the relevant guideline,\\n\\nit explained that its intention was to make clear that “all sentences resulting from\\n\\n 7\\n\\nconstitutionally valid convictions . . . are counted.” Sentencing Guidelines for United\\n\\nStates Courts, 55 Fed. Reg. 5718, 5741 (proposed Feb. 16, 1990) (emphasis added).\\n\\nAdditionally, excluding “prior sentences resulting from constitutionally valid convictions\\n\\non the basis of whether the convictions were counseled or uncounseled would create wide\\n\\ndisparity . . . [and] would deprive the court of significant information relevant to the\\n\\npurposes of sentencing.” Id. Notably, the Commission provided the specific application\\n\\nof this general rule relied on by Defendant to make clear that the Commission “d[id] not\\n\\nbelieve the inclusion of sentences resulting from constitutionally valid, uncounseled\\n\\nmisdemeanor convictions in the criminal history score [wa]s foreclosed by Baldasar v.\\n\\nIllinois, 446 U.S. 222 (1980),” id.—a Supreme Court opinion which was subsequently\\n\\noverruled, see Nichols v. United States, 511 U.S. 738, 748 (1994). Though the language\\n\\nof the background commentary was modified before its enactment in November 1990,\\n\\nthe Commission reemphasized its intention to avoid “considerable disparity in guideline\\n\\napplication” and to count those misdemeanor convictions “for which counsel\\n\\nconstitutionally is not required.” U.S. Sentencing Guidelines Manual app. C, amend. 353\\n\\n(1990). Accordingly, because Defendant voluntarily proceeded without counsel in the\\n\\nprior proceeding—meaning that Defendant’s constitutional right to counsel was not\\n\\nabridged and, therefore, that his misdemeanor conviction was “constitutionally valid”—\\n\\nthe district court did not err in counting the prior misdemeanor conviction in determining\\n\\nDefendant’s Guidelines’ advisory range.\\n\\n Defendant’s voluntary waiver of his right to counsel in the prior proceeding also\\n\\nsets this case apart from the principal decision upon which Defendant relies—the Second\\n\\n 8\\n\\nCircuit’s decision in United States v. Ortega, 94 F.3d 764 (2d Cir. 1996). Defendant\\n\\nemphasizes that Ortega stated that “[a]lthough the [background commentary] does not\\n\\nexpressly exclude uncounseled misdemeanor sentences in which imprisonment was\\n\\nimposed, the interpretive maxim expressio unius est exclusion alterius, coupled with the\\n\\nconstitutional problems raised by such sentences, convinces us that [the background\\n\\ncommentary] excludes from criminal history computations all uncounseled misdemeanor\\n\\nsentences of imprisonment, including those imposed after the revocation of a defendant’s\\n\\nprobation.” Id. at 770–71 (emphases added). But in Ortega the government “d[id] not\\n\\ncontest” the defendants’ assertions that they were imprisoned and “unavailingly sought”\\n\\nthe assistance of counsel. Id. at 769. Of course, under the Sixth and Fourteenth\\n\\nAmendments, “absent a knowing and intelligent waiver, no person may be imprisoned for\\n\\nany offense . . . unless he was represented by counsel at his trial.” Argersinger v.\\n\\nHamlin, 407 U.S. 25, 37 (1972). Unlike Ortega, Defendant does not contest the\\n\\nconstitutional validity of his waiver of the right to counsel in the prior proceeding. See\\n\\nOral Argument at 2:55–3:00, 5:20–5:25. And if Defendant did contest the constitutional\\n\\nvalidity of his prior waiver, he could have collaterally attacked that waiver in the instant\\n\\nsentencing proceeding. See United States v. Hondo, 366 F.3d 363, 365 (4th Cir. 2004);\\n\\nsee also Custis v. United States, 511 U.S. 485, 496 (1994). Accordingly, this case does\\n\\nnot invoke the “constitutional problems” that the Second Circuit confronted in Ortega.\\n\\nPut simply, Ortega is inapposite. Accord United States v. Feliciano, 498 F.3d 661, 666\\n\\n(7th Cir. 2007); United States v. Fitch, 39 F. App’x 518, 520 (9th Cir. 2002)\\n\\n(unpublished).\\n\\n 9\\n\\n III.\\n\\n In sum, the district court properly counted Defendant’s prior voluntarily\\n\\nuncounseled misdemeanor offense of providing false information to a police officer for\\n\\nwhich he was sentenced to thirty days’ imprisonment. Accordingly, we affirm\\n\\nDefendant’s sentence.\\n\\n AFFIRMED\\n\\n\\n\\n\\n 10\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4381042/\", \"author_raw\": \"joined. Judge Richardson wrote an opinion concurring\"}, {\"author\": \"RICHARDSON, Circuit Judge, concurring\", \"type\": \"concurrence\", \"text\": \"RICHARDSON, Circuit Judge, concurring in part and concurring in the judgment:\\n\\n I enthusiastically join my good colleague’s opinion except for the analysis of\\n\\nregulatory history. That analysis relies substantially on language in the draft background\\n\\ncommentary initially proposed by the Commission. Ante at 7–8. After receiving\\n\\ncomments, the Commission discarded that proposed background commentary and\\n\\nadopted different language. Compare 55 Fed. Reg. 5718, 5741 (Feb. 16, 1990) (notice of\\n\\nproposed amendments), with 55 Fed. Reg. 19,188, 19,204–05 (May 8, 1990)\\n\\n(amendments submitted to Congress). That initial, unadopted background commentary\\n\\nprovides no reliable interpretative guidance. What is more, the passing paragraph\\n\\ndiscussing it is unnecessary given the rest of my friend’s analysis. So I join only the rest\\n\\nof the opinion.\\n\\n\\n\\n\\n 11\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4381042/\", \"author_raw\": \"RICHARDSON, Circuit Judge, concurring\"}]}"},"judge1":{"kind":"string","value":"WYNN"},"judge2":{"kind":"string","value":"DIAZ"},"judge3":{"kind":"string","value":"RICHARDSON"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":3,"string":"3"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":2,"string":"2"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4603789/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Plaintiff - Appellee, v. Justin Tyme HAWLEY, Defendant - Appellant.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-03-26\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: Yes\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-4167\n\n\nUNITED STATES OF AMERICA,\n\n Plaintiff - Appellee,\n\nv.\n\nJUSTIN TYME HAWLEY,\n\n Defendant - Appellant.\n\n\nAppeal from the United States District Court for the Eastern District of North Carolina, at\nRaleigh. Malcolm J. Howard, Senior District Judge. (5:17-cr-00219-H-1)\n\n\nArgued: January 31, 2019 Decided: March 26, 2019\n\n\nBefore WYNN, DIAZ, and RICHARDSON, Circuit Judges.\n\n\nAffirmed by published opinion. Judge Wynn wrote the opinion, in which Judge Diaz\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Plaintiff - Appellee, v. Justin Tyme HAWLEY, Defendant - Appellant.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-03-26\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: Yes\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-4167\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\nv.\\n\\nJUSTIN TYME HAWLEY,\\n\\n Defendant - Appellant.\\n\\n\\nAppeal from the United States District Court for the Eastern District of North Carolina, at\\nRaleigh. Malcolm J. Howard, Senior District Judge. (5:17-cr-00219-H-1)\\n\\n\\nArgued: January 31, 2019 Decided: March 26, 2019\\n\\n\\nBefore WYNN, DIAZ, and RICHARDSON, Circuit Judges.\\n\\n\\nAffirmed by published opinion. Judge Wynn wrote the opinion, in which Judge Diaz\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1070,"cells":{"id":{"kind":"number","value":4604190,"string":"4,604,190"},"name":{"kind":"string","value":"UNITED STATES of America, Plaintiff - Appellee, v. Michael SMITH, Jr., A/K/A Mikey, A/K/A Lil Mike, A/K/A Mik, Defendant - Appellant. United States of America, Plaintiff - Appellee, v. Mark Bazemore, A/K/A Uncle Mark, Defendant - Appellant. United States of America, Plaintiff - Appellee, v. Timothy Hurtt, A/K/A Uncle Tim, A/K/A Tim, Defendant - Appellant."},"name_abbreviation":{"kind":"string","value":"United States v. Michael Smith"},"decision_date":{"kind":"string","value":"2019-03-27"},"docket_number":{"kind":"string","value":"16-4746; 16-4764; 16-4765"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Niemeyer, Thacker, Richardson\", \"parties\": \"\", \"opinions\": [{\"author\": \"RICHARDSON, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 16-4746\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\n v.\\n\\nMICHAEL SMITH, JR., a/k/a Mikey, a/k/a Lil Mike, a/k/a Mik,\\n\\n Defendant - Appellant.\\n\\n\\n No. 16-4764\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\n v.\\n\\nMARK BAZEMORE, a/k/a Uncle Mark,\\n\\n Defendant - Appellant.\\n\\n\\n No. 16-4765\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\n v.\\n\\fTIMOTHY HURTT, a/k/a Uncle Tim, a/k/a Tim,\\n\\n Defendant - Appellant.\\n\\n\\nAppeals from the United States District Court for the District of Maryland, at Baltimore.\\nJames K. Bredar, Chief District Judge. (1:14-cr-00479-JKB-8; 1:14-cr-00479-JKB-11;\\n1:14-cr-00479-JKB-17)\\n\\n\\nArgued: October 30, 2018 Decided: March 27, 2019\\n\\n\\nBefore NIEMEYER, THACKER, and RICHARDSON, Circuit Judges.\\n\\n\\nAffirmed by published opinion. Judge Richardson wrote the opinion, in which Judge\\nNiemeyer and Judge Thacker concurred.\\n\\n\\nARGUED: Michael Daniel Montemarano, MICHAEL D. MONTEMARANO, PA,\\nEllicott City, Maryland; Charles Burnham, BURNHAM & GOROKHOV PLLC,\\nWashington, D.C., for Appellants. David Daniel Metcalf, OFFICE OF THE UNITED\\nSTATES ATTORNEY, Baltimore, Maryland, for Appellee. ON BRIEF: Harry D.\\nMcKnett, LAW OFFICE OF HARRY D. MCKNETT, LLC, Columbia, Maryland, for\\nAppellant Michael Smith, Jr. Stephen M. Schenning, Acting United States Attorney,\\nJames Wallner, Assistant United States Attorney, OFFICE OF THE UNITED STATES\\nATTORNEY, Baltimore, Maryland, for Appellee.\\n\\n\\n\\n\\n 2\\n\\fRICHARDSON, Circuit Judge:\\n\\n Defendants Mark Bazemore, Michael Smith, Jr., and Timothy Hurtt participated in\\n\\nthe illegal activities of a Baltimore street and prison gang known as the Black Guerrilla\\n\\nFamily. Their involvement in the gang’s drug dealing and acts of violence led to their\\n\\nconvictions. The Defendants seek to reverse those convictions for two main reasons.\\n\\nFirst, they argue the district court improperly handled the fears some jurors expressed to\\n\\nthe court after learning of this gang’s predilection for violence and retaliation. Second,\\n\\nthey claim the district court should have excluded an FBI agent’s expert testimony\\n\\ndecoding intercepted calls. We reject their challenges.\\n\\n I.\\n\\n A. Factual Background\\n\\n Bazemore, Smith, and Hurtt were high-ranking members of the Black Guerilla\\n\\nFamily, a criminal gang founded in the 1960s in California’s San Quentin State Prison.\\n\\nThe gang moved across the country, establishing itself in Maryland’s prison system\\n\\nbefore expanding to the streets of Baltimore.\\n\\n The gang organized itself into subsets called “regimes” that controlled the drug\\n\\ntrade in Maryland state prisons and in dozens of Baltimore neighborhoods. Each regime\\n\\nwas overseen by a “bushman,” often referred to as “Uncle” or “Unc.” In leading a\\n\\nregime, the bushman collected dues, settled disputes, and enforced protocol by ordering\\n\\n\\n\\n\\n 3\\n\\fsanctions ranging from fines to death against members who broke the gang’s many\\n\\nrules. 1\\n\\n Troubled by the gang’s criminal activities, the FBI undertook a broad investigation\\n\\ninto the Black Guerilla Family’s Baltimore operations. They wiretapped the phone of the\\n\\ngang’s city-wide commander, Timothy Michael Gray, along with dozens of phones used\\n\\nby other gang members (including Defendants Bazemore and Hurtt). The FBI’s\\n\\ninvestigation exposed the gang’s sprawling drug business, documenting forty Baltimore\\n\\nlocations where the gang distributed heroin and cocaine. With these drug profits at stake,\\n\\nthe gang often turned to violence to protect its territory.\\n\\n Along with violently protecting their drug trade, the gang’s leaders had a penchant\\n\\nfor killing their subordinates that broke protocol. For instance, Bazemore ordered the\\n\\nmurders of members George Nealy and Ronald Hall. Of all the gang’s violence, the\\n\\nattempted murder of Hall bears most directly on this appeal. On March 10, 2014,\\n\\nBazemore ordered gang member William “Boosie” Harrington to kill Hall for allegedly\\n\\n 1\\n Black Guerilla Family members adhered to official bylaws and upon initiation\\nswore to the following oath:\\n\\n Should ever I be untrue and forsake the chosen few, this oath shall kill me.\\n Should ever I become lax in discipline at times of strife and neglect my\\n brother, this oath shall kill me.\\n If ever I sought to do harm or allow harm to come to my brothers, this oath\\n shall kill me.\\n If ever I refuse or deny to give assistance to [] or reject my brother, this\\n oath shall kill me.\\n If ever I fail the sworn secrecies of this oath, this oath shall kill me.\\n\\nJ.A. 839–40; see J.A. 670, 843.\\n\\n\\n 4\\n\\flying to the gang’s leadership. Shortly before the shooting, Bazemore and Harrington\\n\\nspoke twice by telephone. The first call took place at 3:50 PM when Harrington asked to\\n\\nconfirm the order:\\n\\n Bazemore: “Yo.”\\n Harrington: “Hey, Unc, what’s up baby?\\n Bazemore: “What’s good?”\\n Harrington: “Listen to me real carefully.”\\n Bazemore: “Uh huh.”\\n Harrington: “I’m around Lil Shorty, you heard me?”\\n Bazemore: “Yeah.”\\n Harrington: “The one you always wanted me to holler at.”\\n Bazemore: “Right.”\\n Harrington: “I’m out Lakeland.”\\n Bazemore: “Right.”\\n Harrington: “Is that special light still good, good?”\\n ...\\n Harrington: “I got him right here.”\\n Bazemore: “Matter fact, don’t worry about it, don’t worry about it. I’m\\n holler at you on the close up about that one.”\\n\\nS.J.A. 122. One minute later, Harrington again called Bazemore and said, “Unc I’m in\\n\\nhis bushes. Like right now, it’d be easy and I’d be out of here, you feel me?” S.J.A. 124.\\n\\nBazemore replied with the authorization: “Alright, so go ahead then. Go ahead and do it\\n\\nthen.” Id.\\n\\n FBI Special Agent Mark James monitored these wiretapped conversations in real-\\n\\ntime. Understanding Bazemore’s order to kill, Agent James alerted local police that an\\n\\nact of violence was about to occur in South Baltimore’s Lakeland neighborhood.\\n\\nBaltimore Police arrived at the scene to find Hall with gunshot wounds to his arms and\\n\\ntorso. After he was rushed to the hospital, Hall survived.\\n\\n\\n\\n\\n 5\\n\\f Three weeks after shooting Hall, Harrington was arrested and detained by state\\n\\nauthorities for attempted murder. In jail, Harrington faced violent retaliation from other\\n\\nincarcerated Black Guerilla Family members for shooting their fellow gang member,\\n\\nHall. In hopes of avoiding attack, Harrington placed several calls from a jail telephone\\n\\nseeking to “get in touch with Uncle Mark” to prove he acted with Mark Bazemore’s go-\\n\\nahead. S.J.A. 067. When Harrington finally reached Bazemore, he passed the phone to a\\n\\nfellow inmate after telling Bazemore that “[t]his [is] another good soldier here that\\n\\nwanted to holler at you.” J.A. 1013. Bazemore then confirmed to the other inmate that\\n\\nhe authorized Harrington to shoot Hall: “What Boosie [Harrington] did to him came\\n\\nstraight from the head. It came from me. I told him do that and he can do that.” J.A.\\n\\n1014.\\n\\n B. The Trial\\n\\n The Defendants, along with 15 other members of the gang, faced federal charges\\n\\nfor conspiring to participate in a racketeering enterprise (18 U.S.C. § 1962(d)) and for\\n\\nconspiring to distribute drugs (21 U.S.C. § 846). 2 Bazemore was also charged with\\n\\nattempted murder and conspiracy to commit murder in aid of racketeering (18 U.S.C.\\n\\n§ 1959(a)(5)). And Bazemore and Hurtt were charged with conspiring to use a firearm in\\n\\nrelation to the racketeering and drug conspiracies (18 U.S.C. § 924(o)). After their co-\\n\\ndefendants all pleaded guilty, Bazemore, Smith, and Hurtt stood trial in May 2016.\\n\\n\\n 2\\n Harrington pleaded guilty to the racketeering conspiracy and, after stipulating to\\nhis involvement in the shooting of Hall as an act in furtherance of the conspiracy,\\nreceived 151 months in prison.\\n\\n 6\\n\\f Over the course of a month, the Government proved the racketeering, drug,\\n\\nattempted murder, and firearm offenses through three main sources of evidence. First,\\n\\nlaw enforcement officials (including Agent James) testified about their investigation.\\n\\nSecond, seven cooperating gang members described the gang’s organization and criminal\\n\\nactivities. And third, recordings of wiretapped and jailhouse telephone calls confirmed\\n\\nthe law enforcement and cooperator testimony.\\n\\n The trial evidence highlighted the gang’s violent nature. This caused anxiety for\\n\\nsome members of the jury. On the third day, Juror No. 5 notified the court that she was\\n\\nafraid. In a sealed hearing, Juror No. 5 explained that she had revealed during jury\\n\\nselection her husband’s exact employment location. In sharing that information at side-\\n\\nbar, Juror No. 5 had mistakenly assumed that the Defendants were unable to hear her.\\n\\nHaving realized her mistake, she explained, “[i]f these people are the people that the\\n\\n[Government] contends, and if the jury comes back with a guilty verdict, [] it would be\\n\\nvery easy if they had retaliation on their mind” to use the information shared to obtain her\\n\\nfamily’s address. J.A. 1241. After Juror No. 5 voiced doubt that she could remain fair\\n\\nand impartial, the district court excused her.\\n\\n The district court also asked Juror No. 5 whether she had discussed her fears with\\n\\nother jurors, and she replied that she had spoken with “a Jim, a Jimmy, and a Mike.” J.A.\\n\\n1246. Based on the possibility that her discussions might have contaminated the entire\\n\\njury, the Defendants moved for a mistrial.\\n\\n Rather than grant the requested mistrial, the district court devised two questions to\\n\\nask each juror to probe for impartiality, bias, or contamination:\\n\\n 7\\n\\f Question 1: When we last spoke during the jury selection process, you told\\n me that you believed that you could be a fair and impartial juror. Has\\n anything occurred since we last spoke that would cause you to change your\\n answer to that question?\\n\\n Question 2: Since you began to serve on the jury, has anything been said or\\n overheard by you in the jury room that would affect your ability to be a fair\\n and impartial juror?\\n\\nJ.A. 1254–55. In response, all but two jurors confirmed that they could remain fair and\\n\\nimpartial.\\n\\n The first juror who expressed apprehension about being fair was Juror No. 10. He\\n\\nexplained that “the nature of the case” made him scared for himself and his family. The\\n\\ndistrict court noted that “the juror became emotional and . . . was crying or nearly crying\\n\\nand struggling to control his emotions” during the questioning. J.A. 1292–95. Doubting\\n\\nthat Juror No. 10 could be fair and impartial, the court excused him for cause.\\n\\n The second juror voicing concern about her ability to remain impartial was\\n\\nAlternate Juror No. 4. Much like Juror No. 5, Alternate Juror No. 4 expressed concern\\n\\nbecause she now realized that the Defendants could hear the details she shared during\\n\\njury selection. As a result, she explained that she feared being recognized by gang\\n\\nmembers on the streets of Baltimore. J.A. 1307. The district court then excused\\n\\nAlternate Juror No. 4 for cause.\\n\\n After the three jurors were excused, twelve jurors and one alternate remained. The\\n\\ndistrict court denied the Defendants’ renewed request for a mistrial, finding that its\\n\\nquestioning “did not detect any contamination or something untoward, rampant, or even\\n\\nrunning among the remaining jurors.” J.A. 1318–19.\\n\\n\\n 8\\n\\f When the trial resumed, the Government called Gray, the head of the Baltimore\\n\\ngang. Gray testified at length about the gang’s operations and explained several\\n\\nwiretapped calls coordinating its various illegal activities. As part of his testimony\\n\\nhighlighting the gang’s extensive reach throughout Maryland, Gray implicated Bazemore\\n\\nas the bushman who ordered Harrington to kill Hall. See J.A. 571–85 (expounding upon\\n\\na call between Gray and Bazemore).\\n\\n Having heard from Gray, the Government sought to use several recorded calls to\\n\\nconfirm that Bazemore authorized Harrington to kill Hall. Most of the recorded\\n\\nconversations took place in code—an assortment of slang, nicknames, and substituted\\n\\nwords meant to prevent an outside listener from deciphering their meaning. So the\\n\\nGovernment re-called Agent James to provide expert interpretations of the calls. 3 After\\n\\nAgent James was qualified as an expert in drug and gang terminology in Maryland, he\\n\\nexplained the meanings of several coded terms.\\n\\n Agent James’s explanations began with the call from March 10, 2014, at 3:50 PM,\\n\\nin which Harrington asked Bazemore if the “special light” remained good. Agent James\\n\\ndescribed that the term “Unc” meant a bushman in the Black Guerrilla Family. Before\\n\\nAgent James could give his expert opinion on the meaning of “special light,” the\\n\\nDefendants objected, expecting that the testimony would conflate expert interpretation\\n\\nwith factual analysis. The district court permitted Agent James to opine that he\\n\\n 3\\n Agent James testified earlier in the trial as a fact witness to describe the FBI\\ninvestigation and its use of wiretaps, controlled drug buys, and other investigatory\\ntechniques.\\n\\n\\n 9\\n\\finterpreted “special light” as a “green light,” which is an “authorization used by gang\\n\\nmembers . . . to kill another person.” J.A. 971. Agent James testified that he based his\\n\\ninterpretation on the context, other incidents in the investigation, and debriefings from\\n\\nother gang investigations he had done. Agent James was not permitted to interpret\\n\\nBazemore’s next statement—“don’t worry about it.” The Government then played,\\n\\nwithout interpretation, the very next call in which Bazemore gave Harrington the “go\\n\\nahead” to “do it.”\\n\\n After that call was played, Agent James described to the jury the steps he took to\\n\\nalert the Baltimore Police. The district court permitted this limited factual testimony over\\n\\nthe Defendants’ objection to what they called an improper “blurring of lines” between\\n\\nexpert and factual testimony. 4\\n\\n Once Agent James explained how Baltimore Police received the information, the\\n\\nGovernment called Detective David Bomenka, who had responded to the scene.\\n\\nDetective Bomenka testified that on the afternoon of March 10, 2014, he arrived in\\n\\nLakeland to find Hall shot and shell casings on the ground.\\n\\n Agent James then re-took the stand to continue in his role as expert witness. He\\n\\ninterpreted several of Harrington’s jail calls with other gang members, including\\n\\n\\n 4\\n Throughout the trial, the district court worked to maintain clarity and avoid\\nconflating expert and lay testimony, admonishing the Government “to be very careful in\\nyour questioning to make it crystal clear that you are asking for the agent’s interpretation\\nof the language … and not [permit the agent] to stray into offering opinions more broadly\\nabout what the plotters and schemers are up to.” J.A. 1004; see also J.A. 965D (“I want a\\nreally crisp line drawn between his testimony as an expert witness and his testimony as a\\nfact witness.”).\\n\\n 10\\n\\fBazemore, about the authorization to shoot Hall. At the end of Agent James’s direct\\n\\ntestimony, the district court gave to the jury a long cautionary instruction emphasizing the\\n\\nimportance of separating fact testimony from expert opinions. 5 The Defendants declined\\n\\nto cross-examine Agent James.\\n\\n\\n\\n 5\\n The district court’s cautionary instruction read:\\n\\n Ladies and gentlemen, Special Agent James has testified on two separate\\n occasions during this trial. During his initial testimony, Special Agent\\n James provided fact testimony, but as I instructed you during his second\\n time on the stand today, I instructed you that Special Agent James today\\n was permitted to give opinion testimony regarding drug and gang\\n terminology that may have been present in the phone calls that you’ve just\\n heard. I caution you that during his second time on the stand, Special\\n Agent James was providing only his opinion as an expert as to the\\n substance of those calls and phrases. The fact that he also possesses factual\\n information regarding this case should not be taken into account by you as\\n you determine what, if any, weight to decide to give Special Agent James’s\\n expert opinions. It’s for you to decide how much weight to give all of the\\n evidence, including fact and opinion testimony. Special Agent James's\\n testimony as a fact or expert witness is entitled to no greater or lesser\\n weight simply because he is an expert in one context and was previously\\n qualified to do so.\\n\\n You’ve just heard extensive testimony from Agent James. Agent James\\n was called and qualified and permitted to testify as an expert witness. His\\n field of expertise was drug and gang terminology in Maryland. Within that\\n zone of expertise, Agent James was permitted to offer you his opinions.\\n Specifically, he was allowed to tell you his interpretations based on his\\n training and experience as to the meaning of statements made by alleged\\n members of the Black Guerilla Family during telephone calls. You are\\n permitted to give Agent James’s expert opinions on the meaning of drug\\n and gang terminology, such weight as you may think they deserve.\\n\\n Ladies and gentlemen, I draw a distinction between the opinion testimony\\n about drug and gang terminology, and any more traditional fact testimony\\n that Agent James may have given earlier in this trial. During his previous\\n(Continued)\\n 11\\n\\f The jury convicted the Defendants on all charges. The jury specifically found\\n\\nBazemore and Hurtt responsible for multiple acts of first-degree murder, attempted\\n\\nmurder, conspiracy to commit murder, extortion, witness retaliation, and drug distribution\\n\\nas part of the racketeering conspiracy. S.J.A. 49, 53. The jury found Smith responsible\\n\\nfor extortion and drug distribution under the racketeering conspiracy. S.J.A. 56. The\\n\\ndistrict court sentenced Bazemore to life, Hurtt to 324 months, and Smith to 210 months.\\n\\n II.\\n\\n The Defendants challenge their convictions on two main grounds. First, they\\n\\nclaim that the district court improperly handled jurors’ fears for their safety. Second, the\\n\\nDefendants argue that the district court erred by allowing portions of Agent James’s\\n\\nexpert testimony. We reject each argument in turn.\\n\\n A. Juror Bias\\n\\n The Defendants fault the district court for how it addressed the jurors’ fears of\\n\\ngang retaliation. They claim the district court’s questioning of the jurors was inadequate\\n\\n\\n\\n\\n testimony he was not testifying as an expert, and he was not permitted to\\n offer expert opinions on the subjects then presented to him.\\n\\n If ever during this trial you thought you heard Agent James offer an expert\\n opinion on a subject outside the scope of drug and gang terminology in\\n Maryland, then I instruct you to disregard that testimony. Agent James’s\\n expert opinions are only allowed as to drug and gang terminology. On all\\n other topics on which he might have testified, he’s a fact witness and not\\n authorized to present expert opinions.\\n\\nJ.A. 1023–25.\\n\\n\\n 12\\n\\ffor failing to ask each juror expressly about Juror No. 5’s fears and discussions with other\\n\\njurors. Besides this process concern, the Defendants also object to the court’s ultimate\\n\\nrefusal to grant a mistrial.\\n\\n The Sixth Amendment guarantees a criminal defendant the right to a trial “by an\\n\\nimpartial jury.” U.S. CONST. amend. VI. This right requires a trial judge to remain\\n\\n“‘ever watchful to prevent prejudicial occurrences,’ and [he] therefore must conduct voir\\n\\ndire in a manner that adequately identifies unqualified or potentially biased jurors.”\\n\\nGardner v. Ozmint, 511 F.3d 420, 424 (4th Cir. 2007) (quoting Smith v. Phillips, 455\\n\\nU.S. 209, 217 (1982)).\\n\\n When a serious, non-speculative question of juror impartiality arises during trial,\\n\\nthe district court must determine whether the affected jurors remain fair and impartial.\\n\\nSee United States v. Thompson, 744 F.2d 1065, 1068 (4th Cir. 1984); Neal v. United\\n\\nStates, 22 F.2d 52, 53 (4th Cir. 1927). As the trial judge is in the best position to make\\n\\nthis determination, the inquiry is committed to his discretion, including ample leeway to\\n\\nformulate the questions to be asked. United States v. Barber, 80 F.3d 964, 967 (4th Cir.\\n\\n1996) (en banc).\\n\\n After learning of Juror No. 5’s fears, the district judge here questioned each juror\\n\\nindividually. That required balancing the need to detect bias against the concern that\\n\\ninartful questioning could itself generate bias. As the trial judge observed, detailed or\\n\\nfact-specific questions could “become the toxin by which the [jurors’] minds are\\n\\npoisoned and the fears are generated.” J.A. 1256. He thus asked about bias directly,\\n\\nwithout explicitly discussing Juror No. 5 or any fears of violent retaliation. In evaluating\\n\\n 13\\n\\ftheir responses, he considered the jurors’ reactions and, where necessary, followed up.\\n\\nSee, e.g., J.A. 1267–74 (asking more questions and discussing the juror’s demeanor).\\n\\nDistrict courts are encouraged to take this direct approach to detect bias in jurors. See,\\n\\ne.g., United States v. Caro, 597 F.3d 608, 615 (4th Cir. 2010). This trial judge made\\n\\nreasoned judgments in walking the line between detecting bias and creating bias. And we\\n\\nare not here to micro-manage those considered choices.\\n\\n Just as the trial judge has latitude in framing the inquiry, so too does he have broad\\n\\ndiscretion in evaluating the significance of potential juror bias. See Arizona v.\\n\\nWashington, 434 U.S. 497, 513–14 (1978) (discussing the “great deference” owed to a\\n\\ntrial judge’s decision to declare a mistrial based on possible juror bias). This trial judge\\n\\nmade appropriate inquiries into juror bias. He then excused those jurors who, by their\\n\\nanswers or demeanor, suggested they could not be fair and impartial. Left only with\\n\\njurors who had assured him of their continued impartiality, the trial judge acted well\\n\\nwithin his discretion in denying the requested mistrial. See United States v. Jones, 716\\n\\nF.3d 851, 857 (4th Cir. 2013) (noting that the court may rely on a juror’s assurance of\\n\\ncontinued impartiality if the court finds it credible).\\n\\n B. Agent James’s Expert Testimony\\n\\n The Defendants next argue that the district court abused its discretion in admitting\\n\\nportions of Agent James’s expert testimony. See United States v. Wilson, 484 F.3d 267,\\n\\n273 (4th Cir. 2007). The Defendants claim first that his experience-based linguistic\\n\\nopinions were not the product of a reliable methodology for interpreting coded jargon.\\n\\nSecond, they argue that Agent James impermissibly blended fact and expert testimony,\\n\\n 14\\n\\fcreating jury confusion and unfair prejudice. Third, they allege that Agent James served\\n\\nas a mere conduit for testimonial hearsay in violation of the Confrontation Clause. We\\n\\nreject each argument and also find harmless any instance in which Agent James may have\\n\\nstrayed outside the bounds of proper testimony.\\n\\n 1. Qualification and Methodology\\n\\n Agent James used a reliable methodology in forming his expert opinions. Federal\\n\\nRule of Evidence 702 permits expert testimony from “[a] witness who is qualified as an\\n\\nexpert by knowledge, skill, experience, training, or education” where the “specialized\\n\\nknowledge will help the trier of fact to understand the evidence or to determine a fact in\\n\\nissue” so long as the expert’s opinion is “based on sufficient facts or data,” is “the\\n\\nproduct of reliable principles and methods,” and the expert “has reliably applied the\\n\\nprinciples and methods to the facts.”\\n\\n Under Rule 702, a district court must ensure that the expert is qualified and that\\n\\nthe expert’s testimony is both relevant and reliable. Daubert v. Merrell Dow Pharm.,\\n\\nInc., 509 U.S. 579, 589 (1993). In performing this gatekeeping role, a district court “is\\n\\nnot intended to serve as a replacement for the adversary system, and consequently, the\\n\\nrejection of expert testimony is the exception rather than the rule.” In re Lipitor\\n\\n(Atorvastatin Calcium) Mktg., Sales Practices & Prod. Liab. Litig. (No II), 892 F.3d 624,\\n\\n631 (4th Cir. 2018) (citation and quotation marks omitted).\\n\\n We begin by recognizing that Agent James’s experience appropriately qualified\\n\\nhim to serve as an expert. Agent James was a twelve-year veteran of the FBI with\\n\\nsubstantial experience in drug and gang investigations (conducting controlled buys,\\n\\n 15\\n\\finterviewing drug dealers and gang members, using gang members as confidential\\n\\nsources, listening to thousands of recorded conversations, and so forth). Without\\n\\nobjection, the court qualified Agent James as an expert in drug and gang terminology in\\n\\nMaryland.\\n\\n Having found Agent James qualified, the district court explained that he applied a\\n\\nmethodology based on his extensive experience to understand the conversations. J.A.\\n\\n965G–H. Courts have consistently approved of law enforcement agents like Agent James\\n\\noffering expert interpretations of gang and drug communications based on their\\n\\nexperience. United States v. Galloway, 749 F.3d 238, 245 (4th Cir. 2014) (accepting\\n\\nagents’ “method of applying their extensive experience to analyze the meaning of the\\n\\n[drug-related] conversations through context”); see also United States v. Palacios, 677\\n\\nF.3d 234, 242 (4th Cir. 2012); United States v. Baptiste, 596 F.3d 214, 222–23 (4th Cir.\\n\\n2010); Wilson, 484 F.3d at 274–75. The district court here correctly approved of Agent\\n\\nJames’s methodology for interpreting gang and drug calls based on his experience.\\n\\n The conclusion that Agent James employed a sound methodology is only one step\\n\\nin our analysis. We must also decide whether he reliably applied it to the facts in forming\\n\\nhis expert opinions. Fed. R. Evid. 702(d). As the district court rightly concluded, Agent\\n\\nJames reliably applied his methodology. See Wilson, 484 F.3d at 274 (noting the district\\n\\ncourt’s “broad latitude” in determining whether the expert’s methodology is reliable).\\n\\nFor example, in the first call on March 10, 2014, between Bazemore and Harrington,\\n\\nAgent James interpreted the phrase “special light” as “a green light,” which he described\\n\\n\\n\\n 16\\n\\fas an authorization used by gang members to kill another person. J.A. 971. 6 He based\\n\\nthat interpretation on his experience with other investigations as well as the context of\\n\\nthis investigation.\\n\\n In the same manner, Agent James applied his experience to interpret various other\\n\\ncoded terms like “Unc,” “rolled out of JI,” “burnt,” and “checking in.” See, e.g., J.A. 977\\n\\n(explaining that “JI” is a housing unit in the city jail and that “[g]etting rolled out of JI is\\n\\ngetting moved out of that section of the city jail”). In doing so, Agent James provided a\\n\\nbasis for his interpretation, rendering it both susceptible to scrutiny by the district court\\n\\nand to being challenged on cross examination by the Defendants.\\n\\n Agent James did not always point to a specific experience that informed each\\n\\nexpert opinion. This is unsurprising. Agent James based his interpretations on years of\\n\\ninvestigatory experience and exposure to thousands of gang and drug conversations. The\\n\\napplication of this experience to analyze the meaning of certain terms does not lend itself\\n\\nto a direct correlation between one experience and one opinion. This is much like how\\n\\nforeign-language experts, such as Spanish interpreters, apply their training and\\n\\nexperience to analyze the meaning of conversations. Those experts do not translate based\\n\\non any one piece of information or learned treatise (like a dictionary) but analyze and\\n\\nsynthesize an array of information learned over years.\\n\\n\\n 6\\n The Defendants vacillate between conceding that Agent James could interpret\\n“special light,” see Reply at 11; J.A. 967, and challenging even this interpretation of\\n“special light,” see Reply at 13. Regardless, we find the court properly admitted this\\nimportant testimony.\\n\\n\\n 17\\n\\f Whether one considers Agent James more like a foreign-language interpreter or an\\n\\nanthropologist who studies a group by educating himself and conducting fieldwork, see\\n\\nUnited States v. Mejia, 545 F.3d 179, 190 (2d Cir. 2008) (analogizing a gang expert to an\\n\\nanthropologist), his expertise does not derive from any singular piece of information. As\\n\\nit would be impossible to ask this expert to lay such a precise foundation for an opinion\\n\\nwhen his expertise was gained over extended, repeated exposure, we cannot say that the\\n\\ndistrict court abused its discretion in concluding that Agent James reliably applied his\\n\\nmethodology.\\n\\n 2. Blending Facts and Expert Opinions\\n\\n The Defendants also argue that Agent James improperly blended expertise with\\n\\nfactual testimony. To be sure, while serving as an expert, Agent James did at times\\n\\ntestify to facts he learned as a participant in the investigation. This dual-role testimony—\\n\\nlike all testimony—requires a determination of whether “its probative value is\\n\\nsubstantially outweighed” by the risk of unfair prejudice or jury confusion. Fed. R. Evid.\\n\\n403. To maintain this Rule 403 balance, district courts must be vigilant to avoid the\\n\\ndanger of confusing the jury when a case agent testifies as an expert. See Wilson, 484\\n\\nF.3d at 278 n.5.\\n\\n That is why we have directed district courts to take steps to provide the jury clarity\\n\\nabout the dual roles. United States v. Baptiste, 596 F.3d 214, 224 (4th Cir. 2010). As\\n\\nexamples of safeguards the district court may employ, we have suggested “requiring the\\n\\nwitness to testify at different times, in each capacity; giving a cautionary instruction to\\n\\nthe jury regarding the basis of the testimony; allowing for cross-examination by defense\\n\\n 18\\n\\fcounsel; establishing a proper foundation for the expertise; or having counsel ground the\\n\\nquestion in either fact or expertise while asking the question.” United States v. Garcia,\\n\\n752 F.3d 382, 392 (4th Cir. 2014). None of the options on this list are necessary or per se\\n\\nsufficient. Id. (noting that precautions may be insufficient to mitigate the risk of jury\\n\\nconfusion and prejudice resulting from a given agent’s expert and fact testimony). The\\n\\nultimate question is whether, considering the safeguards used, the testimony’s “probative\\n\\nvalue is substantially outweighed” by the risk of jury confusion or unfair prejudice. Fed.\\n\\nR. Evid. 403.\\n\\n Before considering the district court’s implemented safeguards, it bears\\n\\nmentioning that certain instances of Agent James’s fact testimony were not only\\n\\npermissible but indeed necessary to provide context for his interpretations of the\\n\\nintercepted calls. An expert’s methodology cannot be applied in a factual vacuum. Thus,\\n\\nan expert in code or language must consider the context surrounding the language in\\n\\ndetermining the appropriate interpretation. See, e.g., Galloway, 749 F.3d at 245\\n\\n(approving analysis of the “context” of communications); Wilson, 484 F.3d at 275–76\\n\\n(approving consideration of the “situation” surrounding a call). As anyone teaching a\\n\\nchild to read can attest, context often provides invaluable clues to understanding the\\n\\nmeaning of words. Cf. PEGGY PARISH, AMELIA BEDELIA (1963) (humorous tale of a\\n\\nmaid who misinterprets various commands; for example, when asked to “draw the\\n\\ndrapes,” she sketches a picture of them); FRED GWYNNE, THE KING WHO RAINED (1970)\\n\\n(illustrations of a bewildered young girl who gets tripped up over homophones; for\\n\\n\\n\\n 19\\n\\fexample, “a king who rained for forty years” shown as a king floating in the sky as a rain\\n\\ncloud).\\n\\n This context includes the date and time of the intercepted call along with the\\n\\nsequence of calls: for example, the fact that certain calls occurred on the same day and\\n\\none immediately followed the other. Indeed, given the obvious need for this type of\\n\\ncontext, the Defendants necessarily conceded that Agent James could provide this factual\\n\\ncontext during his expert testimony. 7\\n\\n But appropriate factual context is not limited to a call’s date and time. It includes\\n\\nother contextual information such as the identity of the callers. And along with date,\\n\\ntime, and participants, the context of a conversation also includes the surrounding\\n\\ncircumstances, like whether a participant in the call was incarcerated or whether police\\n\\nfound a man shot shortly after a call seemingly authorized a shooting. Far from\\n\\ngenerating confusion for the jury, including this factual context reduced the risk of jury\\n\\nconfusion by providing a more coherent narrative of the investigation and a proper\\n\\nframework for Agent James’s expert opinions.\\n\\n\\n\\n\\n 7\\n While the use of context as part of the expert’s analysis is permissible, an agent\\nexpert may not rely exclusively on the surrounding events to provide an expert\\ninterpretation of the call. See Garcia, 752 F.3d at 393 (criticizing an agent’s testimony\\nthat “a hundred forty five point” meant 145 grams of heroin apparently based solely on a\\nlater seizure of 145 grams of heroin; the agent applied no expertise and, in any event, the\\nwords did not require decoding).\\n\\n\\n 20\\n\\f The Defendants suggest that the factual context surrounding the calls must come\\n\\nsolely from independent evidence. 8 In other words, the Defendants want to preclude any\\n\\ncontext coming from Agent James’s own factual observations. This novel suggestion—\\n\\nthat an expert may only consider “independently verified” evidence—can be rejected by\\n\\nreading the plain text of Rule 703, which provides that an “expert may base an opinion on\\n\\nfacts or data in the case that the expert has been made aware of or personally observed.”\\n\\nFed. R. Evid. 703 (emphasis added). 9\\n\\n Balancing the need for factual context for Agent James’s opinions and the risk in\\n\\nblending expert and factual testimony, the Government and the district court here took\\n\\neffective steps to mitigate any jury confusion or unfair prejudice to the Defendants.\\n\\nBaptiste, 596 F.3d at 224. Despite the broad scope of the investigation and charges, the\\n\\nGovernment focused Agent James’s expert testimony on calls related to a single incident:\\n\\n\\n 8\\n Some caller identifications used by Agent James stemmed from evidence\\notherwise admitted at trial (e.g., a co-conspirator identified the phone number or voice),\\nbut others followed from Agent James’s own knowledge as a percipient witness.\\nSimilarly, circumstances surrounding the context of a call sometimes came from\\nindependently admitted evidence and sometimes from his own factual observations.\\n 9\\n The Defendants are also incorrect in contending that in forming his opinions,\\nAgent James was limited to relying on admissible evidence. An expert may rely on\\ninadmissible evidence, including hearsay. See United States v. Leeson, 453 F.3d 631,\\n637 (4th Cir. 2006); see also Fed. R. Evid. 703. In particular, we have repeatedly held\\nthat an agent may rely on testimonial hearsay in forming his expert opinions. Palacios,\\n677 F.3d at 242–43; see also United States v. Johnson, 587 F.3d 625, 635 (4th Cir. 2009)\\n(observing that the Confrontation Clause “forbids the introduction of testimonial hearsay\\nas evidence in itself, but it in no way prevents expert witnesses from offering their\\nindependent judgments merely because those judgments were in some part informed by\\ntheir exposure to otherwise inadmissible evidence”).\\n\\n\\n 21\\n\\fthe attempted murder of Hall. The Government also agreed to call Agent James to the\\n\\nwitness stand twice, first as a percipient witness and later as a qualified expert. By\\n\\nlimiting the breadth of the expert testimony and separating in time his fact and expert\\n\\ntestimony, the Government cabined any potential confusion or unfair prejudice. See\\n\\nWilson, 484 F.3d at 278 n.5.\\n\\n The district court further limited the scope of Agent James’s expert opinions about\\n\\nthe calls related to the shooting by admonishing the Government to avoid “stray[ing] into\\n\\noffering opinions more broadly about what the plotters and schemers [were] up to,” J.A.\\n\\n1004, and sustaining objections when the Government approached that line, see J.A. 972,\\n\\n996–97. In doing so, the court limited any unfair prejudice that arose from Agent\\n\\nJames’s knowledge of the investigation. The court also provided the Defendants an\\n\\nopportunity to cross-examine Agent James, which they could have used to probe his\\n\\nexpert opinions. Yet they declined that opportunity. Finally, the district court provided a\\n\\nthorough instruction to the jury on the importance of distinguishing fact testimony from\\n\\nexpert opinions, insulating it from the risk of confusion. See Baptiste, 596 F.3d at 224;\\n\\nUnited States v. Farmer, 543 F.3d 363, 370–71 (7th Cir. 2008). In sum, based on the\\n\\ncircumstances here, the district court properly performed its gatekeeping role and avoided\\n\\nhaving unfair prejudice and jury confusion substantially outweigh the probative value of\\n\\nthe narrow expert testimony offered. See Fed. R. Evid. 403.\\n\\n 3. Confrontation Clause\\n\\n Despite the district court’s efforts to avoid juror confusion and unfair prejudice,\\n\\nAgent James’s testimony would have been improper if it served simply as a conduit for\\n\\n 22\\n\\ftestimonial hearsay. Garcia, 752 F.3d at 394–95; Johnson, 587 F.3d at 635. A direct\\n\\ntransmission of testimonial hearsay to the jury—as opposed to reliance on testimonial\\n\\nhearsay as part of proper expert opinion—would violate the Confrontation Clause.\\n\\nJohnson, 587 F.3d at 634–36 (discussing Crawford v. Washington, 541 U.S. 36 (2004)).\\n\\nTo determine whether an expert’s testimony raises a Confrontation Clause issue, we look\\n\\nfor indicia that the expert is giving an independent judgment and not “merely acting as a\\n\\ntransmitter for testimonial hearsay.” Id.\\n\\n The Defendants claim that Agent James’s expert testimony was improper under\\n\\nour decision in Garcia. In that drug-conspiracy case, the Government’s evidence\\n\\nconsisted primarily of law enforcement surveillance and recordings of wiretapped calls.\\n\\nGarcia, 752 F.3d at 385–86. To interpret the calls, the Government called an FBI agent\\n\\nto opine on the meaning of the conversations, many of which were in Spanish. In doing\\n\\nso, the agent admitted to debriefing three co-conspirators during the investigation to\\n\\nconfirm her understanding of the code. Id. at 394. Garcia claimed the agent’s\\n\\ninterpretations impermissibly transmitted that testimonial hearsay rather than providing\\n\\nindependent judgment about the meaning of coded terms. Given the apparent reliance on\\n\\nco-conspirator debriefings, we found that “it was incumbent upon the Government to\\n\\ndemonstrate that [the agent] was not merely channeling information and statements by\\n\\nnon-testifying participants in the conspiracy into the trial record.” Id. After reviewing\\n\\nthe record, we concluded that it was “devoid of evidence” that the agent used the\\n\\ndebriefings only to confirm her understandings rather than to serve as the sole basis of\\n\\nthose opinions. Id. at 395. We therefore found error in admitting the testimony.\\n\\n 23\\n\\f But Agent James’s testimony materially differs from that in Garcia. Agent James\\n\\napplied his own judgment to interpret the conversations in question; he was not simply\\n\\nrelaying the conspirators’ interpretations. Nothing from Agent James’ testimony\\n\\nsuggests he relied at all on co-conspirator interviews. In contrast, the record reveals that\\n\\nhis interpretation of the code between Bazemore and Harrington turned on his own\\n\\nexpertise given that, minutes after the calls on March 10, 2014, he alerted local\\n\\nauthorities. This timing confirms that Agent James exercised his judgment independent\\n\\nof any later debriefings. Not surprisingly, later developments—such as the discovery of a\\n\\nwounded Ronald Hall and jailhouse calls about the authorization to shoot Hall—\\n\\nconfirmed his own interpretations. These are all indicia that the interpretations were not\\n\\nregurgitations of inadmissible testimonial hearsay. There were no Confrontation Clause\\n\\nproblems with Agent James’s testimony.\\n\\n 4. Harmless Error\\n\\n Even if some of Agent James’s testimony went beyond the plainly permissible,\\n\\nthat limited testimony would be harmless. See United States v. White, 810 F.3d 212, 228\\n\\n(4th Cir. 2016) (“Ultimately, the question is whether we can say ‘with fair assurance,\\n\\nafter pondering all that happened without stripping the erroneous action from the whole,\\n\\nthat the jurors’ judgment was not substantially swayed by the error.’” (quoting Kotteakos\\n\\nv. United States, 328 U.S. 750, 765 (1946)).\\n\\n To begin with, Agent James’s expert opinions applied only to calls establishing\\n\\nBazemore’s involvement in the attempted murder of Hall. So any error would not affect\\n\\n\\n\\n 24\\n\\fthe convictions of Smith and Hurtt. But even for Bazemore, we find harmless any\\n\\nimproper opinion testimony from Agent James.\\n\\n At times, Agent James’s testimony contained interpretations of conversations\\n\\nbetween gang members without code. For example, Agent James interpreted “[a]nd\\n\\nthey’re trying to do something to Shorty for something he did” as “[h]e’s saying that [the\\n\\ngang] is trying to do something to Mr. Harrington for something Mr. Harrington did.”\\n\\nJ.A. 989. Agent James also interpreted some ambiguous words, including determining\\n\\nthat the word “yo” had a few different meanings. 10 In doing so, Agent James purported\\n\\nto offer expert interpretations but actually provided explanations based on his knowledge\\n\\nof this specific investigation. While lay opinion testimony may be combined with expert\\n\\nopinion testimony, doing so generally requires a more substantial foundation to\\n\\ndistinguish between lay opinion and expert opinion. 11\\n\\n\\n 10\\n Agent James gave several interpretations of the flexible pronoun “yo.” For one\\nparticular intercepted call, Agent James explained that “the yo” referred to the shooting\\nof Hall; “yo told me” referred to Bazemore; “that yo” referred to Hall himself; and\\n“holler at yo” referred to Bazemore. See J.A. 981 (“I already talked -- talked to him\\nabout the yo -- yo told me you not -- that yo not right point blank. He -- he -- he gave you\\nall the oaths, okay, so anybody got a problem with it, holler at yo.”). At other times,\\nAgent James also interpreted “yo” to refer to shooting Hall. J.A. 1007. These meanings\\nare not inherently inconsistent given the elasticity of the indefinite “yo.” Even so, these\\ninterpretations do appear to assert information learned as the case agent under the guise\\nof expert opinion. See supra n.7 (distinguishing between the proper use of context to\\ninform an expert opinion from the improper use of personal knowledge as the sole basis\\nfor the opinion); Garcia, 752 F.3d at 393. Context may help form the basis for an expert\\nopinion, but context must not be mistaken for expertise itself.\\n 11\\n Vigilantly safeguarding against jury confusion and unfair prejudice does not\\nrequire a blanket prohibition against an expert witness also offering lay opinions. See,\\ne.g., United States v. Freeman, 498 F.3d 893, 904 (9th Cir. 2007) (permitting an agent to\\n(Continued)\\n 25\\n\\f In any event, we need not determine which portions of this type of testimony were\\n\\nin error because we find that they would have been harmless. See Wilson, 484 F.3d at\\n\\n278 (finding harmless any error in admitting portions of an agent’s expert testimony\\n\\nwhen the “overwhelming majority” of the “testimony was properly admitted”). This was,\\n\\nafter all, not a close case.\\n\\n The jury heard considerable evidence that Bazemore ordered the attempted murder\\n\\nof Hall, leading us to conclude that any oversteps in Agent James’s testimony did not\\n\\nsubstantially sway the jury. That evidence includes (1) the first call on March 10, 2014,\\n\\nwhich Agent James properly interpreted as seeking authorization to kill; (2) the second\\n\\ncall on March 10, 2014, in which Bazemore instructed Harrington to “[g]o ahead and do\\n\\nit,” played at trial without interpretation; (3) the testimony of Detective Bomenka, who\\n\\ndiscussed finding a wounded Hall in Lakeland shortly after Agent James alerted\\n\\nBaltimore Police; (4) the testimony of Bazemore’s co-conspirator Gray, who implicated\\n\\nBazemore as having ordered Harrington to shoot Hall; and (5) the jailhouse calls\\n\\n\\n\\n\\noffer both expert and lay opinion testimony and stating that “the use of case agents as\\nboth expert and lay witnesses is not so inherently suspect that it should be categorically\\nprohibited”). Indeed, “[t]estimony of this kind may save time and expense, and will not\\nnecessarily result in juror confusion, provided that the district court engages in vigilant\\ngatekeeping.” Id.\\n We have yet to address directly how a court should manage an expert offering\\nboth expert interpretation of coded conversations and lay opinions of ambiguous or vague\\nstatements. See id. at 902. The district court here largely kept out Agent James’s lay\\nopinions and we leave for another day the best manner for district courts to safeguard\\nagainst the potential dangers from dual-opinion testimony.\\n\\n\\n 26\\n\\fdiscussing the authorization. Taken together, this evidence paints a strong evidentiary\\n\\npicture that Bazemore authorized Harrington to shoot Hall. 12\\n\\n * * *\\n\\n After a long trial, the jury convicted the Defendants based on voluminous\\n\\nevidence of participating in a broad conspiracy that involved widespread drug dealing\\n\\nand acts of violence. Throughout, the district court made every effort to afford the\\n\\nDefendants a fair trial. The Defendants’ challenges to their convictions do not call into\\n\\nquestion the fairness of the proceeding.\\n\\n For the reasons given, the district court’s judgment as to each Defendant is\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 12\\n Two additional claims need not detain us long. First, Hurtt argues that a passing\\nreference by a Government witness to Hurtt being previously “locked up” required a\\nmistrial. This singular stray reference to Hurtt’s prior incarceration did not amount to\\nprejudicial testimony requiring a mistrial. See United States v. Hayden, 85 F.3d 153, 158\\n(4th Cir. 1996). Second, Bazemore argues that his sentence was substantively\\nunreasonable, but he fails to rebut the presumption that his within-Guidelines sentence\\nwas reasonable considering the factors set forth in 18 U.S.C. § 3553(a). See United\\nStates v. Louthian, 756 F.3d 295, 306 (4th Cir. 2014). We find the district court did not\\nabuse its discretion in either denying Hurtt’s requested mistrial or sentencing Bazemore\\nto life in prison.\\n\\n 27\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4381443/\", \"author_raw\": \"RICHARDSON, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"NIEMEYER"},"judge2":{"kind":"string","value":"THACKER"},"judge3":{"kind":"string","value":"RICHARDSON"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4604190/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Plaintiff - Appellee, v. Michael SMITH, Jr., A/K/A Mikey, A/K/A Lil Mike, A/K/A Mik, Defendant - Appellant. United States of America, Plaintiff - Appellee, v. Mark Bazemore, A/K/A Uncle Mark, Defendant - Appellant. United States of America, Plaintiff - Appellee, v. Timothy Hurtt, A/K/A Uncle Tim, A/K/A Tim, Defendant - Appellant.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-03-27\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 16-4746\n\n\nUNITED STATES OF AMERICA,\n\n Plaintiff - Appellee,\n\n v.\n\nMICHAEL SMITH, JR., a/k/a Mikey, a/k/a Lil Mike, a/k/a Mik,\n\n Defendant - Appellant.\n\n\n No. 16-4764\n\n\nUNITED STATES OF AMERICA,\n\n Plaintiff - Appellee,\n\n v.\n\nMARK BAZEMORE, a/k/a Uncle Mark,\n\n Defendant - Appellant.\n\n\n No. 16-4765\n\n\nUNITED STATES OF AMERICA,\n\n Plaintiff - Appellee,\n\n v.\n\fTIMOTHY HURTT, a/k/a Uncle Tim, a/k/a Tim,\n\n Defendant - Appellant.\n\n\nAppeals from the United States District Court for the District of Maryland, at Baltimore.\nJames K. Bredar, Chief District Judge. (1:14-cr-00479-JKB-8; 1:14-cr-00479-JKB-11;\n1:14-cr-00479-JKB-17)\n\n\nArgued: October 30, 2018 Decided: March 27, 2019\n\n\nBefore NIEMEYER, THACKER, and RICHARDSON, Circuit Judges.\n\n\nAffirmed by published opinion. Judge Richardson wrote the opinion, in which Judge\nNiemeyer and Judge Thacker concurred.\n\n\nARGUED: Michael Daniel Montemarano, MICHAEL D. MONTEMARANO, PA,\nEllicott City, Maryland; Charles Burnham, BURNHAM & GOROKHOV PLLC,\nWashington, D.C., for Appellants. David Daniel Metcalf, OFFICE OF THE UNITED\nSTATES ATTORNEY, Baltimore, Maryland, for Appellee. ON BRIEF: Harry D.\nMcKnett, LAW OFFICE OF HARRY D. MCKNETT, LLC, Columbia, Maryland, for\nAppellant Michael Smith, Jr. Stephen M. Schenning, Acting United States Attorney,\nJames Wallner, Assistant United States Attorney, OFFICE OF THE UNITED STATES\nATTORNEY, Baltimore, Maryland, for Appellee.\n\n\n\n\n 2\n\fRICHARDSON, Circuit Judge:\n\n Defendants Mark Bazemore, Michael Smith, Jr., and Timothy Hurtt participated in\n\nthe illegal activities of a Baltimore street and prison gang known as the Black Guerrilla\n\nFamily. Their involvement in the gang’s drug dealing and acts of violence led to their\n\nconvictions. The Defendants seek to reverse those convictions for two main reasons.\n\nFirst, they argue the district court improperly handled the fears some jurors expressed to\n\nthe court after learning of this gang’s predilection for violence and retaliation. Second,\n\nthey claim the district court should have excluded an FBI agent’s expert testimony\n\ndecoding intercepted calls. We reject their challenges.\n\n I.\n\n A. Factual Background\n\n Bazemore, Smith, and Hurtt were high-ranking members of the Black Guerilla\n\nFamily, a criminal gang founded in the 1960s in California’s San Quentin State Prison.\n\nThe gang moved across the country, establishing itself in Maryland’s prison system\n\nbefore expanding to the streets of Baltimore.\n\n The gang organized itself into subsets called “regimes” that controlled the drug\n\ntrade in Maryland state prisons and in dozens of Baltimore neighborhoods. Each regime\n\nwas overseen by a “bushman,” often referred to as “Uncle” or “Unc.” In leading a\n\nregime, the bushman collected dues, settled disputes, and enforced protocol by ordering\n\n\n\n\n 3\n\fsanctions ranging from fines to death against members who broke the gang’s many\n\nrules. 1\n\n Troubled by the gang’s criminal activities, the FBI undertook a broad investigation\n\ninto the Black Guerilla Family’s Baltimore operations. They wiretapped the phone of the\n\ngang’s city-wide commander, Timothy Michael Gray, along with dozens of phones used\n\nby other gang members (including Defendants Bazemore and Hurtt). The FBI’s\n\ninvestigation exposed the gang’s sprawling drug business, documenting forty Baltimore\n\nlocations where the gang distributed heroin and cocaine. With these drug profits at stake,\n\nthe gang often turned to violence to protect its territory.\n\n Along with violently protecting their drug trade, the gang’s leaders had a penchant\n\nfor killing their subordinates that broke protocol. For instance, Bazemore ordered the\n\nmurders of members George Nealy and Ronald Hall. Of all the gang’s violence, the\n\nattempted murder of Hall bears most directly on this appeal. On March 10, 2014,\n\nBazemore ordered gang member William “Boosie” Harrington to kill Hall for allegedly\n\n 1\n Black Guerilla Family members adhered to official bylaws and upon initiation\nswore to the following oath:\n\n Should ever I be untrue and forsake the chosen few, this oath shall kill me.\n Should ever I become lax in discipline at times of strife and neglect my\n brother, this oath shall kill me.\n If ever I sought to do harm or allow harm to come to my brothers, this oath\n shall kill me.\n If ever I refuse or deny to give assistance to [] or reject my brother, this\n oath shall kill me.\n If ever I fail the sworn secrecies of this oath, this oath shall kill me.\n\nJ.A. 839–40; see J.A. 670, 843.\n\n\n 4\n\flying to the gang’s leadership. Shortly before the shooting, Bazemore and Harrington\n\nspoke twice by telephone. The first call took place at 3:50 PM when Harrington asked to\n\nconfirm the order:\n\n Bazemore: “Yo.”\n Harrington: “Hey, Unc, what’s up baby?\n Bazemore: “What’s good?”\n Harrington: “Listen to me real carefully.”\n Bazemore: “Uh huh.”\n Harrington: “I’m around Lil Shorty, you heard me?”\n Bazemore: “Yeah.”\n Harrington: “The one you always wanted me to holler at.”\n Bazemore: “Right.”\n Harrington: “I’m out Lakeland.”\n Bazemore: “Right.”\n Harrington: “Is that special light still good, good?”\n ...\n Harrington: “I got him right here.”\n Bazemore: “Matter fact, don’t worry about it, don’t worry about it. I’m\n holler at you on the close up about that one.”\n\nS.J.A. 122. One minute later, Harrington again called Bazemore and said, “Unc I’m in\n\nhis bushes. Like right now, it’d be easy and I’d be out of here, you feel me?” S.J.A. 124.\n\nBazemore replied with the authorization: “Alright, so go ahead then. Go ahead and do it\n\nthen.” Id.\n\n FBI Special Agent Mark James monitored these wiretapped conversations in real-\n\ntime. Understanding Bazemore’s order to kill, Agent James alerted local police that an\n\nact of violence was about to occur in South Baltimore’s Lakeland neighborhood.\n\nBaltimore Police arrived at the scene to find Hall with gunshot wounds to his arms and\n\ntorso. After he was rushed to the hospital, Hall survived.\n\n\n\n\n 5\n\f Three weeks after shooting Hall, Harrington was arrested and detained by state\n\nauthorities for attempted murder. In jail, Harrington faced violent retaliation from other\n\nincarcerated Black Guerilla Family members for shooting their fellow gang member,\n\nHall. In hopes of avoiding attack, Harrington placed several calls from a jail telephone\n\nseeking to “get in touch with Uncle Mark” to prove he acted with Mark Bazemore’s go-\n\nahead. S.J.A. 067. When Harrington finally reached Bazemore, he passed the phone to a\n\nfellow inmate after telling Bazemore that “[t]his [is] another good soldier here that\n\nwanted to holler at you.” J.A. 1013. Bazemore then confirmed to the other inmate that\n\nhe authorized Harrington to shoot Hall: “What Boosie [Harrington] did to him came\n\nstraight from the head. It came from me. I told him do that and he can do that.” J.A.\n\n1014.\n\n B. The Trial\n\n The Defendants, along with 15 other members of the gang, faced federal charges\n\nfor conspiring to participate in a racketeering enterprise (18 U.S.C. § 1962(d)) and for\n\nconspiring to distribute drugs (21 U.S.C. § 846). 2 Bazemore was also charged with\n\nattempted murder and conspiracy to commit murder in aid of racketeering (18 U.S.C.\n\n§ 1959(a)(5)). And Bazemore and Hurtt were charged with conspiring to use a firearm in\n\nrelation to the racketeering and drug conspiracies (18 U.S.C. § 924(o)). After their co-\n\ndefendants all pleaded guilty, Bazemore, Smith, and Hurtt stood trial in May 2016.\n\n\n 2\n Harrington pleaded guilty to the racketeering conspiracy and, after stipulating to\nhis involvement in the shooting of Hall as an act in furtherance of the conspiracy,\nreceived 151 months in prison.\n\n 6\n\f Over the course of a month, the Government proved the racketeering, drug,\n\nattempted murder, and firearm offenses through three main sources of evidence. First,\n\nlaw enforcement officials (including Agent James) testified about their investigation.\n\nSecond, seven cooperating gang members described the gang’s organization and criminal\n\nactivities. And third, recordings of wiretapped and jailhouse telephone calls confirmed\n\nthe law enforcement and cooperator testimony.\n\n The trial evidence highlighted the gang’s violent nature. This caused anxiety for\n\nsome members of the jury. On the third day, Juror No. 5 notified the court that she was\n\nafraid. In a sealed hearing, Juror No. 5 explained that she had revealed during jury\n\nselection her husband’s exact employment location. In sharing that information at side-\n\nbar, Juror No. 5 had mistakenly assumed that the Defendants were unable to hear her.\n\nHaving realized her mistake, she explained, “[i]f these people are the people that the\n\n[Government] contends, and if the jury comes back with a guilty verdict, [] it would be\n\nvery easy if they had retaliation on their mind” to use the information shared to obtain her\n\nfamily’s address. J.A. 1241. After Juror No. 5 voiced doubt that she could remain fair\n\nand impartial, the district court excused her.\n\n The district court also asked Juror No. 5 whether she had discussed her fears with\n\nother jurors, and she replied that she had spoken with “a Jim, a Jimmy, and a Mike.” J.A.\n\n1246. Based on the possibility that her discussions might have contaminated the entire\n\njury, the Defendants moved for a mistrial.\n\n Rather than grant the requested mistrial, the district court devised two questions to\n\nask each juror to probe for impartiality, bias, or contamination:\n\n 7\n\f Question 1: When we last spoke during the jury selection process, you told\n me that you believed that you could be a fair and impartial juror. Has\n anything occurred since we last spoke that would cause you to change your\n answer to that question?\n\n Question 2: Since you began to serve on the jury, has anything been said or\n overheard by you in the jury room that would affect your ability to be a fair\n and impartial juror?\n\nJ.A. 1254–55. In response, all but two jurors confirmed that they could remain fair and\n\nimpartial.\n\n The first juror who expressed apprehension about being fair was Juror No. 10. He\n\nexplained that “the nature of the case” made him scared for himself and his family. The\n\ndistrict court noted that “the juror became emotional and . . . was crying or nearly crying\n\nand struggling to control his emotions” during the questioning. J.A. 1292–95. Doubting\n\nthat Juror No. 10 could be fair and impartial, the court excused him for cause.\n\n The second juror voicing concern about her ability to remain impartial was\n\nAlternate Juror No. 4. Much like Juror No. 5, Alternate Juror No. 4 expressed concern\n\nbecause she now realized that the Defendants could hear the details she shared during\n\njury selection. As a result, she explained that she feared being recognized by gang\n\nmembers on the streets of Baltimore. J.A. 1307. The district court then excused\n\nAlternate Juror No. 4 for cause.\n\n After the three jurors were excused, twelve jurors and one alternate remained. The\n\ndistrict court denied the Defendants’ renewed request for a mistrial, finding that its\n\nquestioning “did not detect any contamination or something untoward, rampant, or even\n\nrunning among the remaining jurors.” J.A. 1318–19.\n\n\n 8\n\f When the trial resumed, the Government called Gray, the head of the Baltimore\n\ngang. Gray testified at length about the gang’s operations and explained several\n\nwiretapped calls coordinating its various illegal activities. As part of his testimony\n\nhighlighting the gang’s extensive reach throughout Maryland, Gray implicated Bazemore\n\nas the bushman who ordered Harrington to kill Hall. See J.A. 571–85 (expounding upon\n\na call between Gray and Bazemore).\n\n Having heard from Gray, the Government sought to use several recorded calls to\n\nconfirm that Bazemore authorized Harrington to kill Hall. Most of the recorded\n\nconversations took place in code—an assortment of slang, nicknames, and substituted\n\nwords meant to prevent an outside listener from deciphering their meaning. So the\n\nGovernment re-called Agent James to provide expert interpretations of the calls. 3 After\n\nAgent James was qualified as an expert in drug and gang terminology in Maryland, he\n\nexplained the meanings of several coded terms.\n\n Agent James’s explanations began with the call from March 10, 2014, at 3:50 PM,\n\nin which Harrington asked Bazemore if the “special light” remained good. Agent James\n\ndescribed that the term “Unc” meant a bushman in the Black Guerrilla Family. Before\n\nAgent James could give his expert opinion on the meaning of “special light,” the\n\nDefendants objected, expecting that the testimony would conflate expert interpretation\n\nwith factual analysis. The district court permitted Agent James to opine that he\n\n 3\n Agent James testified earlier in the trial as a fact witness to describe the FBI\ninvestigation and its use of wiretaps, controlled drug buys, and other investigatory\ntechniques.\n\n\n 9\n\finterpreted “special light” as a “green light,” which is an “authorization used by gang\n\nmembers . . . to kill another person.” J.A. 971. Agent James testified that he based his\n\ninterpretation on the context, other incidents in the investigation, and debriefings from\n\nother gang investigations he had done. Agent James was not permitted to interpret\n\nBazemore’s next statement—“don’t worry about it.” The Government then played,\n\nwithout interpretation, the very next call in which Bazemore gave Harrington the “go\n\nahead” to “do it.”\n\n After that call was played, Agent James described to the jury the steps he took to\n\nalert the Baltimore Police. The district court permitted this limited factual testimony over\n\nthe Defendants’ objection to what they called an improper “blurring of lines” between\n\nexpert and factual testimony. 4\n\n Once Agent James explained how Baltimore Police received the information, the\n\nGovernment called Detective David Bomenka, who had responded to the scene.\n\nDetective Bomenka testified that on the afternoon of March 10, 2014, he arrived in\n\nLakeland to find Hall shot and shell casings on the ground.\n\n Agent James then re-took the stand to continue in his role as expert witness. He\n\ninterpreted several of Harrington’s jail calls with other gang members, including\n\n\n 4\n Throughout the trial, the district court worked to maintain clarity and avoid\nconflating expert and lay testimony, admonishing the Government “to be very careful in\nyour questioning to make it crystal clear that you are asking for the agent’s interpretation\nof the language … and not [permit the agent] to stray into offering opinions more broadly\nabout what the plotters and schemers are up to.” J.A. 1004; see also J.A. 965D (“I want a\nreally crisp line drawn between his testimony as an expert witness and his testimony as a\nfact witness.”).\n\n 10\n\fBazemore, about the authorization to shoot Hall. At the end of Agent James’s direct\n\ntestimony, the district court gave to the jury a long cautionary instruction emphasizing the\n\nimportance of separating fact testimony from expert opinions. 5 The Defendants declined\n\nto cross-examine Agent James.\n\n\n\n 5\n The district court’s cautionary instruction read:\n\n Ladies and gentlemen, Special Agent James has testified on two separate\n occasions during this trial. During his initial testimony, Special Agent\n James provided fact testimony, but as I instructed you during his second\n time on the stand today, I instructed you that Special Agent James today\n was permitted to give opinion testimony regarding drug and gang\n terminology that may have been present in the phone calls that you’ve just\n heard. I caution you that during his second time on the stand, Special\n Agent James was providing only his opinion as an expert as to the\n substance of those calls and phrases. The fact that he also possesses factual\n information regarding this case should not be taken into account by you as\n you determine what, if any, weight to decide to give Special Agent James’s\n expert opinions. It’s for you to decide how much weight to give all of the\n evidence, including fact and opinion testimony. Special Agent James's\n testimony as a fact or expert witness is entitled to no greater or lesser\n weight simply because he is an expert in one context and was previously\n qualified to do so.\n\n You’ve just heard extensive testimony from Agent James. Agent James\n was called and qualified and permitted to testify as an expert witness. His\n field of expertise was drug and gang terminology in Maryland. Within that\n zone of expertise, Agent James was permitted to offer you his opinions.\n Specifically, he was allowed to tell you his interpretations based on his\n training and experience as to the meaning of statements made by alleged\n members of the Black Guerilla Family during telephone calls. You are\n permitted to give Agent James’s expert opinions on the meaning of drug\n and gang terminology, such weight as you may think they deserve.\n\n Ladies and gentlemen, I draw a distinction between the opinion testimony\n about drug and gang terminology, and any more traditional fact testimony\n that Agent James may have given earlier in this trial. During his previous\n(Continued)\n 11\n\f The jury convicted the Defendants on all charges. The jury specifically found\n\nBazemore and Hurtt responsible for multiple acts of first-degree murder, attempted\n\nmurder, conspiracy to commit murder, extortion, witness retaliation, and drug distribution\n\nas part of the racketeering conspiracy. S.J.A. 49, 53. The jury found Smith responsible\n\nfor extortion and drug distribution under the racketeering conspiracy. S.J.A. 56. The\n\ndistrict court sentenced Bazemore to life, Hurtt to 324 months, and Smith to 210 months.\n\n II.\n\n The Defendants challenge their convictions on two main grounds. First, they\n\nclaim that the district court improperly handled jurors’ fears for their safety. Second, the\n\nDefendants argue that the district court erred by allowing portions of Agent James’s\n\nexpert testimony. We reject each argument in turn.\n\n A. Juror Bias\n\n The Defendants fault the district court for how it addressed the jurors’ fears of\n\ngang retaliation. They claim the district court’s questioning of the jurors was inadequate\n\n\n\n\n testimony he was not testifying as an expert, and he was not permitted to\n offer expert opinions on the subjects then presented to him.\n\n If ever during this trial you thought you heard Agent James offer an expert\n opinion on a subject outside the scope of drug and gang terminology in\n Maryland, then I instruct you to disregard that testimony. Agent James’s\n expert opinions are only allowed as to drug and gang terminology. On all\n other topics on which he might have testified, he’s a fact witness and not\n authorized to present expert opinions.\n\nJ.A. 1023–25.\n\n\n 12\n\ffor failing to ask each juror expressly about Juror No. 5’s fears and discussions with other\n\njurors. Besides this process concern, the Defendants also object to the court’s ultimate\n\nrefusal to grant a mistrial.\n\n The Sixth Amendment guarantees a criminal defendant the right to a trial “by an\n\nimpartial jury.” U.S. CONST. amend. VI. This right requires a trial judge to remain\n\n“‘ever watchful to prevent prejudicial occurrences,’ and [he] therefore must conduct voir\n\ndire in a manner that adequately identifies unqualified or potentially biased jurors.”\n\nGardner v. Ozmint, 511 F.3d 420, 424 (4th Cir. 2007) (quoting Smith v. Phillips, 455\n\nU.S. 209, 217 (1982)).\n\n When a serious, non-speculative question of juror impartiality arises during trial,\n\nthe district court must determine whether the affected jurors remain fair and impartial.\n\nSee United States v. Thompson, 744 F.2d 1065, 1068 (4th Cir. 1984); Neal v. United\n\nStates, 22 F.2d 52, 53 (4th Cir. 1927). As the trial judge is in the best position to make\n\nthis determination, the inquiry is committed to his discretion, including ample leeway to\n\nformulate the questions to be asked. United States v. Barber, 80 F.3d 964, 967 (4th Cir.\n\n1996) (en banc).\n\n After learning of Juror No. 5’s fears, the district judge here questioned each juror\n\nindividually. That required balancing the need to detect bias against the concern that\n\ninartful questioning could itself generate bias. As the trial judge observed, detailed or\n\nfact-specific questions could “become the toxin by which the [jurors’] minds are\n\npoisoned and the fears are generated.” J.A. 1256. He thus asked about bias directly,\n\nwithout explicitly discussing Juror No. 5 or any fears of violent retaliation. In evaluating\n\n 13\n\ftheir responses, he considered the jurors’ reactions and, where necessary, followed up.\n\nSee, e.g., J.A. 1267–74 (asking more questions and discussing the juror’s demeanor).\n\nDistrict courts are encouraged to take this direct approach to detect bias in jurors. See,\n\ne.g., United States v. Caro, 597 F.3d 608, 615 (4th Cir. 2010). This trial judge made\n\nreasoned judgments in walking the line between detecting bias and creating bias. And we\n\nare not here to micro-manage those considered choices.\n\n Just as the trial judge has latitude in framing the inquiry, so too does he have broad\n\ndiscretion in evaluating the significance of potential juror bias. See Arizona v.\n\nWashington, 434 U.S. 497, 513–14 (1978) (discussing the “great deference” owed to a\n\ntrial judge’s decision to declare a mistrial based on possible juror bias). This trial judge\n\nmade appropriate inquiries into juror bias. He then excused those jurors who, by their\n\nanswers or demeanor, suggested they could not be fair and impartial. Left only with\n\njurors who had assured him of their continued impartiality, the trial judge acted well\n\nwithin his discretion in denying the requested mistrial. See United States v. Jones, 716\n\nF.3d 851, 857 (4th Cir. 2013) (noting that the court may rely on a juror’s assurance of\n\ncontinued impartiality if the court finds it credible).\n\n B. Agent James’s Expert Testimony\n\n The Defendants next argue that the district court abused its discretion in admitting\n\nportions of Agent James’s expert testimony. See United States v. Wilson, 484 F.3d 267,\n\n273 (4th Cir. 2007). The Defendants claim first that his experience-based linguistic\n\nopinions were not the product of a reliable methodology for interpreting coded jargon.\n\nSecond, they argue that Agent James impermissibly blended fact and expert testimony,\n\n 14\n\fcreating jury confusion and unfair prejudice. Third, they allege that Agent James served\n\nas a mere conduit for testimonial hearsay in violation of the Confrontation Clause. We\n\nreject each argument and also find harmless any instance in which Agent James may have\n\nstrayed outside the bounds of proper testimony.\n\n 1. Qualification and Methodology\n\n Agent James used a reliable methodology in forming his expert opinions. Federal\n\nRule of Evidence 702 permits expert testimony from “[a] witness who is qualified as an\n\nexpert by knowledge, skill, experience, training, or education” where the “specialized\n\nknowledge will help the trier of fact to understand the evidence or to determine a fact in\n\nissue” so long as the expert’s opinion is “based on sufficient facts or data,” is “the\n\nproduct of reliable principles and methods,” and the expert “has reliably applied the\n\nprinciples and methods to the facts.”\n\n Under Rule 702, a district court must ensure that the expert is qualified and that\n\nthe expert’s testimony is both relevant and reliable. Daubert v. Merrell Dow Pharm.,\n\nInc., 509 U.S. 579, 589 (1993). In performing this gatekeeping role, a district court “is\n\nnot intended to serve as a replacement for the adversary system, and consequently, the\n\nrejection of expert testimony is the exception rather than the rule.” In re Lipitor\n\n(Atorvastatin Calcium) Mktg., Sales Practices & Prod. Liab. Litig. (No II), 892 F.3d 624,\n\n631 (4th Cir. 2018) (citation and quotation marks omitted).\n\n We begin by recognizing that Agent James’s experience appropriately qualified\n\nhim to serve as an expert. Agent James was a twelve-year veteran of the FBI with\n\nsubstantial experience in drug and gang investigations (conducting controlled buys,\n\n 15\n\finterviewing drug dealers and gang members, using gang members as confidential\n\nsources, listening to thousands of recorded conversations, and so forth). Without\n\nobjection, the court qualified Agent James as an expert in drug and gang terminology in\n\nMaryland.\n\n Having found Agent James qualified, the district court explained that he applied a\n\nmethodology based on his extensive experience to understand the conversations. J.A.\n\n965G–H. Courts have consistently approved of law enforcement agents like Agent James\n\noffering expert interpretations of gang and drug communications based on their\n\nexperience. United States v. Galloway, 749 F.3d 238, 245 (4th Cir. 2014) (accepting\n\nagents’ “method of applying their extensive experience to analyze the meaning of the\n\n[drug-related] conversations through context”); see also United States v. Palacios, 677\n\nF.3d 234, 242 (4th Cir. 2012); United States v. Baptiste, 596 F.3d 214, 222–23 (4th Cir.\n\n2010); Wilson, 484 F.3d at 274–75. The district court here correctly approved of Agent\n\nJames’s methodology for interpreting gang and drug calls based on his experience.\n\n The conclusion that Agent James employed a sound methodology is only one step\n\nin our analysis. We must also decide whether he reliably applied it to the facts in forming\n\nhis expert opinions. Fed. R. Evid. 702(d). As the district court rightly concluded, Agent\n\nJames reliably applied his methodology. See Wilson, 484 F.3d at 274 (noting the district\n\ncourt’s “broad latitude” in determining whether the expert’s methodology is reliable).\n\nFor example, in the first call on March 10, 2014, between Bazemore and Harrington,\n\nAgent James interpreted the phrase “special light” as “a green light,” which he described\n\n\n\n 16\n\fas an authorization used by gang members to kill another person. J.A. 971. 6 He based\n\nthat interpretation on his experience with other investigations as well as the context of\n\nthis investigation.\n\n In the same manner, Agent James applied his experience to interpret various other\n\ncoded terms like “Unc,” “rolled out of JI,” “burnt,” and “checking in.” See, e.g., J.A. 977\n\n(explaining that “JI” is a housing unit in the city jail and that “[g]etting rolled out of JI is\n\ngetting moved out of that section of the city jail”). In doing so, Agent James provided a\n\nbasis for his interpretation, rendering it both susceptible to scrutiny by the district court\n\nand to being challenged on cross examination by the Defendants.\n\n Agent James did not always point to a specific experience that informed each\n\nexpert opinion. This is unsurprising. Agent James based his interpretations on years of\n\ninvestigatory experience and exposure to thousands of gang and drug conversations. The\n\napplication of this experience to analyze the meaning of certain terms does not lend itself\n\nto a direct correlation between one experience and one opinion. This is much like how\n\nforeign-language experts, such as Spanish interpreters, apply their training and\n\nexperience to analyze the meaning of conversations. Those experts do not translate based\n\non any one piece of information or learned treatise (like a dictionary) but analyze and\n\nsynthesize an array of information learned over years.\n\n\n 6\n The Defendants vacillate between conceding that Agent James could interpret\n“special light,” see Reply at 11; J.A. 967, and challenging even this interpretation of\n“special light,” see Reply at 13. Regardless, we find the court properly admitted this\nimportant testimony.\n\n\n 17\n\f Whether one considers Agent James more like a foreign-language interpreter or an\n\nanthropologist who studies a group by educating himself and conducting fieldwork, see\n\nUnited States v. Mejia, 545 F.3d 179, 190 (2d Cir. 2008) (analogizing a gang expert to an\n\nanthropologist), his expertise does not derive from any singular piece of information. As\n\nit would be impossible to ask this expert to lay such a precise foundation for an opinion\n\nwhen his expertise was gained over extended, repeated exposure, we cannot say that the\n\ndistrict court abused its discretion in concluding that Agent James reliably applied his\n\nmethodology.\n\n 2. Blending Facts and Expert Opinions\n\n The Defendants also argue that Agent James improperly blended expertise with\n\nfactual testimony. To be sure, while serving as an expert, Agent James did at times\n\ntestify to facts he learned as a participant in the investigation. This dual-role testimony—\n\nlike all testimony—requires a determination of whether “its probative value is\n\nsubstantially outweighed” by the risk of unfair prejudice or jury confusion. Fed. R. Evid.\n\n403. To maintain this Rule 403 balance, district courts must be vigilant to avoid the\n\ndanger of confusing the jury when a case agent testifies as an expert. See Wilson, 484\n\nF.3d at 278 n.5.\n\n That is why we have directed district courts to take steps to provide the jury clarity\n\nabout the dual roles. United States v. Baptiste, 596 F.3d 214, 224 (4th Cir. 2010). As\n\nexamples of safeguards the district court may employ, we have suggested “requiring the\n\nwitness to testify at different times, in each capacity; giving a cautionary instruction to\n\nthe jury regarding the basis of the testimony; allowing for cross-examination by defense\n\n 18\n\fcounsel; establishing a proper foundation for the expertise; or having counsel ground the\n\nquestion in either fact or expertise while asking the question.” United States v. Garcia,\n\n752 F.3d 382, 392 (4th Cir. 2014). None of the options on this list are necessary or per se\n\nsufficient. Id. (noting that precautions may be insufficient to mitigate the risk of jury\n\nconfusion and prejudice resulting from a given agent’s expert and fact testimony). The\n\nultimate question is whether, considering the safeguards used, the testimony’s “probative\n\nvalue is substantially outweighed” by the risk of jury confusion or unfair prejudice. Fed.\n\nR. Evid. 403.\n\n Before considering the district court’s implemented safeguards, it bears\n\nmentioning that certain instances of Agent James’s fact testimony were not only\n\npermissible but indeed necessary to provide context for his interpretations of the\n\nintercepted calls. An expert’s methodology cannot be applied in a factual vacuum. Thus,\n\nan expert in code or language must consider the context surrounding the language in\n\ndetermining the appropriate interpretation. See, e.g., Galloway, 749 F.3d at 245\n\n(approving analysis of the “context” of communications); Wilson, 484 F.3d at 275–76\n\n(approving consideration of the “situation” surrounding a call). As anyone teaching a\n\nchild to read can attest, context often provides invaluable clues to understanding the\n\nmeaning of words. Cf. PEGGY PARISH, AMELIA BEDELIA (1963) (humorous tale of a\n\nmaid who misinterprets various commands; for example, when asked to “draw the\n\ndrapes,” she sketches a picture of them); FRED GWYNNE, THE KING WHO RAINED (1970)\n\n(illustrations of a bewildered young girl who gets tripped up over homophones; for\n\n\n\n 19\n\fexample, “a king who rained for forty years” shown as a king floating in the sky as a rain\n\ncloud).\n\n This context includes the date and time of the intercepted call along with the\n\nsequence of calls: for example, the fact that certain calls occurred on the same day and\n\none immediately followed the other. Indeed, given the obvious need for this type of\n\ncontext, the Defendants necessarily conceded that Agent James could provide this factual\n\ncontext during his expert testimony. 7\n\n But appropriate factual context is not limited to a call’s date and time. It includes\n\nother contextual information such as the identity of the callers. And along with date,\n\ntime, and participants, the context of a conversation also includes the surrounding\n\ncircumstances, like whether a participant in the call was incarcerated or whether police\n\nfound a man shot shortly after a call seemingly authorized a shooting. Far from\n\ngenerating confusion for the jury, including this factual context reduced the risk of jury\n\nconfusion by providing a more coherent narrative of the investigation and a proper\n\nframework for Agent James’s expert opinions.\n\n\n\n\n 7\n While the use of context as part of the expert’s analysis is permissible, an agent\nexpert may not rely exclusively on the surrounding events to provide an expert\ninterpretation of the call. See Garcia, 752 F.3d at 393 (criticizing an agent’s testimony\nthat “a hundred forty five point” meant 145 grams of heroin apparently based solely on a\nlater seizure of 145 grams of heroin; the agent applied no expertise and, in any event, the\nwords did not require decoding).\n\n\n 20\n\f The Defendants suggest that the factual context surrounding the calls must come\n\nsolely from independent evidence. 8 In other words, the Defendants want to preclude any\n\ncontext coming from Agent James’s own factual observations. This novel suggestion—\n\nthat an expert may only consider “independently verified” evidence—can be rejected by\n\nreading the plain text of Rule 703, which provides that an “expert may base an opinion on\n\nfacts or data in the case that the expert has been made aware of or personally observed.”\n\nFed. R. Evid. 703 (emphasis added). 9\n\n Balancing the need for factual context for Agent James’s opinions and the risk in\n\nblending expert and factual testimony, the Government and the district court here took\n\neffective steps to mitigate any jury confusion or unfair prejudice to the Defendants.\n\nBaptiste, 596 F.3d at 224. Despite the broad scope of the investigation and charges, the\n\nGovernment focused Agent James’s expert testimony on calls related to a single incident:\n\n\n 8\n Some caller identifications used by Agent James stemmed from evidence\notherwise admitted at trial (e.g., a co-conspirator identified the phone number or voice),\nbut others followed from Agent James’s own knowledge as a percipient witness.\nSimilarly, circumstances surrounding the context of a call sometimes came from\nindependently admitted evidence and sometimes from his own factual observations.\n 9\n The Defendants are also incorrect in contending that in forming his opinions,\nAgent James was limited to relying on admissible evidence. An expert may rely on\ninadmissible evidence, including hearsay. See United States v. Leeson, 453 F.3d 631,\n637 (4th Cir. 2006); see also Fed. R. Evid. 703. In particular, we have repeatedly held\nthat an agent may rely on testimonial hearsay in forming his expert opinions. Palacios,\n677 F.3d at 242–43; see also United States v. Johnson, 587 F.3d 625, 635 (4th Cir. 2009)\n(observing that the Confrontation Clause “forbids the introduction of testimonial hearsay\nas evidence in itself, but it in no way prevents expert witnesses from offering their\nindependent judgments merely because those judgments were in some part informed by\ntheir exposure to otherwise inadmissible evidence”).\n\n\n 21\n\fthe attempted murder of Hall. The Government also agreed to call Agent James to the\n\nwitness stand twice, first as a percipient witness and later as a qualified expert. By\n\nlimiting the breadth of the expert testimony and separating in time his fact and expert\n\ntestimony, the Government cabined any potential confusion or unfair prejudice. See\n\nWilson, 484 F.3d at 278 n.5.\n\n The district court further limited the scope of Agent James’s expert opinions about\n\nthe calls related to the shooting by admonishing the Government to avoid “stray[ing] into\n\noffering opinions more broadly about what the plotters and schemers [were] up to,” J.A.\n\n1004, and sustaining objections when the Government approached that line, see J.A. 972,\n\n996–97. In doing so, the court limited any unfair prejudice that arose from Agent\n\nJames’s knowledge of the investigation. The court also provided the Defendants an\n\nopportunity to cross-examine Agent James, which they could have used to probe his\n\nexpert opinions. Yet they declined that opportunity. Finally, the district court provided a\n\nthorough instruction to the jury on the importance of distinguishing fact testimony from\n\nexpert opinions, insulating it from the risk of confusion. See Baptiste, 596 F.3d at 224;\n\nUnited States v. Farmer, 543 F.3d 363, 370–71 (7th Cir. 2008). In sum, based on the\n\ncircumstances here, the district court properly performed its gatekeeping role and avoided\n\nhaving unfair prejudice and jury confusion substantially outweigh the probative value of\n\nthe narrow expert testimony offered. See Fed. R. Evid. 403.\n\n 3. Confrontation Clause\n\n Despite the district court’s efforts to avoid juror confusion and unfair prejudice,\n\nAgent James’s testimony would have been improper if it served simply as a conduit for\n\n 22\n\ftestimonial hearsay. Garcia, 752 F.3d at 394–95; Johnson, 587 F.3d at 635. A direct\n\ntransmission of testimonial hearsay to the jury—as opposed to reliance on testimonial\n\nhearsay as part of proper expert opinion—would violate the Confrontation Clause.\n\nJohnson, 587 F.3d at 634–36 (discussing Crawford v. Washington, 541 U.S. 36 (2004)).\n\nTo determine whether an expert’s testimony raises a Confrontation Clause issue, we look\n\nfor indicia that the expert is giving an independent judgment and not “merely acting as a\n\ntransmitter for testimonial hearsay.” Id.\n\n The Defendants claim that Agent James’s expert testimony was improper under\n\nour decision in Garcia. In that drug-conspiracy case, the Government’s evidence\n\nconsisted primarily of law enforcement surveillance and recordings of wiretapped calls.\n\nGarcia, 752 F.3d at 385–86. To interpret the calls, the Government called an FBI agent\n\nto opine on the meaning of the conversations, many of which were in Spanish. In doing\n\nso, the agent admitted to debriefing three co-conspirators during the investigation to\n\nconfirm her understanding of the code. Id. at 394. Garcia claimed the agent’s\n\ninterpretations impermissibly transmitted that testimonial hearsay rather than providing\n\nindependent judgment about the meaning of coded terms. Given the apparent reliance on\n\nco-conspirator debriefings, we found that “it was incumbent upon the Government to\n\ndemonstrate that [the agent] was not merely channeling information and statements by\n\nnon-testifying participants in the conspiracy into the trial record.” Id. After reviewing\n\nthe record, we concluded that it was “devoid of evidence” that the agent used the\n\ndebriefings only to confirm her understandings rather than to serve as the sole basis of\n\nthose opinions. Id. at 395. We therefore found error in admitting the testimony.\n\n 23\n\f But Agent James’s testimony materially differs from that in Garcia. Agent James\n\napplied his own judgment to interpret the conversations in question; he was not simply\n\nrelaying the conspirators’ interpretations. Nothing from Agent James’ testimony\n\nsuggests he relied at all on co-conspirator interviews. In contrast, the record reveals that\n\nhis interpretation of the code between Bazemore and Harrington turned on his own\n\nexpertise given that, minutes after the calls on March 10, 2014, he alerted local\n\nauthorities. This timing confirms that Agent James exercised his judgment independent\n\nof any later debriefings. Not surprisingly, later developments—such as the discovery of a\n\nwounded Ronald Hall and jailhouse calls about the authorization to shoot Hall—\n\nconfirmed his own interpretations. These are all indicia that the interpretations were not\n\nregurgitations of inadmissible testimonial hearsay. There were no Confrontation Clause\n\nproblems with Agent James’s testimony.\n\n 4. Harmless Error\n\n Even if some of Agent James’s testimony went beyond the plainly permissible,\n\nthat limited testimony would be harmless. See United States v. White, 810 F.3d 212, 228\n\n(4th Cir. 2016) (“Ultimately, the question is whether we can say ‘with fair assurance,\n\nafter pondering all that happened without stripping the erroneous action from the whole,\n\nthat the jurors’ judgment was not substantially swayed by the error.’” (quoting Kotteakos\n\nv. United States, 328 U.S. 750, 765 (1946)).\n\n To begin with, Agent James’s expert opinions applied only to calls establishing\n\nBazemore’s involvement in the attempted murder of Hall. So any error would not affect\n\n\n\n 24\n\fthe convictions of Smith and Hurtt. But even for Bazemore, we find harmless any\n\nimproper opinion testimony from Agent James.\n\n At times, Agent James’s testimony contained interpretations of conversations\n\nbetween gang members without code. For example, Agent James interpreted “[a]nd\n\nthey’re trying to do something to Shorty for something he did” as “[h]e’s saying that [the\n\ngang] is trying to do something to Mr. Harrington for something Mr. Harrington did.”\n\nJ.A. 989. Agent James also interpreted some ambiguous words, including determining\n\nthat the word “yo” had a few different meanings. 10 In doing so, Agent James purported\n\nto offer expert interpretations but actually provided explanations based on his knowledge\n\nof this specific investigation. While lay opinion testimony may be combined with expert\n\nopinion testimony, doing so generally requires a more substantial foundation to\n\ndistinguish between lay opinion and expert opinion. 11\n\n\n 10\n Agent James gave several interpretations of the flexible pronoun “yo.” For one\nparticular intercepted call, Agent James explained that “the yo” referred to the shooting\nof Hall; “yo told me” referred to Bazemore; “that yo” referred to Hall himself; and\n“holler at yo” referred to Bazemore. See J.A. 981 (“I already talked -- talked to him\nabout the yo -- yo told me you not -- that yo not right point blank. He -- he -- he gave you\nall the oaths, okay, so anybody got a problem with it, holler at yo.”). At other times,\nAgent James also interpreted “yo” to refer to shooting Hall. J.A. 1007. These meanings\nare not inherently inconsistent given the elasticity of the indefinite “yo.” Even so, these\ninterpretations do appear to assert information learned as the case agent under the guise\nof expert opinion. See supra n.7 (distinguishing between the proper use of context to\ninform an expert opinion from the improper use of personal knowledge as the sole basis\nfor the opinion); Garcia, 752 F.3d at 393. Context may help form the basis for an expert\nopinion, but context must not be mistaken for expertise itself.\n 11\n Vigilantly safeguarding against jury confusion and unfair prejudice does not\nrequire a blanket prohibition against an expert witness also offering lay opinions. See,\ne.g., United States v. Freeman, 498 F.3d 893, 904 (9th Cir. 2007) (permitting an agent to\n(Continued)\n 25\n\f In any event, we need not determine which portions of this type of testimony were\n\nin error because we find that they would have been harmless. See Wilson, 484 F.3d at\n\n278 (finding harmless any error in admitting portions of an agent’s expert testimony\n\nwhen the “overwhelming majority” of the “testimony was properly admitted”). This was,\n\nafter all, not a close case.\n\n The jury heard considerable evidence that Bazemore ordered the attempted murder\n\nof Hall, leading us to conclude that any oversteps in Agent James’s testimony did not\n\nsubstantially sway the jury. That evidence includes (1) the first call on March 10, 2014,\n\nwhich Agent James properly interpreted as seeking authorization to kill; (2) the second\n\ncall on March 10, 2014, in which Bazemore instructed Harrington to “[g]o ahead and do\n\nit,” played at trial without interpretation; (3) the testimony of Detective Bomenka, who\n\ndiscussed finding a wounded Hall in Lakeland shortly after Agent James alerted\n\nBaltimore Police; (4) the testimony of Bazemore’s co-conspirator Gray, who implicated\n\nBazemore as having ordered Harrington to shoot Hall; and (5) the jailhouse calls\n\n\n\n\noffer both expert and lay opinion testimony and stating that “the use of case agents as\nboth expert and lay witnesses is not so inherently suspect that it should be categorically\nprohibited”). Indeed, “[t]estimony of this kind may save time and expense, and will not\nnecessarily result in juror confusion, provided that the district court engages in vigilant\ngatekeeping.” Id.\n We have yet to address directly how a court should manage an expert offering\nboth expert interpretation of coded conversations and lay opinions of ambiguous or vague\nstatements. See id. at 902. The district court here largely kept out Agent James’s lay\nopinions and we leave for another day the best manner for district courts to safeguard\nagainst the potential dangers from dual-opinion testimony.\n\n\n 26\n\fdiscussing the authorization. Taken together, this evidence paints a strong evidentiary\n\npicture that Bazemore authorized Harrington to shoot Hall. 12\n\n * * *\n\n After a long trial, the jury convicted the Defendants based on voluminous\n\nevidence of participating in a broad conspiracy that involved widespread drug dealing\n\nand acts of violence. Throughout, the district court made every effort to afford the\n\nDefendants a fair trial. The Defendants’ challenges to their convictions do not call into\n\nquestion the fairness of the proceeding.\n\n For the reasons given, the district court’s judgment as to each Defendant is\n\n AFFIRMED.\n\n\n\n\n 12\n Two additional claims need not detain us long. First, Hurtt argues that a passing\nreference by a Government witness to Hurtt being previously “locked up” required a\nmistrial. This singular stray reference to Hurtt’s prior incarceration did not amount to\nprejudicial testimony requiring a mistrial. See United States v. Hayden, 85 F.3d 153, 158\n(4th Cir. 1996). Second, Bazemore argues that his sentence was substantively\nunreasonable, but he fails to rebut the presumption that his within-Guidelines sentence\nwas reasonable considering the factors set forth in 18 U.S.C. § 3553(a). See United\nStates v. Louthian, 756 F.3d 295, 306 (4th Cir. 2014). We find the district court did not\nabuse its discretion in either denying Hurtt’s requested mistrial or sentencing Bazemore\nto life in prison.\n\n 27\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Plaintiff - Appellee, v. Michael SMITH, Jr., A/K/A Mikey, A/K/A Lil Mike, A/K/A Mik, Defendant - Appellant. United States of America, Plaintiff - Appellee, v. Mark Bazemore, A/K/A Uncle Mark, Defendant - Appellant. United States of America, Plaintiff - Appellee, v. Timothy Hurtt, A/K/A Uncle Tim, A/K/A Tim, Defendant - Appellant.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-03-27\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 16-4746\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\n v.\\n\\nMICHAEL SMITH, JR., a/k/a Mikey, a/k/a Lil Mike, a/k/a Mik,\\n\\n Defendant - Appellant.\\n\\n\\n No. 16-4764\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\n v.\\n\\nMARK BAZEMORE, a/k/a Uncle Mark,\\n\\n Defendant - Appellant.\\n\\n\\n No. 16-4765\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\n v.\\n\\fTIMOTHY HURTT, a/k/a Uncle Tim, a/k/a Tim,\\n\\n Defendant - Appellant.\\n\\n\\nAppeals from the United States District Court for the District of Maryland, at Baltimore.\\nJames K. Bredar, Chief District Judge. (1:14-cr-00479-JKB-8; 1:14-cr-00479-JKB-11;\\n1:14-cr-00479-JKB-17)\\n\\n\\nArgued: October 30, 2018 Decided: March 27, 2019\\n\\n\\nBefore NIEMEYER, THACKER, and RICHARDSON, Circuit Judges.\\n\\n\\nAffirmed by published opinion. Judge Richardson wrote the opinion, in which Judge\\nNiemeyer and Judge Thacker concurred.\\n\\n\\nARGUED: Michael Daniel Montemarano, MICHAEL D. MONTEMARANO, PA,\\nEllicott City, Maryland; Charles Burnham, BURNHAM & GOROKHOV PLLC,\\nWashington, D.C., for Appellants. David Daniel Metcalf, OFFICE OF THE UNITED\\nSTATES ATTORNEY, Baltimore, Maryland, for Appellee. ON BRIEF: Harry D.\\nMcKnett, LAW OFFICE OF HARRY D. MCKNETT, LLC, Columbia, Maryland, for\\nAppellant Michael Smith, Jr. Stephen M. Schenning, Acting United States Attorney,\\nJames Wallner, Assistant United States Attorney, OFFICE OF THE UNITED STATES\\nATTORNEY, Baltimore, Maryland, for Appellee.\\n\\n\\n\\n\\n 2\\n\\fRICHARDSON, Circuit Judge:\\n\\n Defendants Mark Bazemore, Michael Smith, Jr., and Timothy Hurtt participated in\\n\\nthe illegal activities of a Baltimore street and prison gang known as the Black Guerrilla\\n\\nFamily. Their involvement in the gang’s drug dealing and acts of violence led to their\\n\\nconvictions. The Defendants seek to reverse those convictions for two main reasons.\\n\\nFirst, they argue the district court improperly handled the fears some jurors expressed to\\n\\nthe court after learning of this gang’s predilection for violence and retaliation. Second,\\n\\nthey claim the district court should have excluded an FBI agent’s expert testimony\\n\\ndecoding intercepted calls. We reject their challenges.\\n\\n I.\\n\\n A. Factual Background\\n\\n Bazemore, Smith, and Hurtt were high-ranking members of the Black Guerilla\\n\\nFamily, a criminal gang founded in the 1960s in California’s San Quentin State Prison.\\n\\nThe gang moved across the country, establishing itself in Maryland’s prison system\\n\\nbefore expanding to the streets of Baltimore.\\n\\n The gang organized itself into subsets called “regimes” that controlled the drug\\n\\ntrade in Maryland state prisons and in dozens of Baltimore neighborhoods. Each regime\\n\\nwas overseen by a “bushman,” often referred to as “Uncle” or “Unc.” In leading a\\n\\nregime, the bushman collected dues, settled disputes, and enforced protocol by ordering\\n\\n\\n\\n\\n 3\\n\\fsanctions ranging from fines to death against members who broke the gang’s many\\n\\nrules. 1\\n\\n Troubled by the gang’s criminal activities, the FBI undertook a broad investigation\\n\\ninto the Black Guerilla Family’s Baltimore operations. They wiretapped the phone of the\\n\\ngang’s city-wide commander, Timothy Michael Gray, along with dozens of phones used\\n\\nby other gang members (including Defendants Bazemore and Hurtt). The FBI’s\\n\\ninvestigation exposed the gang’s sprawling drug business, documenting forty Baltimore\\n\\nlocations where the gang distributed heroin and cocaine. With these drug profits at stake,\\n\\nthe gang often turned to violence to protect its territory.\\n\\n Along with violently protecting their drug trade, the gang’s leaders had a penchant\\n\\nfor killing their subordinates that broke protocol. For instance, Bazemore ordered the\\n\\nmurders of members George Nealy and Ronald Hall. Of all the gang’s violence, the\\n\\nattempted murder of Hall bears most directly on this appeal. On March 10, 2014,\\n\\nBazemore ordered gang member William “Boosie” Harrington to kill Hall for allegedly\\n\\n 1\\n Black Guerilla Family members adhered to official bylaws and upon initiation\\nswore to the following oath:\\n\\n Should ever I be untrue and forsake the chosen few, this oath shall kill me.\\n Should ever I become lax in discipline at times of strife and neglect my\\n brother, this oath shall kill me.\\n If ever I sought to do harm or allow harm to come to my brothers, this oath\\n shall kill me.\\n If ever I refuse or deny to give assistance to [] or reject my brother, this\\n oath shall kill me.\\n If ever I fail the sworn secrecies of this oath, this oath shall kill me.\\n\\nJ.A. 839–40; see J.A. 670, 843.\\n\\n\\n 4\\n\\flying to the gang’s leadership. Shortly before the shooting, Bazemore and Harrington\\n\\nspoke twice by telephone. The first call took place at 3:50 PM when Harrington asked to\\n\\nconfirm the order:\\n\\n Bazemore: “Yo.”\\n Harrington: “Hey, Unc, what’s up baby?\\n Bazemore: “What’s good?”\\n Harrington: “Listen to me real carefully.”\\n Bazemore: “Uh huh.”\\n Harrington: “I’m around Lil Shorty, you heard me?”\\n Bazemore: “Yeah.”\\n Harrington: “The one you always wanted me to holler at.”\\n Bazemore: “Right.”\\n Harrington: “I’m out Lakeland.”\\n Bazemore: “Right.”\\n Harrington: “Is that special light still good, good?”\\n ...\\n Harrington: “I got him right here.”\\n Bazemore: “Matter fact, don’t worry about it, don’t worry about it. I’m\\n holler at you on the close up about that one.”\\n\\nS.J.A. 122. One minute later, Harrington again called Bazemore and said, “Unc I’m in\\n\\nhis bushes. Like right now, it’d be easy and I’d be out of here, you feel me?” S.J.A. 124.\\n\\nBazemore replied with the authorization: “Alright, so go ahead then. Go ahead and do it\\n\\nthen.” Id.\\n\\n FBI Special Agent Mark James monitored these wiretapped conversations in real-\\n\\ntime. Understanding Bazemore’s order to kill, Agent James alerted local police that an\\n\\nact of violence was about to occur in South Baltimore’s Lakeland neighborhood.\\n\\nBaltimore Police arrived at the scene to find Hall with gunshot wounds to his arms and\\n\\ntorso. After he was rushed to the hospital, Hall survived.\\n\\n\\n\\n\\n 5\\n\\f Three weeks after shooting Hall, Harrington was arrested and detained by state\\n\\nauthorities for attempted murder. In jail, Harrington faced violent retaliation from other\\n\\nincarcerated Black Guerilla Family members for shooting their fellow gang member,\\n\\nHall. In hopes of avoiding attack, Harrington placed several calls from a jail telephone\\n\\nseeking to “get in touch with Uncle Mark” to prove he acted with Mark Bazemore’s go-\\n\\nahead. S.J.A. 067. When Harrington finally reached Bazemore, he passed the phone to a\\n\\nfellow inmate after telling Bazemore that “[t]his [is] another good soldier here that\\n\\nwanted to holler at you.” J.A. 1013. Bazemore then confirmed to the other inmate that\\n\\nhe authorized Harrington to shoot Hall: “What Boosie [Harrington] did to him came\\n\\nstraight from the head. It came from me. I told him do that and he can do that.” J.A.\\n\\n1014.\\n\\n B. The Trial\\n\\n The Defendants, along with 15 other members of the gang, faced federal charges\\n\\nfor conspiring to participate in a racketeering enterprise (18 U.S.C. § 1962(d)) and for\\n\\nconspiring to distribute drugs (21 U.S.C. § 846). 2 Bazemore was also charged with\\n\\nattempted murder and conspiracy to commit murder in aid of racketeering (18 U.S.C.\\n\\n§ 1959(a)(5)). And Bazemore and Hurtt were charged with conspiring to use a firearm in\\n\\nrelation to the racketeering and drug conspiracies (18 U.S.C. § 924(o)). After their co-\\n\\ndefendants all pleaded guilty, Bazemore, Smith, and Hurtt stood trial in May 2016.\\n\\n\\n 2\\n Harrington pleaded guilty to the racketeering conspiracy and, after stipulating to\\nhis involvement in the shooting of Hall as an act in furtherance of the conspiracy,\\nreceived 151 months in prison.\\n\\n 6\\n\\f Over the course of a month, the Government proved the racketeering, drug,\\n\\nattempted murder, and firearm offenses through three main sources of evidence. First,\\n\\nlaw enforcement officials (including Agent James) testified about their investigation.\\n\\nSecond, seven cooperating gang members described the gang’s organization and criminal\\n\\nactivities. And third, recordings of wiretapped and jailhouse telephone calls confirmed\\n\\nthe law enforcement and cooperator testimony.\\n\\n The trial evidence highlighted the gang’s violent nature. This caused anxiety for\\n\\nsome members of the jury. On the third day, Juror No. 5 notified the court that she was\\n\\nafraid. In a sealed hearing, Juror No. 5 explained that she had revealed during jury\\n\\nselection her husband’s exact employment location. In sharing that information at side-\\n\\nbar, Juror No. 5 had mistakenly assumed that the Defendants were unable to hear her.\\n\\nHaving realized her mistake, she explained, “[i]f these people are the people that the\\n\\n[Government] contends, and if the jury comes back with a guilty verdict, [] it would be\\n\\nvery easy if they had retaliation on their mind” to use the information shared to obtain her\\n\\nfamily’s address. J.A. 1241. After Juror No. 5 voiced doubt that she could remain fair\\n\\nand impartial, the district court excused her.\\n\\n The district court also asked Juror No. 5 whether she had discussed her fears with\\n\\nother jurors, and she replied that she had spoken with “a Jim, a Jimmy, and a Mike.” J.A.\\n\\n1246. Based on the possibility that her discussions might have contaminated the entire\\n\\njury, the Defendants moved for a mistrial.\\n\\n Rather than grant the requested mistrial, the district court devised two questions to\\n\\nask each juror to probe for impartiality, bias, or contamination:\\n\\n 7\\n\\f Question 1: When we last spoke during the jury selection process, you told\\n me that you believed that you could be a fair and impartial juror. Has\\n anything occurred since we last spoke that would cause you to change your\\n answer to that question?\\n\\n Question 2: Since you began to serve on the jury, has anything been said or\\n overheard by you in the jury room that would affect your ability to be a fair\\n and impartial juror?\\n\\nJ.A. 1254–55. In response, all but two jurors confirmed that they could remain fair and\\n\\nimpartial.\\n\\n The first juror who expressed apprehension about being fair was Juror No. 10. He\\n\\nexplained that “the nature of the case” made him scared for himself and his family. The\\n\\ndistrict court noted that “the juror became emotional and . . . was crying or nearly crying\\n\\nand struggling to control his emotions” during the questioning. J.A. 1292–95. Doubting\\n\\nthat Juror No. 10 could be fair and impartial, the court excused him for cause.\\n\\n The second juror voicing concern about her ability to remain impartial was\\n\\nAlternate Juror No. 4. Much like Juror No. 5, Alternate Juror No. 4 expressed concern\\n\\nbecause she now realized that the Defendants could hear the details she shared during\\n\\njury selection. As a result, she explained that she feared being recognized by gang\\n\\nmembers on the streets of Baltimore. J.A. 1307. The district court then excused\\n\\nAlternate Juror No. 4 for cause.\\n\\n After the three jurors were excused, twelve jurors and one alternate remained. The\\n\\ndistrict court denied the Defendants’ renewed request for a mistrial, finding that its\\n\\nquestioning “did not detect any contamination or something untoward, rampant, or even\\n\\nrunning among the remaining jurors.” J.A. 1318–19.\\n\\n\\n 8\\n\\f When the trial resumed, the Government called Gray, the head of the Baltimore\\n\\ngang. Gray testified at length about the gang’s operations and explained several\\n\\nwiretapped calls coordinating its various illegal activities. As part of his testimony\\n\\nhighlighting the gang’s extensive reach throughout Maryland, Gray implicated Bazemore\\n\\nas the bushman who ordered Harrington to kill Hall. See J.A. 571–85 (expounding upon\\n\\na call between Gray and Bazemore).\\n\\n Having heard from Gray, the Government sought to use several recorded calls to\\n\\nconfirm that Bazemore authorized Harrington to kill Hall. Most of the recorded\\n\\nconversations took place in code—an assortment of slang, nicknames, and substituted\\n\\nwords meant to prevent an outside listener from deciphering their meaning. So the\\n\\nGovernment re-called Agent James to provide expert interpretations of the calls. 3 After\\n\\nAgent James was qualified as an expert in drug and gang terminology in Maryland, he\\n\\nexplained the meanings of several coded terms.\\n\\n Agent James’s explanations began with the call from March 10, 2014, at 3:50 PM,\\n\\nin which Harrington asked Bazemore if the “special light” remained good. Agent James\\n\\ndescribed that the term “Unc” meant a bushman in the Black Guerrilla Family. Before\\n\\nAgent James could give his expert opinion on the meaning of “special light,” the\\n\\nDefendants objected, expecting that the testimony would conflate expert interpretation\\n\\nwith factual analysis. The district court permitted Agent James to opine that he\\n\\n 3\\n Agent James testified earlier in the trial as a fact witness to describe the FBI\\ninvestigation and its use of wiretaps, controlled drug buys, and other investigatory\\ntechniques.\\n\\n\\n 9\\n\\finterpreted “special light” as a “green light,” which is an “authorization used by gang\\n\\nmembers . . . to kill another person.” J.A. 971. Agent James testified that he based his\\n\\ninterpretation on the context, other incidents in the investigation, and debriefings from\\n\\nother gang investigations he had done. Agent James was not permitted to interpret\\n\\nBazemore’s next statement—“don’t worry about it.” The Government then played,\\n\\nwithout interpretation, the very next call in which Bazemore gave Harrington the “go\\n\\nahead” to “do it.”\\n\\n After that call was played, Agent James described to the jury the steps he took to\\n\\nalert the Baltimore Police. The district court permitted this limited factual testimony over\\n\\nthe Defendants’ objection to what they called an improper “blurring of lines” between\\n\\nexpert and factual testimony. 4\\n\\n Once Agent James explained how Baltimore Police received the information, the\\n\\nGovernment called Detective David Bomenka, who had responded to the scene.\\n\\nDetective Bomenka testified that on the afternoon of March 10, 2014, he arrived in\\n\\nLakeland to find Hall shot and shell casings on the ground.\\n\\n Agent James then re-took the stand to continue in his role as expert witness. He\\n\\ninterpreted several of Harrington’s jail calls with other gang members, including\\n\\n\\n 4\\n Throughout the trial, the district court worked to maintain clarity and avoid\\nconflating expert and lay testimony, admonishing the Government “to be very careful in\\nyour questioning to make it crystal clear that you are asking for the agent’s interpretation\\nof the language … and not [permit the agent] to stray into offering opinions more broadly\\nabout what the plotters and schemers are up to.” J.A. 1004; see also J.A. 965D (“I want a\\nreally crisp line drawn between his testimony as an expert witness and his testimony as a\\nfact witness.”).\\n\\n 10\\n\\fBazemore, about the authorization to shoot Hall. At the end of Agent James’s direct\\n\\ntestimony, the district court gave to the jury a long cautionary instruction emphasizing the\\n\\nimportance of separating fact testimony from expert opinions. 5 The Defendants declined\\n\\nto cross-examine Agent James.\\n\\n\\n\\n 5\\n The district court’s cautionary instruction read:\\n\\n Ladies and gentlemen, Special Agent James has testified on two separate\\n occasions during this trial. During his initial testimony, Special Agent\\n James provided fact testimony, but as I instructed you during his second\\n time on the stand today, I instructed you that Special Agent James today\\n was permitted to give opinion testimony regarding drug and gang\\n terminology that may have been present in the phone calls that you’ve just\\n heard. I caution you that during his second time on the stand, Special\\n Agent James was providing only his opinion as an expert as to the\\n substance of those calls and phrases. The fact that he also possesses factual\\n information regarding this case should not be taken into account by you as\\n you determine what, if any, weight to decide to give Special Agent James’s\\n expert opinions. It’s for you to decide how much weight to give all of the\\n evidence, including fact and opinion testimony. Special Agent James's\\n testimony as a fact or expert witness is entitled to no greater or lesser\\n weight simply because he is an expert in one context and was previously\\n qualified to do so.\\n\\n You’ve just heard extensive testimony from Agent James. Agent James\\n was called and qualified and permitted to testify as an expert witness. His\\n field of expertise was drug and gang terminology in Maryland. Within that\\n zone of expertise, Agent James was permitted to offer you his opinions.\\n Specifically, he was allowed to tell you his interpretations based on his\\n training and experience as to the meaning of statements made by alleged\\n members of the Black Guerilla Family during telephone calls. You are\\n permitted to give Agent James’s expert opinions on the meaning of drug\\n and gang terminology, such weight as you may think they deserve.\\n\\n Ladies and gentlemen, I draw a distinction between the opinion testimony\\n about drug and gang terminology, and any more traditional fact testimony\\n that Agent James may have given earlier in this trial. During his previous\\n(Continued)\\n 11\\n\\f The jury convicted the Defendants on all charges. The jury specifically found\\n\\nBazemore and Hurtt responsible for multiple acts of first-degree murder, attempted\\n\\nmurder, conspiracy to commit murder, extortion, witness retaliation, and drug distribution\\n\\nas part of the racketeering conspiracy. S.J.A. 49, 53. The jury found Smith responsible\\n\\nfor extortion and drug distribution under the racketeering conspiracy. S.J.A. 56. The\\n\\ndistrict court sentenced Bazemore to life, Hurtt to 324 months, and Smith to 210 months.\\n\\n II.\\n\\n The Defendants challenge their convictions on two main grounds. First, they\\n\\nclaim that the district court improperly handled jurors’ fears for their safety. Second, the\\n\\nDefendants argue that the district court erred by allowing portions of Agent James’s\\n\\nexpert testimony. We reject each argument in turn.\\n\\n A. Juror Bias\\n\\n The Defendants fault the district court for how it addressed the jurors’ fears of\\n\\ngang retaliation. They claim the district court’s questioning of the jurors was inadequate\\n\\n\\n\\n\\n testimony he was not testifying as an expert, and he was not permitted to\\n offer expert opinions on the subjects then presented to him.\\n\\n If ever during this trial you thought you heard Agent James offer an expert\\n opinion on a subject outside the scope of drug and gang terminology in\\n Maryland, then I instruct you to disregard that testimony. Agent James’s\\n expert opinions are only allowed as to drug and gang terminology. On all\\n other topics on which he might have testified, he’s a fact witness and not\\n authorized to present expert opinions.\\n\\nJ.A. 1023–25.\\n\\n\\n 12\\n\\ffor failing to ask each juror expressly about Juror No. 5’s fears and discussions with other\\n\\njurors. Besides this process concern, the Defendants also object to the court’s ultimate\\n\\nrefusal to grant a mistrial.\\n\\n The Sixth Amendment guarantees a criminal defendant the right to a trial “by an\\n\\nimpartial jury.” U.S. CONST. amend. VI. This right requires a trial judge to remain\\n\\n“‘ever watchful to prevent prejudicial occurrences,’ and [he] therefore must conduct voir\\n\\ndire in a manner that adequately identifies unqualified or potentially biased jurors.”\\n\\nGardner v. Ozmint, 511 F.3d 420, 424 (4th Cir. 2007) (quoting Smith v. Phillips, 455\\n\\nU.S. 209, 217 (1982)).\\n\\n When a serious, non-speculative question of juror impartiality arises during trial,\\n\\nthe district court must determine whether the affected jurors remain fair and impartial.\\n\\nSee United States v. Thompson, 744 F.2d 1065, 1068 (4th Cir. 1984); Neal v. United\\n\\nStates, 22 F.2d 52, 53 (4th Cir. 1927). As the trial judge is in the best position to make\\n\\nthis determination, the inquiry is committed to his discretion, including ample leeway to\\n\\nformulate the questions to be asked. United States v. Barber, 80 F.3d 964, 967 (4th Cir.\\n\\n1996) (en banc).\\n\\n After learning of Juror No. 5’s fears, the district judge here questioned each juror\\n\\nindividually. That required balancing the need to detect bias against the concern that\\n\\ninartful questioning could itself generate bias. As the trial judge observed, detailed or\\n\\nfact-specific questions could “become the toxin by which the [jurors’] minds are\\n\\npoisoned and the fears are generated.” J.A. 1256. He thus asked about bias directly,\\n\\nwithout explicitly discussing Juror No. 5 or any fears of violent retaliation. In evaluating\\n\\n 13\\n\\ftheir responses, he considered the jurors’ reactions and, where necessary, followed up.\\n\\nSee, e.g., J.A. 1267–74 (asking more questions and discussing the juror’s demeanor).\\n\\nDistrict courts are encouraged to take this direct approach to detect bias in jurors. See,\\n\\ne.g., United States v. Caro, 597 F.3d 608, 615 (4th Cir. 2010). This trial judge made\\n\\nreasoned judgments in walking the line between detecting bias and creating bias. And we\\n\\nare not here to micro-manage those considered choices.\\n\\n Just as the trial judge has latitude in framing the inquiry, so too does he have broad\\n\\ndiscretion in evaluating the significance of potential juror bias. See Arizona v.\\n\\nWashington, 434 U.S. 497, 513–14 (1978) (discussing the “great deference” owed to a\\n\\ntrial judge’s decision to declare a mistrial based on possible juror bias). This trial judge\\n\\nmade appropriate inquiries into juror bias. He then excused those jurors who, by their\\n\\nanswers or demeanor, suggested they could not be fair and impartial. Left only with\\n\\njurors who had assured him of their continued impartiality, the trial judge acted well\\n\\nwithin his discretion in denying the requested mistrial. See United States v. Jones, 716\\n\\nF.3d 851, 857 (4th Cir. 2013) (noting that the court may rely on a juror’s assurance of\\n\\ncontinued impartiality if the court finds it credible).\\n\\n B. Agent James’s Expert Testimony\\n\\n The Defendants next argue that the district court abused its discretion in admitting\\n\\nportions of Agent James’s expert testimony. See United States v. Wilson, 484 F.3d 267,\\n\\n273 (4th Cir. 2007). The Defendants claim first that his experience-based linguistic\\n\\nopinions were not the product of a reliable methodology for interpreting coded jargon.\\n\\nSecond, they argue that Agent James impermissibly blended fact and expert testimony,\\n\\n 14\\n\\fcreating jury confusion and unfair prejudice. Third, they allege that Agent James served\\n\\nas a mere conduit for testimonial hearsay in violation of the Confrontation Clause. We\\n\\nreject each argument and also find harmless any instance in which Agent James may have\\n\\nstrayed outside the bounds of proper testimony.\\n\\n 1. Qualification and Methodology\\n\\n Agent James used a reliable methodology in forming his expert opinions. Federal\\n\\nRule of Evidence 702 permits expert testimony from “[a] witness who is qualified as an\\n\\nexpert by knowledge, skill, experience, training, or education” where the “specialized\\n\\nknowledge will help the trier of fact to understand the evidence or to determine a fact in\\n\\nissue” so long as the expert’s opinion is “based on sufficient facts or data,” is “the\\n\\nproduct of reliable principles and methods,” and the expert “has reliably applied the\\n\\nprinciples and methods to the facts.”\\n\\n Under Rule 702, a district court must ensure that the expert is qualified and that\\n\\nthe expert’s testimony is both relevant and reliable. Daubert v. Merrell Dow Pharm.,\\n\\nInc., 509 U.S. 579, 589 (1993). In performing this gatekeeping role, a district court “is\\n\\nnot intended to serve as a replacement for the adversary system, and consequently, the\\n\\nrejection of expert testimony is the exception rather than the rule.” In re Lipitor\\n\\n(Atorvastatin Calcium) Mktg., Sales Practices & Prod. Liab. Litig. (No II), 892 F.3d 624,\\n\\n631 (4th Cir. 2018) (citation and quotation marks omitted).\\n\\n We begin by recognizing that Agent James’s experience appropriately qualified\\n\\nhim to serve as an expert. Agent James was a twelve-year veteran of the FBI with\\n\\nsubstantial experience in drug and gang investigations (conducting controlled buys,\\n\\n 15\\n\\finterviewing drug dealers and gang members, using gang members as confidential\\n\\nsources, listening to thousands of recorded conversations, and so forth). Without\\n\\nobjection, the court qualified Agent James as an expert in drug and gang terminology in\\n\\nMaryland.\\n\\n Having found Agent James qualified, the district court explained that he applied a\\n\\nmethodology based on his extensive experience to understand the conversations. J.A.\\n\\n965G–H. Courts have consistently approved of law enforcement agents like Agent James\\n\\noffering expert interpretations of gang and drug communications based on their\\n\\nexperience. United States v. Galloway, 749 F.3d 238, 245 (4th Cir. 2014) (accepting\\n\\nagents’ “method of applying their extensive experience to analyze the meaning of the\\n\\n[drug-related] conversations through context”); see also United States v. Palacios, 677\\n\\nF.3d 234, 242 (4th Cir. 2012); United States v. Baptiste, 596 F.3d 214, 222–23 (4th Cir.\\n\\n2010); Wilson, 484 F.3d at 274–75. The district court here correctly approved of Agent\\n\\nJames’s methodology for interpreting gang and drug calls based on his experience.\\n\\n The conclusion that Agent James employed a sound methodology is only one step\\n\\nin our analysis. We must also decide whether he reliably applied it to the facts in forming\\n\\nhis expert opinions. Fed. R. Evid. 702(d). As the district court rightly concluded, Agent\\n\\nJames reliably applied his methodology. See Wilson, 484 F.3d at 274 (noting the district\\n\\ncourt’s “broad latitude” in determining whether the expert’s methodology is reliable).\\n\\nFor example, in the first call on March 10, 2014, between Bazemore and Harrington,\\n\\nAgent James interpreted the phrase “special light” as “a green light,” which he described\\n\\n\\n\\n 16\\n\\fas an authorization used by gang members to kill another person. J.A. 971. 6 He based\\n\\nthat interpretation on his experience with other investigations as well as the context of\\n\\nthis investigation.\\n\\n In the same manner, Agent James applied his experience to interpret various other\\n\\ncoded terms like “Unc,” “rolled out of JI,” “burnt,” and “checking in.” See, e.g., J.A. 977\\n\\n(explaining that “JI” is a housing unit in the city jail and that “[g]etting rolled out of JI is\\n\\ngetting moved out of that section of the city jail”). In doing so, Agent James provided a\\n\\nbasis for his interpretation, rendering it both susceptible to scrutiny by the district court\\n\\nand to being challenged on cross examination by the Defendants.\\n\\n Agent James did not always point to a specific experience that informed each\\n\\nexpert opinion. This is unsurprising. Agent James based his interpretations on years of\\n\\ninvestigatory experience and exposure to thousands of gang and drug conversations. The\\n\\napplication of this experience to analyze the meaning of certain terms does not lend itself\\n\\nto a direct correlation between one experience and one opinion. This is much like how\\n\\nforeign-language experts, such as Spanish interpreters, apply their training and\\n\\nexperience to analyze the meaning of conversations. Those experts do not translate based\\n\\non any one piece of information or learned treatise (like a dictionary) but analyze and\\n\\nsynthesize an array of information learned over years.\\n\\n\\n 6\\n The Defendants vacillate between conceding that Agent James could interpret\\n“special light,” see Reply at 11; J.A. 967, and challenging even this interpretation of\\n“special light,” see Reply at 13. Regardless, we find the court properly admitted this\\nimportant testimony.\\n\\n\\n 17\\n\\f Whether one considers Agent James more like a foreign-language interpreter or an\\n\\nanthropologist who studies a group by educating himself and conducting fieldwork, see\\n\\nUnited States v. Mejia, 545 F.3d 179, 190 (2d Cir. 2008) (analogizing a gang expert to an\\n\\nanthropologist), his expertise does not derive from any singular piece of information. As\\n\\nit would be impossible to ask this expert to lay such a precise foundation for an opinion\\n\\nwhen his expertise was gained over extended, repeated exposure, we cannot say that the\\n\\ndistrict court abused its discretion in concluding that Agent James reliably applied his\\n\\nmethodology.\\n\\n 2. Blending Facts and Expert Opinions\\n\\n The Defendants also argue that Agent James improperly blended expertise with\\n\\nfactual testimony. To be sure, while serving as an expert, Agent James did at times\\n\\ntestify to facts he learned as a participant in the investigation. This dual-role testimony—\\n\\nlike all testimony—requires a determination of whether “its probative value is\\n\\nsubstantially outweighed” by the risk of unfair prejudice or jury confusion. Fed. R. Evid.\\n\\n403. To maintain this Rule 403 balance, district courts must be vigilant to avoid the\\n\\ndanger of confusing the jury when a case agent testifies as an expert. See Wilson, 484\\n\\nF.3d at 278 n.5.\\n\\n That is why we have directed district courts to take steps to provide the jury clarity\\n\\nabout the dual roles. United States v. Baptiste, 596 F.3d 214, 224 (4th Cir. 2010). As\\n\\nexamples of safeguards the district court may employ, we have suggested “requiring the\\n\\nwitness to testify at different times, in each capacity; giving a cautionary instruction to\\n\\nthe jury regarding the basis of the testimony; allowing for cross-examination by defense\\n\\n 18\\n\\fcounsel; establishing a proper foundation for the expertise; or having counsel ground the\\n\\nquestion in either fact or expertise while asking the question.” United States v. Garcia,\\n\\n752 F.3d 382, 392 (4th Cir. 2014). None of the options on this list are necessary or per se\\n\\nsufficient. Id. (noting that precautions may be insufficient to mitigate the risk of jury\\n\\nconfusion and prejudice resulting from a given agent’s expert and fact testimony). The\\n\\nultimate question is whether, considering the safeguards used, the testimony’s “probative\\n\\nvalue is substantially outweighed” by the risk of jury confusion or unfair prejudice. Fed.\\n\\nR. Evid. 403.\\n\\n Before considering the district court’s implemented safeguards, it bears\\n\\nmentioning that certain instances of Agent James’s fact testimony were not only\\n\\npermissible but indeed necessary to provide context for his interpretations of the\\n\\nintercepted calls. An expert’s methodology cannot be applied in a factual vacuum. Thus,\\n\\nan expert in code or language must consider the context surrounding the language in\\n\\ndetermining the appropriate interpretation. See, e.g., Galloway, 749 F.3d at 245\\n\\n(approving analysis of the “context” of communications); Wilson, 484 F.3d at 275–76\\n\\n(approving consideration of the “situation” surrounding a call). As anyone teaching a\\n\\nchild to read can attest, context often provides invaluable clues to understanding the\\n\\nmeaning of words. Cf. PEGGY PARISH, AMELIA BEDELIA (1963) (humorous tale of a\\n\\nmaid who misinterprets various commands; for example, when asked to “draw the\\n\\ndrapes,” she sketches a picture of them); FRED GWYNNE, THE KING WHO RAINED (1970)\\n\\n(illustrations of a bewildered young girl who gets tripped up over homophones; for\\n\\n\\n\\n 19\\n\\fexample, “a king who rained for forty years” shown as a king floating in the sky as a rain\\n\\ncloud).\\n\\n This context includes the date and time of the intercepted call along with the\\n\\nsequence of calls: for example, the fact that certain calls occurred on the same day and\\n\\none immediately followed the other. Indeed, given the obvious need for this type of\\n\\ncontext, the Defendants necessarily conceded that Agent James could provide this factual\\n\\ncontext during his expert testimony. 7\\n\\n But appropriate factual context is not limited to a call’s date and time. It includes\\n\\nother contextual information such as the identity of the callers. And along with date,\\n\\ntime, and participants, the context of a conversation also includes the surrounding\\n\\ncircumstances, like whether a participant in the call was incarcerated or whether police\\n\\nfound a man shot shortly after a call seemingly authorized a shooting. Far from\\n\\ngenerating confusion for the jury, including this factual context reduced the risk of jury\\n\\nconfusion by providing a more coherent narrative of the investigation and a proper\\n\\nframework for Agent James’s expert opinions.\\n\\n\\n\\n\\n 7\\n While the use of context as part of the expert’s analysis is permissible, an agent\\nexpert may not rely exclusively on the surrounding events to provide an expert\\ninterpretation of the call. See Garcia, 752 F.3d at 393 (criticizing an agent’s testimony\\nthat “a hundred forty five point” meant 145 grams of heroin apparently based solely on a\\nlater seizure of 145 grams of heroin; the agent applied no expertise and, in any event, the\\nwords did not require decoding).\\n\\n\\n 20\\n\\f The Defendants suggest that the factual context surrounding the calls must come\\n\\nsolely from independent evidence. 8 In other words, the Defendants want to preclude any\\n\\ncontext coming from Agent James’s own factual observations. This novel suggestion—\\n\\nthat an expert may only consider “independently verified” evidence—can be rejected by\\n\\nreading the plain text of Rule 703, which provides that an “expert may base an opinion on\\n\\nfacts or data in the case that the expert has been made aware of or personally observed.”\\n\\nFed. R. Evid. 703 (emphasis added). 9\\n\\n Balancing the need for factual context for Agent James’s opinions and the risk in\\n\\nblending expert and factual testimony, the Government and the district court here took\\n\\neffective steps to mitigate any jury confusion or unfair prejudice to the Defendants.\\n\\nBaptiste, 596 F.3d at 224. Despite the broad scope of the investigation and charges, the\\n\\nGovernment focused Agent James’s expert testimony on calls related to a single incident:\\n\\n\\n 8\\n Some caller identifications used by Agent James stemmed from evidence\\notherwise admitted at trial (e.g., a co-conspirator identified the phone number or voice),\\nbut others followed from Agent James’s own knowledge as a percipient witness.\\nSimilarly, circumstances surrounding the context of a call sometimes came from\\nindependently admitted evidence and sometimes from his own factual observations.\\n 9\\n The Defendants are also incorrect in contending that in forming his opinions,\\nAgent James was limited to relying on admissible evidence. An expert may rely on\\ninadmissible evidence, including hearsay. See United States v. Leeson, 453 F.3d 631,\\n637 (4th Cir. 2006); see also Fed. R. Evid. 703. In particular, we have repeatedly held\\nthat an agent may rely on testimonial hearsay in forming his expert opinions. Palacios,\\n677 F.3d at 242–43; see also United States v. Johnson, 587 F.3d 625, 635 (4th Cir. 2009)\\n(observing that the Confrontation Clause “forbids the introduction of testimonial hearsay\\nas evidence in itself, but it in no way prevents expert witnesses from offering their\\nindependent judgments merely because those judgments were in some part informed by\\ntheir exposure to otherwise inadmissible evidence”).\\n\\n\\n 21\\n\\fthe attempted murder of Hall. The Government also agreed to call Agent James to the\\n\\nwitness stand twice, first as a percipient witness and later as a qualified expert. By\\n\\nlimiting the breadth of the expert testimony and separating in time his fact and expert\\n\\ntestimony, the Government cabined any potential confusion or unfair prejudice. See\\n\\nWilson, 484 F.3d at 278 n.5.\\n\\n The district court further limited the scope of Agent James’s expert opinions about\\n\\nthe calls related to the shooting by admonishing the Government to avoid “stray[ing] into\\n\\noffering opinions more broadly about what the plotters and schemers [were] up to,” J.A.\\n\\n1004, and sustaining objections when the Government approached that line, see J.A. 972,\\n\\n996–97. In doing so, the court limited any unfair prejudice that arose from Agent\\n\\nJames’s knowledge of the investigation. The court also provided the Defendants an\\n\\nopportunity to cross-examine Agent James, which they could have used to probe his\\n\\nexpert opinions. Yet they declined that opportunity. Finally, the district court provided a\\n\\nthorough instruction to the jury on the importance of distinguishing fact testimony from\\n\\nexpert opinions, insulating it from the risk of confusion. See Baptiste, 596 F.3d at 224;\\n\\nUnited States v. Farmer, 543 F.3d 363, 370–71 (7th Cir. 2008). In sum, based on the\\n\\ncircumstances here, the district court properly performed its gatekeeping role and avoided\\n\\nhaving unfair prejudice and jury confusion substantially outweigh the probative value of\\n\\nthe narrow expert testimony offered. See Fed. R. Evid. 403.\\n\\n 3. Confrontation Clause\\n\\n Despite the district court’s efforts to avoid juror confusion and unfair prejudice,\\n\\nAgent James’s testimony would have been improper if it served simply as a conduit for\\n\\n 22\\n\\ftestimonial hearsay. Garcia, 752 F.3d at 394–95; Johnson, 587 F.3d at 635. A direct\\n\\ntransmission of testimonial hearsay to the jury—as opposed to reliance on testimonial\\n\\nhearsay as part of proper expert opinion—would violate the Confrontation Clause.\\n\\nJohnson, 587 F.3d at 634–36 (discussing Crawford v. Washington, 541 U.S. 36 (2004)).\\n\\nTo determine whether an expert’s testimony raises a Confrontation Clause issue, we look\\n\\nfor indicia that the expert is giving an independent judgment and not “merely acting as a\\n\\ntransmitter for testimonial hearsay.” Id.\\n\\n The Defendants claim that Agent James’s expert testimony was improper under\\n\\nour decision in Garcia. In that drug-conspiracy case, the Government’s evidence\\n\\nconsisted primarily of law enforcement surveillance and recordings of wiretapped calls.\\n\\nGarcia, 752 F.3d at 385–86. To interpret the calls, the Government called an FBI agent\\n\\nto opine on the meaning of the conversations, many of which were in Spanish. In doing\\n\\nso, the agent admitted to debriefing three co-conspirators during the investigation to\\n\\nconfirm her understanding of the code. Id. at 394. Garcia claimed the agent’s\\n\\ninterpretations impermissibly transmitted that testimonial hearsay rather than providing\\n\\nindependent judgment about the meaning of coded terms. Given the apparent reliance on\\n\\nco-conspirator debriefings, we found that “it was incumbent upon the Government to\\n\\ndemonstrate that [the agent] was not merely channeling information and statements by\\n\\nnon-testifying participants in the conspiracy into the trial record.” Id. After reviewing\\n\\nthe record, we concluded that it was “devoid of evidence” that the agent used the\\n\\ndebriefings only to confirm her understandings rather than to serve as the sole basis of\\n\\nthose opinions. Id. at 395. We therefore found error in admitting the testimony.\\n\\n 23\\n\\f But Agent James’s testimony materially differs from that in Garcia. Agent James\\n\\napplied his own judgment to interpret the conversations in question; he was not simply\\n\\nrelaying the conspirators’ interpretations. Nothing from Agent James’ testimony\\n\\nsuggests he relied at all on co-conspirator interviews. In contrast, the record reveals that\\n\\nhis interpretation of the code between Bazemore and Harrington turned on his own\\n\\nexpertise given that, minutes after the calls on March 10, 2014, he alerted local\\n\\nauthorities. This timing confirms that Agent James exercised his judgment independent\\n\\nof any later debriefings. Not surprisingly, later developments—such as the discovery of a\\n\\nwounded Ronald Hall and jailhouse calls about the authorization to shoot Hall—\\n\\nconfirmed his own interpretations. These are all indicia that the interpretations were not\\n\\nregurgitations of inadmissible testimonial hearsay. There were no Confrontation Clause\\n\\nproblems with Agent James’s testimony.\\n\\n 4. Harmless Error\\n\\n Even if some of Agent James’s testimony went beyond the plainly permissible,\\n\\nthat limited testimony would be harmless. See United States v. White, 810 F.3d 212, 228\\n\\n(4th Cir. 2016) (“Ultimately, the question is whether we can say ‘with fair assurance,\\n\\nafter pondering all that happened without stripping the erroneous action from the whole,\\n\\nthat the jurors’ judgment was not substantially swayed by the error.’” (quoting Kotteakos\\n\\nv. United States, 328 U.S. 750, 765 (1946)).\\n\\n To begin with, Agent James’s expert opinions applied only to calls establishing\\n\\nBazemore’s involvement in the attempted murder of Hall. So any error would not affect\\n\\n\\n\\n 24\\n\\fthe convictions of Smith and Hurtt. But even for Bazemore, we find harmless any\\n\\nimproper opinion testimony from Agent James.\\n\\n At times, Agent James’s testimony contained interpretations of conversations\\n\\nbetween gang members without code. For example, Agent James interpreted “[a]nd\\n\\nthey’re trying to do something to Shorty for something he did” as “[h]e’s saying that [the\\n\\ngang] is trying to do something to Mr. Harrington for something Mr. Harrington did.”\\n\\nJ.A. 989. Agent James also interpreted some ambiguous words, including determining\\n\\nthat the word “yo” had a few different meanings. 10 In doing so, Agent James purported\\n\\nto offer expert interpretations but actually provided explanations based on his knowledge\\n\\nof this specific investigation. While lay opinion testimony may be combined with expert\\n\\nopinion testimony, doing so generally requires a more substantial foundation to\\n\\ndistinguish between lay opinion and expert opinion. 11\\n\\n\\n 10\\n Agent James gave several interpretations of the flexible pronoun “yo.” For one\\nparticular intercepted call, Agent James explained that “the yo” referred to the shooting\\nof Hall; “yo told me” referred to Bazemore; “that yo” referred to Hall himself; and\\n“holler at yo” referred to Bazemore. See J.A. 981 (“I already talked -- talked to him\\nabout the yo -- yo told me you not -- that yo not right point blank. He -- he -- he gave you\\nall the oaths, okay, so anybody got a problem with it, holler at yo.”). At other times,\\nAgent James also interpreted “yo” to refer to shooting Hall. J.A. 1007. These meanings\\nare not inherently inconsistent given the elasticity of the indefinite “yo.” Even so, these\\ninterpretations do appear to assert information learned as the case agent under the guise\\nof expert opinion. See supra n.7 (distinguishing between the proper use of context to\\ninform an expert opinion from the improper use of personal knowledge as the sole basis\\nfor the opinion); Garcia, 752 F.3d at 393. Context may help form the basis for an expert\\nopinion, but context must not be mistaken for expertise itself.\\n 11\\n Vigilantly safeguarding against jury confusion and unfair prejudice does not\\nrequire a blanket prohibition against an expert witness also offering lay opinions. See,\\ne.g., United States v. Freeman, 498 F.3d 893, 904 (9th Cir. 2007) (permitting an agent to\\n(Continued)\\n 25\\n\\f In any event, we need not determine which portions of this type of testimony were\\n\\nin error because we find that they would have been harmless. See Wilson, 484 F.3d at\\n\\n278 (finding harmless any error in admitting portions of an agent’s expert testimony\\n\\nwhen the “overwhelming majority” of the “testimony was properly admitted”). This was,\\n\\nafter all, not a close case.\\n\\n The jury heard considerable evidence that Bazemore ordered the attempted murder\\n\\nof Hall, leading us to conclude that any oversteps in Agent James’s testimony did not\\n\\nsubstantially sway the jury. That evidence includes (1) the first call on March 10, 2014,\\n\\nwhich Agent James properly interpreted as seeking authorization to kill; (2) the second\\n\\ncall on March 10, 2014, in which Bazemore instructed Harrington to “[g]o ahead and do\\n\\nit,” played at trial without interpretation; (3) the testimony of Detective Bomenka, who\\n\\ndiscussed finding a wounded Hall in Lakeland shortly after Agent James alerted\\n\\nBaltimore Police; (4) the testimony of Bazemore’s co-conspirator Gray, who implicated\\n\\nBazemore as having ordered Harrington to shoot Hall; and (5) the jailhouse calls\\n\\n\\n\\n\\noffer both expert and lay opinion testimony and stating that “the use of case agents as\\nboth expert and lay witnesses is not so inherently suspect that it should be categorically\\nprohibited”). Indeed, “[t]estimony of this kind may save time and expense, and will not\\nnecessarily result in juror confusion, provided that the district court engages in vigilant\\ngatekeeping.” Id.\\n We have yet to address directly how a court should manage an expert offering\\nboth expert interpretation of coded conversations and lay opinions of ambiguous or vague\\nstatements. See id. at 902. The district court here largely kept out Agent James’s lay\\nopinions and we leave for another day the best manner for district courts to safeguard\\nagainst the potential dangers from dual-opinion testimony.\\n\\n\\n 26\\n\\fdiscussing the authorization. Taken together, this evidence paints a strong evidentiary\\n\\npicture that Bazemore authorized Harrington to shoot Hall. 12\\n\\n * * *\\n\\n After a long trial, the jury convicted the Defendants based on voluminous\\n\\nevidence of participating in a broad conspiracy that involved widespread drug dealing\\n\\nand acts of violence. Throughout, the district court made every effort to afford the\\n\\nDefendants a fair trial. The Defendants’ challenges to their convictions do not call into\\n\\nquestion the fairness of the proceeding.\\n\\n For the reasons given, the district court’s judgment as to each Defendant is\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 12\\n Two additional claims need not detain us long. First, Hurtt argues that a passing\\nreference by a Government witness to Hurtt being previously “locked up” required a\\nmistrial. This singular stray reference to Hurtt’s prior incarceration did not amount to\\nprejudicial testimony requiring a mistrial. See United States v. Hayden, 85 F.3d 153, 158\\n(4th Cir. 1996). Second, Bazemore argues that his sentence was substantively\\nunreasonable, but he fails to rebut the presumption that his within-Guidelines sentence\\nwas reasonable considering the factors set forth in 18 U.S.C. § 3553(a). See United\\nStates v. Louthian, 756 F.3d 295, 306 (4th Cir. 2014). We find the district court did not\\nabuse its discretion in either denying Hurtt’s requested mistrial or sentencing Bazemore\\nto life in prison.\\n\\n 27\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1071,"cells":{"id":{"kind":"number","value":4604710,"string":"4,604,710"},"name":{"kind":"string","value":"UNITED STATES of America, Plaintiff - Appellee, v. Jose Benjamin GUZMAN-VELASQUEZ, Defendant - Appellant."},"name_abbreviation":{"kind":"string","value":"United States v. Jose Guzman-Velasquez"},"decision_date":{"kind":"string","value":"2019-03-28"},"docket_number":{"kind":"string","value":"18-4133"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Motz, Quattlebaum, Duncan\", \"parties\": \"\", \"opinions\": [{\"author\": \"DIANA GRIBBON MOTZ, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-4133\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\n v.\\n\\nJOSE BENJAMIN GUZMAN-VELASQUEZ,\\n\\n Defendant - Appellant.\\n\\n\\nAppeal from the United States District Court for the Eastern District of Virginia, at\\nRichmond. M. Hannah Lauck, District Judge. (3:16-cr-00151-MHL-1)\\n\\n\\nArgued: January 31, 2019 Decided: March 28, 2019\\n\\n\\nBefore MOTZ and QUATTLEBAUM, Circuit Judges, and DUNCAN, Senior Circuit\\nJudge.\\n\\n\\nAffirmed by published opinion. Judge Motz wrote the opinion, in which Judge\\nQuattlebaum and Senior Judge Duncan joined.\\n\\n\\nARGUED: Laura Jill Koenig, OFFICE OF THE FEDERAL PUBLIC DEFENDER,\\nRichmond, Virginia, for Appellant. Daniel Taylor Young, OFFICE OF THE UNITED\\nSTATES ATTORNEY, Alexandria, Virginia, for Appellee. ON BRIEF: Geremy C.\\nKamens, Federal Public Defender, OFFICE OF THE FEDERAL PUBLIC DEFENDER,\\nAlexandria, Virginia, for Appellant. G. Zachary Terwilliger, United States Attorney,\\nAlexandria, Virginia, S. David Schiller, OFFICE OF THE UNITED STATES\\nATTORNEY, Richmond, Virginia, for Appellee.\\n\\fDIANA GRIBBON MOTZ, Circuit Judge:\\n\\n When Jose Benjamin Guzman-Velasquez returned to the United States after being\\n\\ndeported, the government charged him with the crime of illegal reentry. Guzman moved\\n\\nto dismiss the indictment, relying solely on United States v. Mendoza-Lopez, 481 U.S.\\n\\n828 (1987), which held that an administrative removal proceeding marred by due process\\n\\ndefects that foreclosed judicial review could not serve as a basis for criminal conviction.\\n\\nThe district court denied Guzman’s motion. For the reasons that follow, we affirm.\\n\\n\\n\\n I.\\n\\n On December 31, 1998, Guzman, a citizen of El Salvador, entered the United\\n\\nStates without authorization. That same day, the federal government initiated removal\\n\\nproceedings. An immigration judge granted Guzman voluntary departure; when he failed\\n\\nto timely depart, the grant converted into a removal order.\\n\\n Approximately a year later, in response to a series of earthquakes, Attorney\\n\\nGeneral John Ashcroft designated El Salvador for the Temporary Protected Status (TPS)\\n\\nprogram. See 66 Fed. Reg. 14,214, 14,214 (Mar. 9, 2001). TPS “allows eligible\\n\\nnationals of a foreign state to temporarily remain in the United States during the\\n\\npendency of that state’s designation.” Cervantes v. Holder, 597 F.3d 229, 231 (4th Cir.\\n\\n2010). Once granted, the government “shall not remove” an individual with TPS.\\n\\n8 U.S.C. § 1254a(a)(1)(A). Salvadorans were eligible for TPS if they “ha[d] been\\n\\n‘continuously physically present’ in the United States since March 9, 2001,” “ha[d]\\n\\n‘continuously resided’ in the United States since February 13, 2001,” and satisfied other\\n\\n 2\\n\\fstatutory requirements. 66 Fed. Reg. at 14,214 (quoting 8 U.S.C. §§ 1254a(c)(1)(A)(i)\\n\\nand (ii)).\\n\\n Guzman’s attorney submitted a TPS application on his behalf. The Immigration\\n\\nand Naturalization Service (INS) requested additional documentation as to Guzman’s\\n\\ncontinuous physical presence and continuous residence in the United States. Although\\n\\nthe relevant documentation was present in the INS’s file, it was not appended to the TPS\\n\\napplication as required, and Guzman’s attorney did not timely respond to the inquiry.\\n\\n As a result, United States Citizenship and Immigration Services (USCIS) 1 denied\\n\\nGuzman’s TPS application. The agency notified Guzman’s lawyer that he could appeal\\n\\nwithin 30 days and indicated that it had also mailed a notice to Guzman. But Guzman did\\n\\nnot appeal, and in 2007, he was removed. He returned without authorization sometime\\n\\nthereafter and was convicted of three state crimes, rendering him ineligible for TPS.\\n\\n In 2016, a grand jury returned a federal criminal indictment charging Guzman\\n\\nwith felony illegal reentry in violation of 8 U.S.C. § 1326(a). Guzman moved to dismiss\\n\\nthe indictment, relying on Mendoza-Lopez. The parties stipulated that at the time\\n\\nGuzman applied for TPS in 2002, he satisfied all the requirements and that, had USCIS\\n\\nreviewed his full immigration file, he “should have been granted” TPS.\\n\\n The district court denied Guzman’s motion to dismiss the indictment. It reasoned\\n\\nthat Mendoza-Lopez permitted collateral attacks only against removal orders, not TPS\\n\\n 1\\n After the INS’s request for evidence but before its final decision, Congress\\nabolished the INS and created USCIS, in which it vested responsibility for adjudication\\nof immigration benefits. Homeland Security Act of 2002, Pub. L. No. 107–296, § 451,\\n116 Stat. 2135, 2195 (codified as amended at 6 U.S.C. § 271).\\n\\n 3\\n\\fdenials. In the alternative, the court relied on a basis not briefed by the Government: it\\n\\nheld that 8 U.S.C. § 1252, which limits district court jurisdiction to review immigration\\n\\ndeterminations, also deprived the court of jurisdiction to consider Guzman’s defense to\\n\\nhis criminal charge. Reserving the right to seek our review, Guzman pled guilty and\\n\\ntimely noted this appeal.\\n\\n\\n\\n II.\\n\\n We review de novo a denial of a motion to dismiss an illegal reentry indictment.\\n\\nUnited States v. El Shami, 434 F.3d 659, 663 (4th Cir. 2005). Before undertaking this\\n\\nreview, we first outline the statutory and constitutional history at issue.\\n\\n The Government must prove two elements to convict a defendant of felony illegal\\n\\nreentry: (1) the defendant was “deported[] or removed” 2 from the United States “while\\n\\nan order of . . . deportation[] or removal [was] outstanding,” and (2) the defendant\\n\\nsubsequently “enter[ed], attempt[ed] to enter, or [was] at any time found in, the United\\n\\nStates” without authorization. 8 U.S.C. § 1326(a). Guzman asserts a due process\\n\\nchallenge to a portion of the first element of the crime: the fact of a previous removal.\\n\\n Under current law, this removal element requires proof of both a prior removal\\n\\nand the existence of an outstanding removal order. However, this was not the case when\\n\\nthe Supreme Court decided Mendoza-Lopez. At that time, § 1326 made no reference to\\n\\nremoval orders: the removal element required only that the defendant had “been arrested\\n\\n 2\\n The terms “removal” and “deportation” are interchangeable for the purposes of\\n§ 1326. United States v. Moreno-Tapia, 848 F.3d 162, 165 n.1 (4th Cir. 2017).\\n\\n 4\\n\\fand deported or excluded and deported.” Mendoza-Lopez, 481 U.S. at 830 (quoting\\n\\n8 U.S.C. § 1326 (1982)); see also Omnibus Consolidated Appropriations Act, 1997, Pub.\\n\\nL. No. 104–208, § 324(a), 110 Stat. 3009, 3009-629 (1996) (amending § 1326(a) to add\\n\\nfirst reference to deportation orders). Nor did § 1326, as a statutory matter, require a\\n\\nshowing that the defendant’s prior removal was lawful. Mendoza-Lopez, 481 U.S. at\\n\\n834–37.\\n\\n Even so, the Mendoza-Lopez Court held that the Due Process Clause entitles a\\n\\ndefendant, under certain circumstances, to challenge the validity of an underlying\\n\\ndeportation order in a criminal prosecution “in which th[e] prior deportation is an element\\n\\nof the crime.” Id. at 833. The Court explained that “where a determination made in an\\n\\nadministrative proceeding is to play a critical role in the subsequent imposition of a\\n\\ncriminal sanction,” due process requires “some meaningful review of the administrative\\n\\nproceeding.” Id. at 837–38 (collecting cases). Thus, when a deportation hearing is “not\\n\\nconducted in conformity with due process,” and the due process defects “foreclose\\n\\njudicial review of that proceeding,” then the deportation proceeding “may not be used to\\n\\nsupport a criminal conviction” for illegal reentry. Id. at 834, 838, 842.\\n\\n Congress responded to Mendoza-Lopez in 1996 by enacting 8 U.S.C. § 1326(d).\\n\\nAntiterrorism and Effective Death Penalty Act of 1996, Pub. L. No. 104–132, § 441(a),\\n\\n110 Stat. 1214, 1279 (codified at 8 U.S.C. § 1326(d)). Under this statute, a defendant in\\n\\nan illegal reentry prosecution may, as a statutory defense, collaterally attack the order\\n\\nunderlying his prior removal if he shows that (1) he exhausted any available\\n\\nadministrative remedies against the removal order, (2) he was “improperly deprived . . .\\n\\n 5\\n\\fof the opportunity for judicial review” in his removal proceeding, and (3) “the entry of\\n\\nthe [removal] order was fundamentally unfair.” 8 U.S.C. § 1326(d) (emphasis added).\\n\\nThese statutory requirements are identical to the constitutional standards that many courts\\n\\napplied, prior to § 1326(d)’s enactment, in Mendoza-Lopez challenges to removal orders.\\n\\nSee, e.g., United States v. Encarnacion-Galvez, 964 F.2d 402, 406–07 (5th Cir. 1992).\\n\\n\\n\\n III.\\n\\n As Guzman acknowledges, § 1326(d) offers him no refuge: its plain text limits\\n\\ncollateral challenges to removal orders, and Guzman does not question the validity of his\\n\\nremoval order. He instead challenges USCIS’s denial of TPS as violative of the Due\\n\\nProcess Clause under Mendoza-Lopez.\\n\\n Before reaching the merits of this argument, we pause to consider whether federal\\n\\ndistrict courts have the power to evaluate such a claim. The district court held that it\\n\\nlacked jurisdiction to hear Guzman’s challenge because Congress has eliminated district\\n\\ncourts’ jurisdiction to review TPS determinations. Although this may appear to be the\\n\\ncase, it conflates the underlying determination and the specific procedural context in\\n\\nwhich this appeal arose.\\n\\n While the statute on which the district court relied, 8 U.S.C. § 1252, limits only a\\n\\ncourt’s jurisdiction to review immigration determinations, it says nothing about\\n\\njurisdiction to hear a challenge to a criminal indictment. To the contrary, another federal\\n\\nstatute, 18 U.S.C. § 3231, vests district courts with original jurisdiction over criminal\\n\\nproceedings. Thus, district courts regularly hear constitutional challenges to criminal\\n\\n 6\\n\\findictments like the one at hand. See, e.g., United States v. Staten, 666 F.3d 154, 156–68\\n\\n(4th Cir. 2011) (affirming district court’s resolution, on the merits, of Second\\n\\nAmendment challenge to indictment); United States v. Gould, 568 F.3d 459, 462, 470–75\\n\\n(4th Cir. 2009) (same regarding Commerce Clause challenge); United States v. Jefferson,\\n\\n546 F.3d 300, 306–14 (4th Cir. 2008) (same regarding Speech or Debate Clause\\n\\nchallenge).\\n\\n Moreover, there is “no support for the contention” that § 1252’s “withdraw[al] [of]\\n\\njurisdiction over the original deportation order reaches collateral challenges to a criminal\\n\\ncharge for illegal reentry,” regardless of how novel (or even meritless) the challenge may\\n\\nbe. United States v. Charleswell, 456 F.3d 347, 352 n.4 (3d Cir. 2006). After all, it is a\\n\\ncardinal principle that “repeals by implication are not favored and will not be presumed\\n\\nunless the intention of [Congress] to repeal is clear and manifest.” Hui v. Castaneda, 559\\n\\nU.S. 799, 810 (2010) (internal quotation marks omitted). Thus, to our knowledge, until\\n\\nthis case no court has ever construed § 1252 to impliedly repeal § 3231.\\n\\n Indeed, to do so by extending § 1252’s jurisdictional limitations would raise\\n\\n“[s]erious constitutional concerns.” Charleswell, 456 F.3d at 352 n.4. This is so because\\n\\nit would permit Congress to enact a criminal statute and then prohibit courts from\\n\\nexercising jurisdiction over a constitutional challenge to that statute. The Supreme Court\\n\\nhas long recognized that such restrictions on first-instance judicial review of\\n\\nconstitutional claims are problematic, even in immigration proceedings. See, e.g., INS v.\\n\\nSt. Cyr, 533 U.S. 289, 305 (2001) (teaching that “a serious Suspension Clause issue\\n\\n\\n\\n 7\\n\\fwould be presented” if Congress withdrew all judicial review of “pure questions of law”\\n\\nin immigration proceedings). Surely, they are at least as troubling in a criminal context.\\n\\n Furthermore, the district court’s interpretation would lead to absurd results.\\n\\nSection 1252 provides that “a petition for review filed with an appropriate court of\\n\\nappeals” is “the sole and exclusive means for judicial review of an order of removal.”\\n\\n8 U.S.C. § 1252(a)(5). Thus, if we were to endorse an interpretation of this statute that\\n\\nconflated judicial review of immigration determinations with collateral challenges in\\n\\ncriminal proceedings, no district court would have jurisdiction to hear any Mendoza-\\n\\nLopez or § 1326(d) challenge — even one identical to that in Mendoza-Lopez itself. This\\n\\ncannot be so. Mendoza-Lopez announced a constitutional due process right that Congress\\n\\nmay not abrogate.\\n\\n Guzman did not ask the district court to grant him relief from removal; he raised a\\n\\nconstitutional challenge to a criminal charge. Notwithstanding § 1252, the district court\\n\\nhad jurisdiction to consider his argument.\\n\\n\\n\\n IV.\\n\\n We now turn to the merits. Guzman urges us to decide a constitutional question of\\n\\nfirst impression: does the Mendoza-Lopez due process principle extend beyond removal\\n\\norders to authorize constitutional challenges to TPS denials within criminal prosecutions\\n\\nfor illegal reentry?\\n\\n Guzman asserts that the denial of his TPS application violated due process and he\\n\\nwas deprived of judicial review of the decision. In support of his view that Mendoza-\\n\\n 8\\n\\fLopez authorizes this collateral attack, Guzman relies on the Court’s generalized\\n\\ndiscussion of due process constraints on “administrative proceeding[s]” that play a\\n\\n“critical role” in a subsequent criminal prosecution. Mendoza-Lopez, 481 U.S. at 837–\\n\\n38. The Government counters that Mendoza-Lopez addresses infirmities in “deportation\\n\\nproceedings and nothing more.” Gov. Br. 30. Although the Third Circuit has interpreted\\n\\nMendoza-Lopez to permit collateral attack against removal orders and reinstatement\\n\\norders, see Charleswell, 456 F.3d at 352, we are aware of no court that has considered\\n\\nwhether Mendoza-Lopez reaches challenges to TPS determinations as well.\\n\\n We need not resolve this novel question. Even assuming that Mendoza-Lopez\\n\\npermits a constitutional challenge here, Guzman’s claim fails at a more basic level: he\\n\\nhas not asserted a due process violation that would render the adjudication of his TPS\\n\\napplication fundamentally unfair. See Mendoza-Lopez, 481 U.S. at 837–40.\\n\\n On appeal, Guzman’s sole claim of fundamental unfairness is that USCIS violated\\n\\nhis due process right to have the agency “fairly and thoroughly review the materials in\\n\\nthe government’s possession” when evaluating his TPS application. But if Guzman had a\\n\\ndue process right to fair and thorough review, it would only require USCIS to review the\\n\\nmaterials within his TPS application. USCIS did exactly that: it reviewed Guzman’s\\n\\nsubmission, found it to be lacking, requested additional evidence to no avail, and only\\n\\nthen denied relief.\\n\\n Guzman cites no authority to support his broader claim that USCIS was required\\n\\nto go beyond his application and review all materials in its possession. In fact, TPS\\n\\napplicants bear the burden to “submit all documentation as required . . . or requested.”\\n\\n 9\\n\\f8 C.F.R. § 244.9(a). Thus, the record establishes that USCIS did not err in adjudicating\\n\\nGuzman’s TPS application — let alone err on the magnitude of fundamental unfairness. 3\\n\\nSee United States v. Lopez-Collazo, 824 F.3d 453, 467 (4th Cir. 2016).\\n\\n In light of this holding, we refrain from deciding whether an attempt to extend\\n\\nMendoza-Lopez to allow a constitutional attack on a TPS denial could, in a different case,\\n\\nbe meritorious. See Lyng v. Nw. Indian Cemetery Protective Ass’n, 485 U.S. 439, 445\\n\\n(1988). Similarly, we need not determine whether Guzman exhausted his administrative\\n\\nremedies or was improperly deprived of judicial review. Because Guzman has failed to\\n\\npresent any due process violation in the administrative proceedings he seeks to attack —\\n\\nthe core of any Mendoza-Lopez challenge — we must reject his claim.\\n\\n\\n\\n V.\\n\\n For the foregoing reasons, the judgment of the district court is\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 3\\n Before the district court, Guzman contended that his TPS attorney’s\\nineffectiveness constituted a second, independent due process violation. But again, even\\nif such an argument could prevail under the right circumstances, it falls short here.\\nGuzman opted against pressing this argument in any briefing before us, citing his\\ncounsel’s incompetence only to justify his failure to exhaust administrative remedies. He\\nattempted to raise this claim at oral argument but offered no justification for his\\nforfeiture. We therefore decline to consider this undeveloped claim. See United States v.\\nBartko, 728 F.3d 327, 335 (4th Cir. 2013).\\n\\n 10\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4381963/\", \"author_raw\": \"DIANA GRIBBON MOTZ, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"MOTZ"},"judge2":{"kind":"string","value":"QUATTLEBAUM"},"judge3":{"kind":"string","value":"DUNCAN"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4604710/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Plaintiff - Appellee, v. Jose Benjamin GUZMAN-VELASQUEZ, Defendant - Appellant.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-03-28\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-4133\n\n\nUNITED STATES OF AMERICA,\n\n Plaintiff - Appellee,\n\n v.\n\nJOSE BENJAMIN GUZMAN-VELASQUEZ,\n\n Defendant - Appellant.\n\n\nAppeal from the United States District Court for the Eastern District of Virginia, at\nRichmond. M. Hannah Lauck, District Judge. (3:16-cr-00151-MHL-1)\n\n\nArgued: January 31, 2019 Decided: March 28, 2019\n\n\nBefore MOTZ and QUATTLEBAUM, Circuit Judges, and DUNCAN, Senior Circuit\nJudge.\n\n\nAffirmed by published opinion. Judge Motz wrote the opinion, in which Judge\nQuattlebaum and Senior Judge Duncan joined.\n\n\nARGUED: Laura Jill Koenig, OFFICE OF THE FEDERAL PUBLIC DEFENDER,\nRichmond, Virginia, for Appellant. Daniel Taylor Young, OFFICE OF THE UNITED\nSTATES ATTORNEY, Alexandria, Virginia, for Appellee. ON BRIEF: Geremy C.\nKamens, Federal Public Defender, OFFICE OF THE FEDERAL PUBLIC DEFENDER,\nAlexandria, Virginia, for Appellant. G. Zachary Terwilliger, United States Attorney,\nAlexandria, Virginia, S. David Schiller, OFFICE OF THE UNITED STATES\nATTORNEY, Richmond, Virginia, for Appellee.\n\fDIANA GRIBBON MOTZ, Circuit Judge:\n\n When Jose Benjamin Guzman-Velasquez returned to the United States after being\n\ndeported, the government charged him with the crime of illegal reentry. Guzman moved\n\nto dismiss the indictment, relying solely on United States v. Mendoza-Lopez, 481 U.S.\n\n828 (1987), which held that an administrative removal proceeding marred by due process\n\ndefects that foreclosed judicial review could not serve as a basis for criminal conviction.\n\nThe district court denied Guzman’s motion. For the reasons that follow, we affirm.\n\n\n\n I.\n\n On December 31, 1998, Guzman, a citizen of El Salvador, entered the United\n\nStates without authorization. That same day, the federal government initiated removal\n\nproceedings. An immigration judge granted Guzman voluntary departure; when he failed\n\nto timely depart, the grant converted into a removal order.\n\n Approximately a year later, in response to a series of earthquakes, Attorney\n\nGeneral John Ashcroft designated El Salvador for the Temporary Protected Status (TPS)\n\nprogram. See 66 Fed. Reg. 14,214, 14,214 (Mar. 9, 2001). TPS “allows eligible\n\nnationals of a foreign state to temporarily remain in the United States during the\n\npendency of that state’s designation.” Cervantes v. Holder, 597 F.3d 229, 231 (4th Cir.\n\n2010). Once granted, the government “shall not remove” an individual with TPS.\n\n8 U.S.C. § 1254a(a)(1)(A). Salvadorans were eligible for TPS if they “ha[d] been\n\n‘continuously physically present’ in the United States since March 9, 2001,” “ha[d]\n\n‘continuously resided’ in the United States since February 13, 2001,” and satisfied other\n\n 2\n\fstatutory requirements. 66 Fed. Reg. at 14,214 (quoting 8 U.S.C. §§ 1254a(c)(1)(A)(i)\n\nand (ii)).\n\n Guzman’s attorney submitted a TPS application on his behalf. The Immigration\n\nand Naturalization Service (INS) requested additional documentation as to Guzman’s\n\ncontinuous physical presence and continuous residence in the United States. Although\n\nthe relevant documentation was present in the INS’s file, it was not appended to the TPS\n\napplication as required, and Guzman’s attorney did not timely respond to the inquiry.\n\n As a result, United States Citizenship and Immigration Services (USCIS) 1 denied\n\nGuzman’s TPS application. The agency notified Guzman’s lawyer that he could appeal\n\nwithin 30 days and indicated that it had also mailed a notice to Guzman. But Guzman did\n\nnot appeal, and in 2007, he was removed. He returned without authorization sometime\n\nthereafter and was convicted of three state crimes, rendering him ineligible for TPS.\n\n In 2016, a grand jury returned a federal criminal indictment charging Guzman\n\nwith felony illegal reentry in violation of 8 U.S.C. § 1326(a). Guzman moved to dismiss\n\nthe indictment, relying on Mendoza-Lopez. The parties stipulated that at the time\n\nGuzman applied for TPS in 2002, he satisfied all the requirements and that, had USCIS\n\nreviewed his full immigration file, he “should have been granted” TPS.\n\n The district court denied Guzman’s motion to dismiss the indictment. It reasoned\n\nthat Mendoza-Lopez permitted collateral attacks only against removal orders, not TPS\n\n 1\n After the INS’s request for evidence but before its final decision, Congress\nabolished the INS and created USCIS, in which it vested responsibility for adjudication\nof immigration benefits. Homeland Security Act of 2002, Pub. L. No. 107–296, § 451,\n116 Stat. 2135, 2195 (codified as amended at 6 U.S.C. § 271).\n\n 3\n\fdenials. In the alternative, the court relied on a basis not briefed by the Government: it\n\nheld that 8 U.S.C. § 1252, which limits district court jurisdiction to review immigration\n\ndeterminations, also deprived the court of jurisdiction to consider Guzman’s defense to\n\nhis criminal charge. Reserving the right to seek our review, Guzman pled guilty and\n\ntimely noted this appeal.\n\n\n\n II.\n\n We review de novo a denial of a motion to dismiss an illegal reentry indictment.\n\nUnited States v. El Shami, 434 F.3d 659, 663 (4th Cir. 2005). Before undertaking this\n\nreview, we first outline the statutory and constitutional history at issue.\n\n The Government must prove two elements to convict a defendant of felony illegal\n\nreentry: (1) the defendant was “deported[] or removed” 2 from the United States “while\n\nan order of . . . deportation[] or removal [was] outstanding,” and (2) the defendant\n\nsubsequently “enter[ed], attempt[ed] to enter, or [was] at any time found in, the United\n\nStates” without authorization. 8 U.S.C. § 1326(a). Guzman asserts a due process\n\nchallenge to a portion of the first element of the crime: the fact of a previous removal.\n\n Under current law, this removal element requires proof of both a prior removal\n\nand the existence of an outstanding removal order. However, this was not the case when\n\nthe Supreme Court decided Mendoza-Lopez. At that time, § 1326 made no reference to\n\nremoval orders: the removal element required only that the defendant had “been arrested\n\n 2\n The terms “removal” and “deportation” are interchangeable for the purposes of\n§ 1326. United States v. Moreno-Tapia, 848 F.3d 162, 165 n.1 (4th Cir. 2017).\n\n 4\n\fand deported or excluded and deported.” Mendoza-Lopez, 481 U.S. at 830 (quoting\n\n8 U.S.C. § 1326 (1982)); see also Omnibus Consolidated Appropriations Act, 1997, Pub.\n\nL. No. 104–208, § 324(a), 110 Stat. 3009, 3009-629 (1996) (amending § 1326(a) to add\n\nfirst reference to deportation orders). Nor did § 1326, as a statutory matter, require a\n\nshowing that the defendant’s prior removal was lawful. Mendoza-Lopez, 481 U.S. at\n\n834–37.\n\n Even so, the Mendoza-Lopez Court held that the Due Process Clause entitles a\n\ndefendant, under certain circumstances, to challenge the validity of an underlying\n\ndeportation order in a criminal prosecution “in which th[e] prior deportation is an element\n\nof the crime.” Id. at 833. The Court explained that “where a determination made in an\n\nadministrative proceeding is to play a critical role in the subsequent imposition of a\n\ncriminal sanction,” due process requires “some meaningful review of the administrative\n\nproceeding.” Id. at 837–38 (collecting cases). Thus, when a deportation hearing is “not\n\nconducted in conformity with due process,” and the due process defects “foreclose\n\njudicial review of that proceeding,” then the deportation proceeding “may not be used to\n\nsupport a criminal conviction” for illegal reentry. Id. at 834, 838, 842.\n\n Congress responded to Mendoza-Lopez in 1996 by enacting 8 U.S.C. § 1326(d).\n\nAntiterrorism and Effective Death Penalty Act of 1996, Pub. L. No. 104–132, § 441(a),\n\n110 Stat. 1214, 1279 (codified at 8 U.S.C. § 1326(d)). Under this statute, a defendant in\n\nan illegal reentry prosecution may, as a statutory defense, collaterally attack the order\n\nunderlying his prior removal if he shows that (1) he exhausted any available\n\nadministrative remedies against the removal order, (2) he was “improperly deprived . . .\n\n 5\n\fof the opportunity for judicial review” in his removal proceeding, and (3) “the entry of\n\nthe [removal] order was fundamentally unfair.” 8 U.S.C. § 1326(d) (emphasis added).\n\nThese statutory requirements are identical to the constitutional standards that many courts\n\napplied, prior to § 1326(d)’s enactment, in Mendoza-Lopez challenges to removal orders.\n\nSee, e.g., United States v. Encarnacion-Galvez, 964 F.2d 402, 406–07 (5th Cir. 1992).\n\n\n\n III.\n\n As Guzman acknowledges, § 1326(d) offers him no refuge: its plain text limits\n\ncollateral challenges to removal orders, and Guzman does not question the validity of his\n\nremoval order. He instead challenges USCIS’s denial of TPS as violative of the Due\n\nProcess Clause under Mendoza-Lopez.\n\n Before reaching the merits of this argument, we pause to consider whether federal\n\ndistrict courts have the power to evaluate such a claim. The district court held that it\n\nlacked jurisdiction to hear Guzman’s challenge because Congress has eliminated district\n\ncourts’ jurisdiction to review TPS determinations. Although this may appear to be the\n\ncase, it conflates the underlying determination and the specific procedural context in\n\nwhich this appeal arose.\n\n While the statute on which the district court relied, 8 U.S.C. § 1252, limits only a\n\ncourt’s jurisdiction to review immigration determinations, it says nothing about\n\njurisdiction to hear a challenge to a criminal indictment. To the contrary, another federal\n\nstatute, 18 U.S.C. § 3231, vests district courts with original jurisdiction over criminal\n\nproceedings. Thus, district courts regularly hear constitutional challenges to criminal\n\n 6\n\findictments like the one at hand. See, e.g., United States v. Staten, 666 F.3d 154, 156–68\n\n(4th Cir. 2011) (affirming district court’s resolution, on the merits, of Second\n\nAmendment challenge to indictment); United States v. Gould, 568 F.3d 459, 462, 470–75\n\n(4th Cir. 2009) (same regarding Commerce Clause challenge); United States v. Jefferson,\n\n546 F.3d 300, 306–14 (4th Cir. 2008) (same regarding Speech or Debate Clause\n\nchallenge).\n\n Moreover, there is “no support for the contention” that § 1252’s “withdraw[al] [of]\n\njurisdiction over the original deportation order reaches collateral challenges to a criminal\n\ncharge for illegal reentry,” regardless of how novel (or even meritless) the challenge may\n\nbe. United States v. Charleswell, 456 F.3d 347, 352 n.4 (3d Cir. 2006). After all, it is a\n\ncardinal principle that “repeals by implication are not favored and will not be presumed\n\nunless the intention of [Congress] to repeal is clear and manifest.” Hui v. Castaneda, 559\n\nU.S. 799, 810 (2010) (internal quotation marks omitted). Thus, to our knowledge, until\n\nthis case no court has ever construed § 1252 to impliedly repeal § 3231.\n\n Indeed, to do so by extending § 1252’s jurisdictional limitations would raise\n\n“[s]erious constitutional concerns.” Charleswell, 456 F.3d at 352 n.4. This is so because\n\nit would permit Congress to enact a criminal statute and then prohibit courts from\n\nexercising jurisdiction over a constitutional challenge to that statute. The Supreme Court\n\nhas long recognized that such restrictions on first-instance judicial review of\n\nconstitutional claims are problematic, even in immigration proceedings. See, e.g., INS v.\n\nSt. Cyr, 533 U.S. 289, 305 (2001) (teaching that “a serious Suspension Clause issue\n\n\n\n 7\n\fwould be presented” if Congress withdrew all judicial review of “pure questions of law”\n\nin immigration proceedings). Surely, they are at least as troubling in a criminal context.\n\n Furthermore, the district court’s interpretation would lead to absurd results.\n\nSection 1252 provides that “a petition for review filed with an appropriate court of\n\nappeals” is “the sole and exclusive means for judicial review of an order of removal.”\n\n8 U.S.C. § 1252(a)(5). Thus, if we were to endorse an interpretation of this statute that\n\nconflated judicial review of immigration determinations with collateral challenges in\n\ncriminal proceedings, no district court would have jurisdiction to hear any Mendoza-\n\nLopez or § 1326(d) challenge — even one identical to that in Mendoza-Lopez itself. This\n\ncannot be so. Mendoza-Lopez announced a constitutional due process right that Congress\n\nmay not abrogate.\n\n Guzman did not ask the district court to grant him relief from removal; he raised a\n\nconstitutional challenge to a criminal charge. Notwithstanding § 1252, the district court\n\nhad jurisdiction to consider his argument.\n\n\n\n IV.\n\n We now turn to the merits. Guzman urges us to decide a constitutional question of\n\nfirst impression: does the Mendoza-Lopez due process principle extend beyond removal\n\norders to authorize constitutional challenges to TPS denials within criminal prosecutions\n\nfor illegal reentry?\n\n Guzman asserts that the denial of his TPS application violated due process and he\n\nwas deprived of judicial review of the decision. In support of his view that Mendoza-\n\n 8\n\fLopez authorizes this collateral attack, Guzman relies on the Court’s generalized\n\ndiscussion of due process constraints on “administrative proceeding[s]” that play a\n\n“critical role” in a subsequent criminal prosecution. Mendoza-Lopez, 481 U.S. at 837–\n\n38. The Government counters that Mendoza-Lopez addresses infirmities in “deportation\n\nproceedings and nothing more.” Gov. Br. 30. Although the Third Circuit has interpreted\n\nMendoza-Lopez to permit collateral attack against removal orders and reinstatement\n\norders, see Charleswell, 456 F.3d at 352, we are aware of no court that has considered\n\nwhether Mendoza-Lopez reaches challenges to TPS determinations as well.\n\n We need not resolve this novel question. Even assuming that Mendoza-Lopez\n\npermits a constitutional challenge here, Guzman’s claim fails at a more basic level: he\n\nhas not asserted a due process violation that would render the adjudication of his TPS\n\napplication fundamentally unfair. See Mendoza-Lopez, 481 U.S. at 837–40.\n\n On appeal, Guzman’s sole claim of fundamental unfairness is that USCIS violated\n\nhis due process right to have the agency “fairly and thoroughly review the materials in\n\nthe government’s possession” when evaluating his TPS application. But if Guzman had a\n\ndue process right to fair and thorough review, it would only require USCIS to review the\n\nmaterials within his TPS application. USCIS did exactly that: it reviewed Guzman’s\n\nsubmission, found it to be lacking, requested additional evidence to no avail, and only\n\nthen denied relief.\n\n Guzman cites no authority to support his broader claim that USCIS was required\n\nto go beyond his application and review all materials in its possession. In fact, TPS\n\napplicants bear the burden to “submit all documentation as required . . . or requested.”\n\n 9\n\f8 C.F.R. § 244.9(a). Thus, the record establishes that USCIS did not err in adjudicating\n\nGuzman’s TPS application — let alone err on the magnitude of fundamental unfairness. 3\n\nSee United States v. Lopez-Collazo, 824 F.3d 453, 467 (4th Cir. 2016).\n\n In light of this holding, we refrain from deciding whether an attempt to extend\n\nMendoza-Lopez to allow a constitutional attack on a TPS denial could, in a different case,\n\nbe meritorious. See Lyng v. Nw. Indian Cemetery Protective Ass’n, 485 U.S. 439, 445\n\n(1988). Similarly, we need not determine whether Guzman exhausted his administrative\n\nremedies or was improperly deprived of judicial review. Because Guzman has failed to\n\npresent any due process violation in the administrative proceedings he seeks to attack —\n\nthe core of any Mendoza-Lopez challenge — we must reject his claim.\n\n\n\n V.\n\n For the foregoing reasons, the judgment of the district court is\n\n AFFIRMED.\n\n\n\n\n 3\n Before the district court, Guzman contended that his TPS attorney’s\nineffectiveness constituted a second, independent due process violation. But again, even\nif such an argument could prevail under the right circumstances, it falls short here.\nGuzman opted against pressing this argument in any briefing before us, citing his\ncounsel’s incompetence only to justify his failure to exhaust administrative remedies. He\nattempted to raise this claim at oral argument but offered no justification for his\nforfeiture. We therefore decline to consider this undeveloped claim. See United States v.\nBartko, 728 F.3d 327, 335 (4th Cir. 2013).\n\n 10\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Plaintiff - Appellee, v. Jose Benjamin GUZMAN-VELASQUEZ, Defendant - Appellant.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-03-28\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-4133\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\n v.\\n\\nJOSE BENJAMIN GUZMAN-VELASQUEZ,\\n\\n Defendant - Appellant.\\n\\n\\nAppeal from the United States District Court for the Eastern District of Virginia, at\\nRichmond. M. Hannah Lauck, District Judge. (3:16-cr-00151-MHL-1)\\n\\n\\nArgued: January 31, 2019 Decided: March 28, 2019\\n\\n\\nBefore MOTZ and QUATTLEBAUM, Circuit Judges, and DUNCAN, Senior Circuit\\nJudge.\\n\\n\\nAffirmed by published opinion. Judge Motz wrote the opinion, in which Judge\\nQuattlebaum and Senior Judge Duncan joined.\\n\\n\\nARGUED: Laura Jill Koenig, OFFICE OF THE FEDERAL PUBLIC DEFENDER,\\nRichmond, Virginia, for Appellant. Daniel Taylor Young, OFFICE OF THE UNITED\\nSTATES ATTORNEY, Alexandria, Virginia, for Appellee. ON BRIEF: Geremy C.\\nKamens, Federal Public Defender, OFFICE OF THE FEDERAL PUBLIC DEFENDER,\\nAlexandria, Virginia, for Appellant. G. Zachary Terwilliger, United States Attorney,\\nAlexandria, Virginia, S. David Schiller, OFFICE OF THE UNITED STATES\\nATTORNEY, Richmond, Virginia, for Appellee.\\n\\fDIANA GRIBBON MOTZ, Circuit Judge:\\n\\n When Jose Benjamin Guzman-Velasquez returned to the United States after being\\n\\ndeported, the government charged him with the crime of illegal reentry. Guzman moved\\n\\nto dismiss the indictment, relying solely on United States v. Mendoza-Lopez, 481 U.S.\\n\\n828 (1987), which held that an administrative removal proceeding marred by due process\\n\\ndefects that foreclosed judicial review could not serve as a basis for criminal conviction.\\n\\nThe district court denied Guzman’s motion. For the reasons that follow, we affirm.\\n\\n\\n\\n I.\\n\\n On December 31, 1998, Guzman, a citizen of El Salvador, entered the United\\n\\nStates without authorization. That same day, the federal government initiated removal\\n\\nproceedings. An immigration judge granted Guzman voluntary departure; when he failed\\n\\nto timely depart, the grant converted into a removal order.\\n\\n Approximately a year later, in response to a series of earthquakes, Attorney\\n\\nGeneral John Ashcroft designated El Salvador for the Temporary Protected Status (TPS)\\n\\nprogram. See 66 Fed. Reg. 14,214, 14,214 (Mar. 9, 2001). TPS “allows eligible\\n\\nnationals of a foreign state to temporarily remain in the United States during the\\n\\npendency of that state’s designation.” Cervantes v. Holder, 597 F.3d 229, 231 (4th Cir.\\n\\n2010). Once granted, the government “shall not remove” an individual with TPS.\\n\\n8 U.S.C. § 1254a(a)(1)(A). Salvadorans were eligible for TPS if they “ha[d] been\\n\\n‘continuously physically present’ in the United States since March 9, 2001,” “ha[d]\\n\\n‘continuously resided’ in the United States since February 13, 2001,” and satisfied other\\n\\n 2\\n\\fstatutory requirements. 66 Fed. Reg. at 14,214 (quoting 8 U.S.C. §§ 1254a(c)(1)(A)(i)\\n\\nand (ii)).\\n\\n Guzman’s attorney submitted a TPS application on his behalf. The Immigration\\n\\nand Naturalization Service (INS) requested additional documentation as to Guzman’s\\n\\ncontinuous physical presence and continuous residence in the United States. Although\\n\\nthe relevant documentation was present in the INS’s file, it was not appended to the TPS\\n\\napplication as required, and Guzman’s attorney did not timely respond to the inquiry.\\n\\n As a result, United States Citizenship and Immigration Services (USCIS) 1 denied\\n\\nGuzman’s TPS application. The agency notified Guzman’s lawyer that he could appeal\\n\\nwithin 30 days and indicated that it had also mailed a notice to Guzman. But Guzman did\\n\\nnot appeal, and in 2007, he was removed. He returned without authorization sometime\\n\\nthereafter and was convicted of three state crimes, rendering him ineligible for TPS.\\n\\n In 2016, a grand jury returned a federal criminal indictment charging Guzman\\n\\nwith felony illegal reentry in violation of 8 U.S.C. § 1326(a). Guzman moved to dismiss\\n\\nthe indictment, relying on Mendoza-Lopez. The parties stipulated that at the time\\n\\nGuzman applied for TPS in 2002, he satisfied all the requirements and that, had USCIS\\n\\nreviewed his full immigration file, he “should have been granted” TPS.\\n\\n The district court denied Guzman’s motion to dismiss the indictment. It reasoned\\n\\nthat Mendoza-Lopez permitted collateral attacks only against removal orders, not TPS\\n\\n 1\\n After the INS’s request for evidence but before its final decision, Congress\\nabolished the INS and created USCIS, in which it vested responsibility for adjudication\\nof immigration benefits. Homeland Security Act of 2002, Pub. L. No. 107–296, § 451,\\n116 Stat. 2135, 2195 (codified as amended at 6 U.S.C. § 271).\\n\\n 3\\n\\fdenials. In the alternative, the court relied on a basis not briefed by the Government: it\\n\\nheld that 8 U.S.C. § 1252, which limits district court jurisdiction to review immigration\\n\\ndeterminations, also deprived the court of jurisdiction to consider Guzman’s defense to\\n\\nhis criminal charge. Reserving the right to seek our review, Guzman pled guilty and\\n\\ntimely noted this appeal.\\n\\n\\n\\n II.\\n\\n We review de novo a denial of a motion to dismiss an illegal reentry indictment.\\n\\nUnited States v. El Shami, 434 F.3d 659, 663 (4th Cir. 2005). Before undertaking this\\n\\nreview, we first outline the statutory and constitutional history at issue.\\n\\n The Government must prove two elements to convict a defendant of felony illegal\\n\\nreentry: (1) the defendant was “deported[] or removed” 2 from the United States “while\\n\\nan order of . . . deportation[] or removal [was] outstanding,” and (2) the defendant\\n\\nsubsequently “enter[ed], attempt[ed] to enter, or [was] at any time found in, the United\\n\\nStates” without authorization. 8 U.S.C. § 1326(a). Guzman asserts a due process\\n\\nchallenge to a portion of the first element of the crime: the fact of a previous removal.\\n\\n Under current law, this removal element requires proof of both a prior removal\\n\\nand the existence of an outstanding removal order. However, this was not the case when\\n\\nthe Supreme Court decided Mendoza-Lopez. At that time, § 1326 made no reference to\\n\\nremoval orders: the removal element required only that the defendant had “been arrested\\n\\n 2\\n The terms “removal” and “deportation” are interchangeable for the purposes of\\n§ 1326. United States v. Moreno-Tapia, 848 F.3d 162, 165 n.1 (4th Cir. 2017).\\n\\n 4\\n\\fand deported or excluded and deported.” Mendoza-Lopez, 481 U.S. at 830 (quoting\\n\\n8 U.S.C. § 1326 (1982)); see also Omnibus Consolidated Appropriations Act, 1997, Pub.\\n\\nL. No. 104–208, § 324(a), 110 Stat. 3009, 3009-629 (1996) (amending § 1326(a) to add\\n\\nfirst reference to deportation orders). Nor did § 1326, as a statutory matter, require a\\n\\nshowing that the defendant’s prior removal was lawful. Mendoza-Lopez, 481 U.S. at\\n\\n834–37.\\n\\n Even so, the Mendoza-Lopez Court held that the Due Process Clause entitles a\\n\\ndefendant, under certain circumstances, to challenge the validity of an underlying\\n\\ndeportation order in a criminal prosecution “in which th[e] prior deportation is an element\\n\\nof the crime.” Id. at 833. The Court explained that “where a determination made in an\\n\\nadministrative proceeding is to play a critical role in the subsequent imposition of a\\n\\ncriminal sanction,” due process requires “some meaningful review of the administrative\\n\\nproceeding.” Id. at 837–38 (collecting cases). Thus, when a deportation hearing is “not\\n\\nconducted in conformity with due process,” and the due process defects “foreclose\\n\\njudicial review of that proceeding,” then the deportation proceeding “may not be used to\\n\\nsupport a criminal conviction” for illegal reentry. Id. at 834, 838, 842.\\n\\n Congress responded to Mendoza-Lopez in 1996 by enacting 8 U.S.C. § 1326(d).\\n\\nAntiterrorism and Effective Death Penalty Act of 1996, Pub. L. No. 104–132, § 441(a),\\n\\n110 Stat. 1214, 1279 (codified at 8 U.S.C. § 1326(d)). Under this statute, a defendant in\\n\\nan illegal reentry prosecution may, as a statutory defense, collaterally attack the order\\n\\nunderlying his prior removal if he shows that (1) he exhausted any available\\n\\nadministrative remedies against the removal order, (2) he was “improperly deprived . . .\\n\\n 5\\n\\fof the opportunity for judicial review” in his removal proceeding, and (3) “the entry of\\n\\nthe [removal] order was fundamentally unfair.” 8 U.S.C. § 1326(d) (emphasis added).\\n\\nThese statutory requirements are identical to the constitutional standards that many courts\\n\\napplied, prior to § 1326(d)’s enactment, in Mendoza-Lopez challenges to removal orders.\\n\\nSee, e.g., United States v. Encarnacion-Galvez, 964 F.2d 402, 406–07 (5th Cir. 1992).\\n\\n\\n\\n III.\\n\\n As Guzman acknowledges, § 1326(d) offers him no refuge: its plain text limits\\n\\ncollateral challenges to removal orders, and Guzman does not question the validity of his\\n\\nremoval order. He instead challenges USCIS’s denial of TPS as violative of the Due\\n\\nProcess Clause under Mendoza-Lopez.\\n\\n Before reaching the merits of this argument, we pause to consider whether federal\\n\\ndistrict courts have the power to evaluate such a claim. The district court held that it\\n\\nlacked jurisdiction to hear Guzman’s challenge because Congress has eliminated district\\n\\ncourts’ jurisdiction to review TPS determinations. Although this may appear to be the\\n\\ncase, it conflates the underlying determination and the specific procedural context in\\n\\nwhich this appeal arose.\\n\\n While the statute on which the district court relied, 8 U.S.C. § 1252, limits only a\\n\\ncourt’s jurisdiction to review immigration determinations, it says nothing about\\n\\njurisdiction to hear a challenge to a criminal indictment. To the contrary, another federal\\n\\nstatute, 18 U.S.C. § 3231, vests district courts with original jurisdiction over criminal\\n\\nproceedings. Thus, district courts regularly hear constitutional challenges to criminal\\n\\n 6\\n\\findictments like the one at hand. See, e.g., United States v. Staten, 666 F.3d 154, 156–68\\n\\n(4th Cir. 2011) (affirming district court’s resolution, on the merits, of Second\\n\\nAmendment challenge to indictment); United States v. Gould, 568 F.3d 459, 462, 470–75\\n\\n(4th Cir. 2009) (same regarding Commerce Clause challenge); United States v. Jefferson,\\n\\n546 F.3d 300, 306–14 (4th Cir. 2008) (same regarding Speech or Debate Clause\\n\\nchallenge).\\n\\n Moreover, there is “no support for the contention” that § 1252’s “withdraw[al] [of]\\n\\njurisdiction over the original deportation order reaches collateral challenges to a criminal\\n\\ncharge for illegal reentry,” regardless of how novel (or even meritless) the challenge may\\n\\nbe. United States v. Charleswell, 456 F.3d 347, 352 n.4 (3d Cir. 2006). After all, it is a\\n\\ncardinal principle that “repeals by implication are not favored and will not be presumed\\n\\nunless the intention of [Congress] to repeal is clear and manifest.” Hui v. Castaneda, 559\\n\\nU.S. 799, 810 (2010) (internal quotation marks omitted). Thus, to our knowledge, until\\n\\nthis case no court has ever construed § 1252 to impliedly repeal § 3231.\\n\\n Indeed, to do so by extending § 1252’s jurisdictional limitations would raise\\n\\n“[s]erious constitutional concerns.” Charleswell, 456 F.3d at 352 n.4. This is so because\\n\\nit would permit Congress to enact a criminal statute and then prohibit courts from\\n\\nexercising jurisdiction over a constitutional challenge to that statute. The Supreme Court\\n\\nhas long recognized that such restrictions on first-instance judicial review of\\n\\nconstitutional claims are problematic, even in immigration proceedings. See, e.g., INS v.\\n\\nSt. Cyr, 533 U.S. 289, 305 (2001) (teaching that “a serious Suspension Clause issue\\n\\n\\n\\n 7\\n\\fwould be presented” if Congress withdrew all judicial review of “pure questions of law”\\n\\nin immigration proceedings). Surely, they are at least as troubling in a criminal context.\\n\\n Furthermore, the district court’s interpretation would lead to absurd results.\\n\\nSection 1252 provides that “a petition for review filed with an appropriate court of\\n\\nappeals” is “the sole and exclusive means for judicial review of an order of removal.”\\n\\n8 U.S.C. § 1252(a)(5). Thus, if we were to endorse an interpretation of this statute that\\n\\nconflated judicial review of immigration determinations with collateral challenges in\\n\\ncriminal proceedings, no district court would have jurisdiction to hear any Mendoza-\\n\\nLopez or § 1326(d) challenge — even one identical to that in Mendoza-Lopez itself. This\\n\\ncannot be so. Mendoza-Lopez announced a constitutional due process right that Congress\\n\\nmay not abrogate.\\n\\n Guzman did not ask the district court to grant him relief from removal; he raised a\\n\\nconstitutional challenge to a criminal charge. Notwithstanding § 1252, the district court\\n\\nhad jurisdiction to consider his argument.\\n\\n\\n\\n IV.\\n\\n We now turn to the merits. Guzman urges us to decide a constitutional question of\\n\\nfirst impression: does the Mendoza-Lopez due process principle extend beyond removal\\n\\norders to authorize constitutional challenges to TPS denials within criminal prosecutions\\n\\nfor illegal reentry?\\n\\n Guzman asserts that the denial of his TPS application violated due process and he\\n\\nwas deprived of judicial review of the decision. In support of his view that Mendoza-\\n\\n 8\\n\\fLopez authorizes this collateral attack, Guzman relies on the Court’s generalized\\n\\ndiscussion of due process constraints on “administrative proceeding[s]” that play a\\n\\n“critical role” in a subsequent criminal prosecution. Mendoza-Lopez, 481 U.S. at 837–\\n\\n38. The Government counters that Mendoza-Lopez addresses infirmities in “deportation\\n\\nproceedings and nothing more.” Gov. Br. 30. Although the Third Circuit has interpreted\\n\\nMendoza-Lopez to permit collateral attack against removal orders and reinstatement\\n\\norders, see Charleswell, 456 F.3d at 352, we are aware of no court that has considered\\n\\nwhether Mendoza-Lopez reaches challenges to TPS determinations as well.\\n\\n We need not resolve this novel question. Even assuming that Mendoza-Lopez\\n\\npermits a constitutional challenge here, Guzman’s claim fails at a more basic level: he\\n\\nhas not asserted a due process violation that would render the adjudication of his TPS\\n\\napplication fundamentally unfair. See Mendoza-Lopez, 481 U.S. at 837–40.\\n\\n On appeal, Guzman’s sole claim of fundamental unfairness is that USCIS violated\\n\\nhis due process right to have the agency “fairly and thoroughly review the materials in\\n\\nthe government’s possession” when evaluating his TPS application. But if Guzman had a\\n\\ndue process right to fair and thorough review, it would only require USCIS to review the\\n\\nmaterials within his TPS application. USCIS did exactly that: it reviewed Guzman’s\\n\\nsubmission, found it to be lacking, requested additional evidence to no avail, and only\\n\\nthen denied relief.\\n\\n Guzman cites no authority to support his broader claim that USCIS was required\\n\\nto go beyond his application and review all materials in its possession. In fact, TPS\\n\\napplicants bear the burden to “submit all documentation as required . . . or requested.”\\n\\n 9\\n\\f8 C.F.R. § 244.9(a). Thus, the record establishes that USCIS did not err in adjudicating\\n\\nGuzman’s TPS application — let alone err on the magnitude of fundamental unfairness. 3\\n\\nSee United States v. Lopez-Collazo, 824 F.3d 453, 467 (4th Cir. 2016).\\n\\n In light of this holding, we refrain from deciding whether an attempt to extend\\n\\nMendoza-Lopez to allow a constitutional attack on a TPS denial could, in a different case,\\n\\nbe meritorious. See Lyng v. Nw. Indian Cemetery Protective Ass’n, 485 U.S. 439, 445\\n\\n(1988). Similarly, we need not determine whether Guzman exhausted his administrative\\n\\nremedies or was improperly deprived of judicial review. Because Guzman has failed to\\n\\npresent any due process violation in the administrative proceedings he seeks to attack —\\n\\nthe core of any Mendoza-Lopez challenge — we must reject his claim.\\n\\n\\n\\n V.\\n\\n For the foregoing reasons, the judgment of the district court is\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 3\\n Before the district court, Guzman contended that his TPS attorney’s\\nineffectiveness constituted a second, independent due process violation. But again, even\\nif such an argument could prevail under the right circumstances, it falls short here.\\nGuzman opted against pressing this argument in any briefing before us, citing his\\ncounsel’s incompetence only to justify his failure to exhaust administrative remedies. He\\nattempted to raise this claim at oral argument but offered no justification for his\\nforfeiture. We therefore decline to consider this undeveloped claim. See United States v.\\nBartko, 728 F.3d 327, 335 (4th Cir. 2013).\\n\\n 10\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1072,"cells":{"id":{"kind":"number","value":4595685,"string":"4,595,685"},"name":{"kind":"string","value":"UNITED STATES of America, Plaintiff-Appellee v. Alan Victor GOMEZ GOMEZ, Defendant-Appellant"},"name_abbreviation":{"kind":"string","value":"United States v. Alan Gomez Gomez"},"decision_date":{"kind":"string","value":"2019-03-01"},"docket_number":{"kind":"string","value":"17-20526"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"James, Clement, Higginson\", \"parties\": \"\", \"opinions\": [{\"author\": \"JAMES C. HO, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 17-20526 Document: 00514857955 Page: 1 Date Filed: 03/01/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n No. 17-20526 FILED\\n February 26, 2019\\n Lyle W. Cayce\\nUNITED STATES OF AMERICA, Clerk\\n\\n Plaintiff - Appellee\\n\\nv.\\n\\nALAN VICTOR GOMEZ GOMEZ,\\n\\n Defendant - Appellant\\n\\n\\n\\n\\n Appeal from the United States District Court\\n for the Southern District of Texas\\n\\n\\nBefore CLEMENT, HIGGINSON, and HO, Circuit Judges. *\\nJAMES C. HO, Circuit Judge:\\n Alan Victor Gomez Gomez pled guilty to illegally reentering the United\\nStates after deportation. The district court sentenced him under 8 U.S.C.\\n§ 1326(b)(2), based on the conclusion that his prior conviction for aggravated\\nassault constitutes a “crime of violence” under 18 U.S.C. § 16, and thus an\\naggravated felony under 8 U.S.C. § 1101(a)(43)(F). On appeal, he challenges\\nthe characterization of his prior conviction as a crime of violence. We affirm.\\n We recently revisited the definition of “crime of violence,” in one of the\\nmost consequential en banc rulings our court has issued in recent years. See\\n\\n\\n\\n * Judge Higginson concurs in the judgment only.\\n\\f Case: 17-20526 Document: 00514857955 Page: 2 Date Filed: 03/01/2019\\n\\n\\n\\n No. 17-20526\\nUnited States v. Reyes-Contreras, 910 F.3d 169 (5th Cir. 2018) (en banc). That\\nen banc decision expressly overruled no fewer than eighteen of our prior circuit\\nprecedents.\\n No court approaches the act of overruling one of its prior precedents\\nlightly—let alone eighteen of them. But our court deemed it “necessary” to do\\nso, in order to bring our circuit back into alignment with the statutory text as\\nenacted by Congress and construed by the Supreme Court, not to mention\\nnumerous precedents of our sister circuits. Id. at 173. In doing so, Reyes-\\nContreras provided important clarity to the issues that originally gave birth to\\nthis appeal, as it undoubtedly will in countless other pending and future\\nappeals in our circuit.\\n Congress defined “crime of violence” in 18 U.S.C. § 16(a) to include “an\\noffense that has as an element the use, attempted use, or threatened use of\\nphysical force against the person or property of another.” Gomez Gomez argues\\nthat aggravated assault under Tex. Penal Code § 22.02(a)(1) is not a crime of\\nviolence, because the offense can be committed through indirect as well as\\ndirect uses of force.\\n This argument might have had some force prior to Reyes-Contreras,\\nunder our precedents that recognized a distinction between direct and indirect\\nuses of force. But we abrogated that distinction in Reyes-Contreras. 910 F.3d\\nat 180–81. We now instead recognize, consistent with the Supreme Court’s\\ndecision in United States v. Castleman, 572 U.S. 157, 162–68 (2014), that the\\n“use of force” under 18 U.S.C. § 16(a) incorporates the common-law definition\\nof force—and thus includes indirect as well as direct applications of force.\\n Recognizing the significance of our en banc ruling in Reyes-Contreras,\\nGomez Gomez argues that it should not apply precisely because it is a change\\nin the law. That is, he argues that retroactively applying Reyes-Contreras to\\nhis sentence would violate the Ex Post Facto Clause of Article I, Section 9 of\\n 2\\n\\f Case: 17-20526 Document: 00514857955 Page: 3 Date Filed: 03/01/2019\\n\\n\\n\\n No. 17-20526\\nthe Constitution. But the Ex Post Facto Clause does not apply to the judiciary.\\nSee, e.g., Rogers v. Tennessee, 532 U.S. 451, 460 (2001) (“The Ex Post Facto\\nClause, by its own terms, does not apply to courts.”).\\n A retroactive application of a judicial decision can in theory violate the\\nDue Process Clause. For example, in Bouie v. City of Columbia, 378 U.S. 347\\n(1964), the Supreme Court held that a defendant’s due process rights could be\\nviolated by a retroactive application of an unexpected and indefensible\\nexpansion of substantive criminal liability. Id. at 353–54.\\n But Reyes-Contreras did not make previously innocent activities\\ncriminal. It merely reconciled our circuit precedents with the Supreme Court’s\\ndecision in Castleman. As our ruling explained: “The Fifth Circuit stands\\nalone in restricting the reasoning of Castleman on direct versus indirect force\\nto misdemeanor crimes of domestic violence.” Reyes-Contreras, 910 F.3d at\\n180. We simply backed away from our anomalous position and aligned our\\ncircuit with the precedents of other circuits. In short, Reyes-Contreras was\\nneither unexpected nor indefensible. See also United States v. Martinez, 496\\nF.3d 387, 390 (5th Cir. 2007) (holding that a retroactive application of a judicial\\ndecision resolving a circuit split to a defendant’s sentencing was not a violation\\nof due process under Bouie).\\n That conclusion dooms this appeal. In Reyes-Contreras, we held that\\nCastleman “is not limited to cases of domestic violence,” and “that for purposes\\nof identifying a conviction as a [crime of violence], there is no valid distinction\\nbetween direct and indirect force.” 910 F.3d at 182. This holding forecloses\\nGomez Gomez’s use of the distinction between direct and indirect force—a\\ndistinction he had hoped would help him establish that aggravated assault\\nunder Texas law is not a crime of violence under 18 U.S.C. § 16. See also\\nUnited States v. Villegas-Hernandez, 468 F.3d 874 (5th Cir. 2006) (holding that\\nTexas simple bodily assault does not require the use of force and is therefore\\n 3\\n\\f Case: 17-20526 Document: 00514857955 Page: 4 Date Filed: 03/01/2019\\n\\n\\n\\n No. 17-20526\\nnot a crime of violence), overruled by Reyes-Contreras, 910 F.3d at 181–82 (“We\\ntherefore necessarily overrule Part I.A of Villegas-Hernandez . . . to the extent\\nthat Villegas-Hernandez concluded that indirect force does not constitute the\\nuse of physical force.”). Accordingly, we affirm.\\n\\n\\n\\n\\n 4\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4372938/\", \"author_raw\": \"JAMES C. HO, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"JAMES"},"judge2":{"kind":"string","value":"CLEMENT"},"judge3":{"kind":"string","value":"HIGGINSON"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4595685/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Plaintiff-Appellee v. Alan Victor GOMEZ GOMEZ, Defendant-Appellant\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-01\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 17-20526 Document: 00514857955 Page: 1 Date Filed: 03/01/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\n United States Court of Appeals\n Fifth Circuit\n\n No. 17-20526 FILED\n February 26, 2019\n Lyle W. Cayce\nUNITED STATES OF AMERICA, Clerk\n\n Plaintiff - Appellee\n\nv.\n\nALAN VICTOR GOMEZ GOMEZ,\n\n Defendant - Appellant\n\n\n\n\n Appeal from the United States District Court\n for the Southern District of Texas\n\n\nBefore CLEMENT, HIGGINSON, and HO, Circuit Judges. *\nJAMES C. HO, Circuit Judge:\n Alan Victor Gomez Gomez pled guilty to illegally reentering the United\nStates after deportation. The district court sentenced him under 8 U.S.C.\n§ 1326(b)(2), based on the conclusion that his prior conviction for aggravated\nassault constitutes a “crime of violence” under 18 U.S.C. § 16, and thus an\naggravated felony under 8 U.S.C. § 1101(a)(43)(F). On appeal, he challenges\nthe characterization of his prior conviction as a crime of violence. We affirm.\n We recently revisited the definition of “crime of violence,” in one of the\nmost consequential en banc rulings our court has issued in recent years. See\n\n\n\n * Judge Higginson concurs in the judgment only.\n\f Case: 17-20526 Document: 00514857955 Page: 2 Date Filed: 03/01/2019\n\n\n\n No. 17-20526\nUnited States v. Reyes-Contreras, 910 F.3d 169 (5th Cir. 2018) (en banc). That\nen banc decision expressly overruled no fewer than eighteen of our prior circuit\nprecedents.\n No court approaches the act of overruling one of its prior precedents\nlightly—let alone eighteen of them. But our court deemed it “necessary” to do\nso, in order to bring our circuit back into alignment with the statutory text as\nenacted by Congress and construed by the Supreme Court, not to mention\nnumerous precedents of our sister circuits. Id. at 173. In doing so, Reyes-\nContreras provided important clarity to the issues that originally gave birth to\nthis appeal, as it undoubtedly will in countless other pending and future\nappeals in our circuit.\n Congress defined “crime of violence” in 18 U.S.C. § 16(a) to include “an\noffense that has as an element the use, attempted use, or threatened use of\nphysical force against the person or property of another.” Gomez Gomez argues\nthat aggravated assault under Tex. Penal Code § 22.02(a)(1) is not a crime of\nviolence, because the offense can be committed through indirect as well as\ndirect uses of force.\n This argument might have had some force prior to Reyes-Contreras,\nunder our precedents that recognized a distinction between direct and indirect\nuses of force. But we abrogated that distinction in Reyes-Contreras. 910 F.3d\nat 180–81. We now instead recognize, consistent with the Supreme Court’s\ndecision in United States v. Castleman, 572 U.S. 157, 162–68 (2014), that the\n“use of force” under 18 U.S.C. § 16(a) incorporates the common-law definition\nof force—and thus includes indirect as well as direct applications of force.\n Recognizing the significance of our en banc ruling in Reyes-Contreras,\nGomez Gomez argues that it should not apply precisely because it is a change\nin the law. That is, he argues that retroactively applying Reyes-Contreras to\nhis sentence would violate the Ex Post Facto Clause of Article I, Section 9 of\n 2\n\f Case: 17-20526 Document: 00514857955 Page: 3 Date Filed: 03/01/2019\n\n\n\n No. 17-20526\nthe Constitution. But the Ex Post Facto Clause does not apply to the judiciary.\nSee, e.g., Rogers v. Tennessee, 532 U.S. 451, 460 (2001) (“The Ex Post Facto\nClause, by its own terms, does not apply to courts.”).\n A retroactive application of a judicial decision can in theory violate the\nDue Process Clause. For example, in Bouie v. City of Columbia, 378 U.S. 347\n(1964), the Supreme Court held that a defendant’s due process rights could be\nviolated by a retroactive application of an unexpected and indefensible\nexpansion of substantive criminal liability. Id. at 353–54.\n But Reyes-Contreras did not make previously innocent activities\ncriminal. It merely reconciled our circuit precedents with the Supreme Court’s\ndecision in Castleman. As our ruling explained: “The Fifth Circuit stands\nalone in restricting the reasoning of Castleman on direct versus indirect force\nto misdemeanor crimes of domestic violence.” Reyes-Contreras, 910 F.3d at\n180. We simply backed away from our anomalous position and aligned our\ncircuit with the precedents of other circuits. In short, Reyes-Contreras was\nneither unexpected nor indefensible. See also United States v. Martinez, 496\nF.3d 387, 390 (5th Cir. 2007) (holding that a retroactive application of a judicial\ndecision resolving a circuit split to a defendant’s sentencing was not a violation\nof due process under Bouie).\n That conclusion dooms this appeal. In Reyes-Contreras, we held that\nCastleman “is not limited to cases of domestic violence,” and “that for purposes\nof identifying a conviction as a [crime of violence], there is no valid distinction\nbetween direct and indirect force.” 910 F.3d at 182. This holding forecloses\nGomez Gomez’s use of the distinction between direct and indirect force—a\ndistinction he had hoped would help him establish that aggravated assault\nunder Texas law is not a crime of violence under 18 U.S.C. § 16. See also\nUnited States v. Villegas-Hernandez, 468 F.3d 874 (5th Cir. 2006) (holding that\nTexas simple bodily assault does not require the use of force and is therefore\n 3\n\f Case: 17-20526 Document: 00514857955 Page: 4 Date Filed: 03/01/2019\n\n\n\n No. 17-20526\nnot a crime of violence), overruled by Reyes-Contreras, 910 F.3d at 181–82 (“We\ntherefore necessarily overrule Part I.A of Villegas-Hernandez . . . to the extent\nthat Villegas-Hernandez concluded that indirect force does not constitute the\nuse of physical force.”). Accordingly, we affirm.\n\n\n\n\n 4\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Plaintiff-Appellee v. Alan Victor GOMEZ GOMEZ, Defendant-Appellant\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-01\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 17-20526 Document: 00514857955 Page: 1 Date Filed: 03/01/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n No. 17-20526 FILED\\n February 26, 2019\\n Lyle W. Cayce\\nUNITED STATES OF AMERICA, Clerk\\n\\n Plaintiff - Appellee\\n\\nv.\\n\\nALAN VICTOR GOMEZ GOMEZ,\\n\\n Defendant - Appellant\\n\\n\\n\\n\\n Appeal from the United States District Court\\n for the Southern District of Texas\\n\\n\\nBefore CLEMENT, HIGGINSON, and HO, Circuit Judges. *\\nJAMES C. HO, Circuit Judge:\\n Alan Victor Gomez Gomez pled guilty to illegally reentering the United\\nStates after deportation. The district court sentenced him under 8 U.S.C.\\n§ 1326(b)(2), based on the conclusion that his prior conviction for aggravated\\nassault constitutes a “crime of violence” under 18 U.S.C. § 16, and thus an\\naggravated felony under 8 U.S.C. § 1101(a)(43)(F). On appeal, he challenges\\nthe characterization of his prior conviction as a crime of violence. We affirm.\\n We recently revisited the definition of “crime of violence,” in one of the\\nmost consequential en banc rulings our court has issued in recent years. See\\n\\n\\n\\n * Judge Higginson concurs in the judgment only.\\n\\f Case: 17-20526 Document: 00514857955 Page: 2 Date Filed: 03/01/2019\\n\\n\\n\\n No. 17-20526\\nUnited States v. Reyes-Contreras, 910 F.3d 169 (5th Cir. 2018) (en banc). That\\nen banc decision expressly overruled no fewer than eighteen of our prior circuit\\nprecedents.\\n No court approaches the act of overruling one of its prior precedents\\nlightly—let alone eighteen of them. But our court deemed it “necessary” to do\\nso, in order to bring our circuit back into alignment with the statutory text as\\nenacted by Congress and construed by the Supreme Court, not to mention\\nnumerous precedents of our sister circuits. Id. at 173. In doing so, Reyes-\\nContreras provided important clarity to the issues that originally gave birth to\\nthis appeal, as it undoubtedly will in countless other pending and future\\nappeals in our circuit.\\n Congress defined “crime of violence” in 18 U.S.C. § 16(a) to include “an\\noffense that has as an element the use, attempted use, or threatened use of\\nphysical force against the person or property of another.” Gomez Gomez argues\\nthat aggravated assault under Tex. Penal Code § 22.02(a)(1) is not a crime of\\nviolence, because the offense can be committed through indirect as well as\\ndirect uses of force.\\n This argument might have had some force prior to Reyes-Contreras,\\nunder our precedents that recognized a distinction between direct and indirect\\nuses of force. But we abrogated that distinction in Reyes-Contreras. 910 F.3d\\nat 180–81. We now instead recognize, consistent with the Supreme Court’s\\ndecision in United States v. Castleman, 572 U.S. 157, 162–68 (2014), that the\\n“use of force” under 18 U.S.C. § 16(a) incorporates the common-law definition\\nof force—and thus includes indirect as well as direct applications of force.\\n Recognizing the significance of our en banc ruling in Reyes-Contreras,\\nGomez Gomez argues that it should not apply precisely because it is a change\\nin the law. That is, he argues that retroactively applying Reyes-Contreras to\\nhis sentence would violate the Ex Post Facto Clause of Article I, Section 9 of\\n 2\\n\\f Case: 17-20526 Document: 00514857955 Page: 3 Date Filed: 03/01/2019\\n\\n\\n\\n No. 17-20526\\nthe Constitution. But the Ex Post Facto Clause does not apply to the judiciary.\\nSee, e.g., Rogers v. Tennessee, 532 U.S. 451, 460 (2001) (“The Ex Post Facto\\nClause, by its own terms, does not apply to courts.”).\\n A retroactive application of a judicial decision can in theory violate the\\nDue Process Clause. For example, in Bouie v. City of Columbia, 378 U.S. 347\\n(1964), the Supreme Court held that a defendant’s due process rights could be\\nviolated by a retroactive application of an unexpected and indefensible\\nexpansion of substantive criminal liability. Id. at 353–54.\\n But Reyes-Contreras did not make previously innocent activities\\ncriminal. It merely reconciled our circuit precedents with the Supreme Court’s\\ndecision in Castleman. As our ruling explained: “The Fifth Circuit stands\\nalone in restricting the reasoning of Castleman on direct versus indirect force\\nto misdemeanor crimes of domestic violence.” Reyes-Contreras, 910 F.3d at\\n180. We simply backed away from our anomalous position and aligned our\\ncircuit with the precedents of other circuits. In short, Reyes-Contreras was\\nneither unexpected nor indefensible. See also United States v. Martinez, 496\\nF.3d 387, 390 (5th Cir. 2007) (holding that a retroactive application of a judicial\\ndecision resolving a circuit split to a defendant’s sentencing was not a violation\\nof due process under Bouie).\\n That conclusion dooms this appeal. In Reyes-Contreras, we held that\\nCastleman “is not limited to cases of domestic violence,” and “that for purposes\\nof identifying a conviction as a [crime of violence], there is no valid distinction\\nbetween direct and indirect force.” 910 F.3d at 182. This holding forecloses\\nGomez Gomez’s use of the distinction between direct and indirect force—a\\ndistinction he had hoped would help him establish that aggravated assault\\nunder Texas law is not a crime of violence under 18 U.S.C. § 16. See also\\nUnited States v. Villegas-Hernandez, 468 F.3d 874 (5th Cir. 2006) (holding that\\nTexas simple bodily assault does not require the use of force and is therefore\\n 3\\n\\f Case: 17-20526 Document: 00514857955 Page: 4 Date Filed: 03/01/2019\\n\\n\\n\\n No. 17-20526\\nnot a crime of violence), overruled by Reyes-Contreras, 910 F.3d at 181–82 (“We\\ntherefore necessarily overrule Part I.A of Villegas-Hernandez . . . to the extent\\nthat Villegas-Hernandez concluded that indirect force does not constitute the\\nuse of physical force.”). Accordingly, we affirm.\\n\\n\\n\\n\\n 4\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1073,"cells":{"id":{"kind":"number","value":4595935,"string":"4,595,935"},"name":{"kind":"string","value":"UNITED STATES of America, Plaintiff-Appellee, v. Oladimeji Seun AYELOTAN; Femi Alexander Mewase; Rasaq Aderoju Raheem, Defendants-Appellants."},"name_abbreviation":{"kind":"string","value":"United States v. Oladimeji Ayelotan"},"decision_date":{"kind":"string","value":"2019-03-04"},"docket_number":{"kind":"string","value":"17-60397"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Stewart, Dennis, Willett\", \"parties\": \"\", \"opinions\": [{\"author\": \"DON R. WILLETT, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 17-60397 Document: 00514858253 Page: 1 Date Filed: 03/04/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n No. 17-60397 FILED\\n March 4, 2019\\n Lyle W. Cayce\\nUNITED STATES OF AMERICA, Clerk\\n\\n Plaintiff–Appellee,\\n\\nv.\\n\\nOLADIMEJI SEUN AYELOTAN; FEMI ALEXANDER MEWASE; RASAQ\\nADEROJU RAHEEM,\\n\\n Defendants–Appellants.\\n\\n\\n Appeals from the United States District Court\\n for the Southern District of Mississippi\\n\\n\\nBefore STEWART, Chief Judge, and DENNIS and WILLETT, Circuit Judges.\\nDON R. WILLETT, Circuit Judge:\\n Three Africa-based cybercriminals—Oladimeji Ayelotan, Femi Mewase,\\nand Rasaq Raheem—masterminded a sprawling international romance scam\\nthat stole hearts, and money. Posing as bachelors (and bachelorettes) online,\\nthese Nigerian nationals kindled digital romances with scores of lovelorn\\nAmericans. The fraudsters sat at overseas computers, prowling the Internet\\nand spinning false promises of love and romance, ultimately duping their\\nunsuspecting victims into sending money to Nigeria and South Africa.\\n Many fauxmance swindlers escape scot-free, their victims, broke and\\nbrokenhearted, too embarrassed to come forward. Not this time. A wary target\\nreported her suspicions, and the scammers didn’t fare as well in court as they\\nhad online. After a 16-day trial, the jury convicted them, and the district court\\n\\f Case: 17-60397 Document: 00514858253 Page: 2 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nimposed lengthy prison sentences. This appeal alleges several errors—the\\ndistrict court’s imposition of leg restraints during trial; the admission of emails\\nand a nonoriginal passport; the dismissal of a juror during trial; and the\\nsentences handed down.\\n Each argument is meritless, and we AFFIRM.\\n\\n I. BACKGROUND\\n The transnational romance scam worked like this: Ayelotan, Mewase,\\nand Raheem—along with their coconspirators—stole personal information\\nsuch as names, Social Security numbers, credit card numbers, and bank\\naccount numbers. They then impersonated their victims—getting cash\\nadvances and transferring funds out of the victims’ accounts.\\n But they needed a safe way to transfer the fruits of their crimes. Thus\\ntheir digital dalliances. Using dating websites like “seniorpeoplemeet.com,”\\nwell-honed conversation scripts, and step-by-step guides, the conspirators\\ncultivated online relationships, then sweet-talked their “paramours” into\\nlaundering their money. Next, the conspirators would cajole their enamored\\nvictims into becoming money mules, conduits for stolen funds, even providing\\nprepaid shipping labels for the swindled cash and goods.\\n Everything was going according to plan until one prospective money\\nmule grew suspicious. She reported her experience to the police, who ran it by\\nHomeland Security Investigations (the Department of Homeland Security’s\\ninvestigation arm). Agent Todd Williams, posing over email as the target\\nvictim, helped unravel the whole scheme.\\n The district court held a 16-day trial, during which it put the three\\ndefendants in leg restraints. The court also removed and replaced one of the\\njurors.\\n The jury convicted Ayelotan and Raheem on several counts of conspiracy\\nto commit mail fraud, wire fraud, and bank fraud; conspiracy to commit\\n 2\\n\\f Case: 17-60397 Document: 00514858253 Page: 3 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nidentity theft, use of unauthorized access devices, and theft of government\\nproperty; mail fraud; and conspiracy to commit money laundering.\\n The jury acquitted Mewase of conspiracy to commit money laundering.\\nBut it convicted him of conspiracy to commit mail fraud, wire fraud, and bank\\nfraud; and conspiracy to commit identity theft, use of unauthorized access\\ndevices, and theft of government property.\\n The defendants filed post-trial motions for relief. But the district court\\nsentenced each defendant to the statutory maximum for each conviction,\\nrunning consecutively.\\n\\n II. STANDARD OF REVIEW\\n The arguments raised on appeal involve varying standards of review. We\\nreview decisions to shackle criminal defendants, admit evidence, and remove\\njurors for abuse of discretion. 1 And it is an abuse of discretion to apply an\\nerroneous view of the law or to clearly err in assessing evidence. 2 We review\\nalleged Confrontation Clause violations de novo. 3\\n As for sentencing, we review fact findings for clear error and application\\nof the Sentencing Guidelines de novo. 4 And as the Supreme Court requires, we\\nreview the substantive reasonableness of sentences for abuse of discretion. 5\\n Finally, the Supreme Court directs us to review arguments raised for the\\nfirst time on appeal for plain error. 6 In Puckett, the Court elaborated that\\nunder this standard of review, defendants must first establish an error. 7 Next,\\n\\n\\n\\n\\n 1 United States v. Ebron, 683 F.3d 105, 125 (5th Cir. 2012); United States v. Yi, 460\\nF.3d 623, 634 (5th Cir. 2006); United States v. Hope, 102 F.3d 114, 117 (5th Cir. 1996).\\n 2 United States v. Ragsdale, 426 F.3d 765, 774 (5th Cir. 2005).\\n 3 United States v. Morgan, 505 F.3d 332, 338 (5th Cir. 2007) (per curiam).\\n 4 United States v. Trujillo, 502 F.3d 353, 356 (5th Cir. 2007).\\n 5 Gall v. United States, 552 U.S. 38, 51 (2007).\\n 6 Puckett v. United States, 556 U.S. 129, 135 (2009).\\n 7 Id.\\n\\n 3\\n\\f Case: 17-60397 Document: 00514858253 Page: 4 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nthey must show that it’s clear or obvious. 8 Then, they must prove that the error\\naffected their substantial rights. 9 And if they satisfy these three prongs, we\\nmay correct the error—if it “seriously affects the fairness, integrity, or public\\nreputation of judicial proceedings.” 10\\n\\n III. DISCUSSION\\n Ayelotan, Raheem, and Mewase bring assorted challenges—none\\navailing—to their convictions and sentences:\\n • Ayelotan and Raheem—the shackling of their legs during trial\\n • Raheem and Mewase—the admission of various emails and\\n Mewase’s nonoriginal passport\\n • Ayelotan and Mewase—the dismissal of a juror\\n • All three defendants—their sentences\\nA. Shackling the defendants at trial was not an abuse of discretion.\\n Ayelotan and Raheem claim that shackling their legs violated their due\\nprocess rights. As the Supreme Court explained 14 years ago in Deck, the Fifth\\nand Fourteenth Amendments’ due process clauses require courts to have a\\n“particular reason” for shackling; “only in the presence of a special need.” 11 And\\nthe Court forbids visible restraints altogether unless “justified by an essential\\nstate interest” specific to that trial. 12\\n What reasons are enough? Some 25 years ago, in Wilkerson, we held that\\ncourts may shackle defendants when there’s a danger of harm or escape. 13 As\\nwe said then, “[w]e do not underestimate the need to restrain dangerous\\ndefendants to prevent courtroom attacks, or the need to give trial courts\\n\\n\\n 8 Id.\\n 9 Id.\\n 10 Id. (cleaned up).\\n 11 Deck v. Missouri, 544 U.S. 622, 626–28 (2005).\\n 12 Id. at 628–29 (quoting Holbrook v. Fynn, 475 U.S. 560, 568–69 (1986)).\\n 13 Wilkerson v. Whitley, 16 F.3d 64, 68 (5th Cir. 2003).\\n\\n 4\\n\\f Case: 17-60397 Document: 00514858253 Page: 5 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nlatitude in making individualized security determinations.” 14 And a few years\\nbefore that, in Ellender, we stated that district courts “may rely heavily on the\\nU.S. Marshal’s advice” in considering restraints. 15\\n Here, the court had valid reasons: Ayelotan and Raheem posed a danger.\\nAnd the facts show that. For example, at Ayelotan’s extradition hearing, he\\nand other defendants caused such a ruckus that SWAT had to be called in. The\\ndistrict court stressed this concern. And given the extradition escapades, the\\nU.S. Marshals expressed unease too—recommending that the court restrain\\nthe defendants at trial. The court had a valid, particularized reason for\\nshackling the defendants.\\n Plus, the defendants’ restraints weren’t visible. Neither Ayelotan nor\\nRaheem even claim that the restraints were visible. Neither defendant raises\\nany evidence suggesting that the jury saw the restraints. And Raheem asserts\\nmerely that it’s impossible to be sure that a juror never saw him in shackles.\\n In sum, the district court had compelling reasons for shackling the\\ndefendants, and there’s no evidence the jury even saw the restraints. And so\\nthe district court didn’t violate the defendants’ due process rights.\\nB. The emails and copy of Mewase’s passport were admissible.\\n At trial, the Government admitted oodles of emails that the defendants\\nsent to their romantic targets. These emails all came from Google and Yahoo!\\naccounts. And they revealed the defendants’ fraudulent activities. They also\\nincluded instructions for money mules to send cash and progress updates on\\ntheir various schemes. 16 The defendants filed pretrial objections to admission\\nof the emails. But the district court held that the emails and transmittal\\n\\n\\n\\n\\n 14 Id.\\n 15 United States v. Ellender, 947 F.2d 748, 760 (5th Cir. 1991).\\n 16 Id.\\n\\n 5\\n\\f Case: 17-60397 Document: 00514858253 Page: 6 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nrecords, accompanied by Google and Yahoo! records-custodian certificates,\\nwere admissible self-authenticating business records.\\n On appeal, Raheem and Mewase challenge the admission of these emails\\nand records under the Federal Rules of Evidence and the Confrontation\\nClause. Mewase also contends that admission of a duplicate copy of his\\npassport identification page violated the Best Evidence Rule. Both challenges\\nfail.\\n 1. Federal Rules of Evidence\\n The Federal Rules of Evidence ban hearsay—out-of-court statements\\nmade to prove the truth of what’s asserted. 17 But there are exceptions. Here,\\neach email represented two “statements” for purposes of the Federal Rules of\\nEvidence. First was the transmittal certificate—effectively, the email\\nprovider’s statement that one user wrote and sent a message to another user\\nat the recorded time. Second, the content of each email is also a statement. We\\ntake them in that order.\\n The Federal Rules of Evidence except business records from hearsay. 18\\nTo qualify, a records custodian with knowledge must testify unless they’re\\n“self-authenticating.” 19 Records are self-authenticating if they include a\\ncustodian certification that the records “meet[] the requirements of Rule\\n803(6)(A)–(C).” 20\\n All the email records from this conspiracy included certificates. The\\ncertificates stated that Google or Yahoo! recorded the transmittal data\\nautomatically when users send emails, as part of the regular practice of a\\n\\n\\n\\n FED. R. EVID. 801(c) (“‘Hearsay’ means a statement that: (1) the declarant does not\\n 17\\n\\nmake while testifying at the current trial or hearing; and (2) a party offers in evidence to\\nprove the truth of the matter asserted in the statement.”).\\n 18 FED. R. EVID. 803(6).\\n 19 FED. R. EVID. 803(6); FED. R. EVID. 902(11).\\n 20 FED. R. EVID. 902(11).\\n\\n 6\\n\\f Case: 17-60397 Document: 00514858253 Page: 7 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nregularly conducted business activity. This satisfies Rule 803(6)’s\\nrequirements for admission. 21 As we explained in our 1991 Wilson decision,\\ncertificates from a records custodian that “track the language of Rule 803(6)\\nnearly word for word” render the records self-authenticating. 22 Thus, the\\ndistrict court didn’t abuse its discretion by finding a valid hearsay exception\\nfor the certificates.\\n The second possible hearsay is the emails’ substantive content: the\\nmessages between the defendants and their coconspirators. But these were\\nadmissible too. The Government didn’t offer these statements to prove the\\ncontent of them. 23 Same with the e-mule messages.\\n Rather, these statements were “the operative words of [the] criminal\\naction”—what we called “paradigmatic nonhearsay” in our 1981 case Jones. 24\\nThe remaining content in the emails—updates between the coconspirators\\nabout their criminal scheme—was admissible as opposing party and\\ncoconspirator statements under Rule 801(d). 25\\n\\n\\n\\n 21 FED. R. EVID. 803(6) (“The following are not excluded by the rule against hearsay,\\nregardless of whether the declarant is available as a witness: A record of an act, event,\\ncondition, opinion, or diagnosis if: (A) the record was made at or near the time by—or from\\ninformation transmitted by—someone with knowledge; (B) the record was kept in the course\\nof a regularly conducted activity of a business, organization, occupation, or calling, whether\\nor not for profit; (C) making the record was a regular practice of that activity; (D) all these\\nconditions are shown by the testimony of the custodian or another qualified witness, or by a\\ncertification that complies with Rule 902(11) or (12) or with a statute permitting certification;\\nand (E) the opponent does not show that the source of information or the method or\\ncircumstances of preparation indicate a lack of trustworthiness.”).\\n 22 Wilson v. Zapata Off-Shore Co., 939 F.2d 260, 272 (5th Cir. 1991).\\n 23 FED. R. EVID. 801(c)(2).\\n 24 United States v. Jones, 663 F.2d 567, 571 (5th Cir. 1981).\\n 25 FED. R. EVID. 801(d)(2) (“A statement that meets the following conditions is not\\n\\nhearsay: . . . The statement is offered against an opposing party and: (A) was made by the\\nparty in an individual or representative capacity; (B) is one the party manifested that it\\nadopted or believed to be true; (C) was made by a person whom the party authorized to make\\na statement on the subject; (D) was made by the party’s agent or employee on a matter within\\nthe scope of that relationship and while it existed; or (E) was made by the party’s\\ncoconspirator during and in furtherance of the conspiracy.”).\\n 7\\n\\f Case: 17-60397 Document: 00514858253 Page: 8 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\n 2. Confrontation Clause\\n Our Confrontation Clause analysis resembles our Federal Rules of\\nEvidence analysis. And likewise, the district court didn’t misstep in admitting\\nthe emails and records.\\n In 2004, the Supreme Court held in Crawford that the Confrontation\\nClause prohibits admitting out-of-court statements as evidence against\\ndefendants in a criminal case unless they can cross-examine the declarant. 26\\nBut that prohibition applies only if the statements are “testimonial.” 27\\n And two years later in Davis, the Court explained that statements are\\n“testimonial” if their “primary purpose . . . is to establish or prove past events\\npotentially relevant to later criminal prosecution.” 28 Or as the Court explained\\nin Melendez-Diaz three years after that, business records must be “for the\\nadministration of the [business’s] affairs and not for the purpose of\\nestablishing or proving some fact at trial.” 29\\n Under this framework, Google and Yahoo!’s transmittal-data records\\naren’t testimonial. Consider our Towns decision in 2013. 30 There, we\\nconsidered a pharmacy’s prescription-purchase logs. 31 We held that those\\nweren’t testimonial. 32 Rather, the pharmacy recorded those logs “ex ante to\\ncomply with state regulatory measures, not in response to active\\nprosecution.” 33 It’s the same with Google and Yahoo! They didn’t create the\\n\\n\\n\\n\\n 26 See Crawford v. Washington, 541 U.S. 36, 51–53 (2004).\\n 27 Id.\\n 28 Davis v. Washington, 547 U.S. 813, 822 (2006); see also United States v. Duron-\\n\\nCaldera, 737 F.3d 988, 992–93 (5th Cir. 2013) (quoting Davis for that proposition).\\n 29 Melendez-Diaz v. Massachusetts, 557 U.S. 305, 324 (2009).\\n 30 United States v. Towns, 718 F.3d 404, 411 (5th Cir. 2013).\\n 31 Id.\\n 32 Id.\\n 33 Id.\\n\\n 8\\n\\f Case: 17-60397 Document: 00514858253 Page: 9 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nrecords to prove a particular fact at a particular trial—let alone this trial. The\\nrecords are admissible as far as the Confrontation Clause goes.\\n So are the coconspirator statements. Take our 2011 decision in\\nJackson. 34 In that case, we explained that—as a general matter—\\n“coconspirator statements made during the course and in furtherance of a\\nconspiracy” aren’t testimonial. 35 So the district court didn’t violate the\\ndefendants’ Confrontation Clause rights by admitting this evidence.\\n 3. Best Evidence Rule\\n Mewase also contends that the passport copy was inadmissible under the\\nBest Evidence Rule. True, the Federal Rules of Evidence require using “[a]n\\noriginal writing, recording, or photograph” as evidence of that item’s contents\\nat trial. 36 But the Rules clarify that “[a] duplicate is admissible to the same\\nextent as the original unless a genuine question is raised about the original’s\\nauthenticity or the circumstances make it unfair to admit a duplicate.” 37\\n Mewase’s original passport went missing during his extradition. And\\nMewase acknowledges that it wasn’t the Government’s fault. Even so, he still\\nclaims that relying on the duplicate isn’t fair. And yet he doesn’t explain why.\\nSo the district court didn’t abuse its discretion in admitting the duplicate.\\nC. The district court properly removed and replaced Juror 20.\\n Ayelotan and Mewase contend that the district court’s decision to remove\\nJuror 20 violated their due process rights. We review the removal and\\nreplacement of a juror for abuse of discretion. 38 And as we explained in\\n\\n\\n\\n\\n 34 United States v. Jackson, 636 F.3d 687, 692 (5th Cir. 2011).\\n 35 Id.\\n 36 FED. R. EVID. 1002.\\n 37 FED. R. EVID. 1003.\\n 38 United States v. Huntress, 956 F.2d 1309, 1312 (5th Cir. 1992).\\n\\n 9\\n\\f Case: 17-60397 Document: 00514858253 Page: 10 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nHuntress, a court may not dismiss a juror “without factual support or for a\\nlegally irrelevant reason.” 39\\n\\n\\n The Federal Rules of Criminal Procedure allow a judge to remove jurors\\nwho cannot perform their duties. 40 We explained what that means long ago.\\nForty-plus years ago in Smith, we held that “a juror who cannot remain awake\\nduring much of the trial is unable to perform his duty.” 41 And in 2002, we\\nexplained in Edwards that other good reasons for removal include a “lack of\\ncandor” and an “inability or unwillingness to follow instructions.” 42\\n Here, the district court identified legally relevant reasons for removing\\nJuror 20. The juror slept through witness testimony; misrepresented this fact\\nto the district court when asked; didn’t understand, or else didn’t follow, the\\njury instructions; and didn’t deliberate.\\n Ample evidence supported these legitimate reasons. Near the end of the\\nfirst day of jury deliberations, the foreperson delivered two notes to the court:\\n We have one person that is undecided, and we [cannot] get an\\n answer from him.\\n\\n One, we have a juror that has admitted that he slept through some\\n of the testimony; two, he doesn’t believe you can’t go to Western\\n Union and pick up transaction, his opinion/own notation; three, he\\n refuses to follow the judge’s instruction.\\nAfter reviewing the notes, the court called in the foreperson, Juror 20, and\\nevery other juror one at a time.\\n When the district court asked Juror 20 about sleeping through the trial,\\nhe admitted that he may have “nodded off.” But he said that if he did, “it was\\nvery minimal.” Yet his fellow jurors testified otherwise. Some said that Juror\\n\\n\\n 39 Id.\\n 40 FED. R. CRIM. P. 24(c) (permitting removal of jurors who are “unable to perform or\\nare disqualified from performing their duties”).\\n 41 United States v. Smith, 550 F.2d 277, 285 (5th Cir. 1977).\\n 42 United States v. Edwards, 303 F.3d 606, 631–32 (5th Cir. 2002).\\n\\n 10\\n\\f Case: 17-60397 Document: 00514858253 Page: 11 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\n20 admitted that he “was asleep some of the time, so [he] may have missed\\nthings.” And others said he confessed that “he may not have heard everything\\nhe needed to hear” since he fell asleep.\\n Many jurors even said they saw him sleeping more than just a “minimal”\\namount, including his neighboring juror:\\n I sat next to [Juror 20], I noticed that there was quite a few times,\\n a lot of times, that I would look over and notice that he was\\n asleep. . . . It was more than once a day . . . . I do believe that it\\n was enough to miss key information.\\nAnd several other jurors believed that Juror 20 simply couldn’t follow the law.\\n Juror 19, for example, testified that the jury pointed out specific\\ninstructions to Juror 20, which “he refused to follow”—e.g., “considering only\\nthe evidence presented” and following “the law that’s in the instructions.”\\nAnother juror questioned Juror 20’s comprehension: “He spent three hours\\nreading [the Court’s] instructions yesterday, and he got to Page 5. We’ve tried\\nto talk to him, and he just refuses.”\\n Based on this evidence, the district court removed Juror 20. But Ayelotan\\nand Mewase argue that the court really removed Juror 20 because he was a\\n“hold-out”; because he “clearly questioned Mr. Ayelotan’s guilt.” True, Juror 20\\nresisted convicting. Yet as we noted in Edwards, even “hold-out jurors are not\\nimmune from dismissal based upon just cause.” 43\\n The district court had legitimate reasons to dismiss Juror 20. And there\\nwas strong factual support for those legitimate reasons. Removing Juror 20\\nwas not an abuse of discretion.\\nD. Sentencing Challenge\\n The district court sentenced Ayelotan, Raheem, and Mewase to\\npractically interminable prison terms. The court calculated the total intended\\n\\n\\n\\n 43 Edwards, 303 F.3d at 634.\\n 11\\n\\f Case: 17-60397 Document: 00514858253 Page: 12 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nloss of their scheme: over $25 million. At a joint sentencing hearing, the court\\nheard testimony from a postal inspector and two case agents from Homeland\\nSecurity Investigations. They testified on the loss amount and the defendants’\\nroles.\\n For Ayelotan, the court imposed a 22-level increase for the intended loss.\\nAnd it imposed a 4-level enhancement for his leadership role. This came to a\\ntotal Guidelines offense level of 43. Given Ayelotan’s criminal history, his\\nGuidelines sentence was life imprisonment. The court reduced that to the\\nwithin-Guidelines statutory maximum of 95 years. 44 And it sentenced Ayelotan\\nto that.\\n For Raheem, the court also assigned a total offense level of 43 for the\\nintended loss and his leadership role. His initial sentencing range was life\\nimprisonment too. But the court again decreased it. His within-Guidelines\\nstatutory maximum was 115 years. 45 And the court sentenced him to that.\\n Finally, for Mewase, the court also applied the same 22-level increase for\\nthe intended loss. The resulting Guidelines range was 262 to 327 months. The\\ncourt reduced that to 262 to 300, the statutory maximum. The court then\\nsentenced him to 25 years.\\n All three defendants now challenge their sentences on various grounds.\\n 1. Leadership Enhancement\\n On appeal, Ayelotan and Raheem object to their leadership\\nenhancements. 46 And Ayelotan says that the court should’ve given him a\\nminor-role reduction.\\n As we explained in Hebert, the preponderance of the evidence must show\\nthat the defendant was “the organizer or leader of a criminal activity that\\n\\n\\n 44 See U.S. SENTENCING GUIDELINES MANUAL § 5G1.2(b).\\n 45 See id.\\n 46 Id. § 3B1.1(a).\\n\\n 12\\n\\f Case: 17-60397 Document: 00514858253 Page: 13 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\ninvolved five or more participants or was otherwise extensive.” 47 We will\\nreverse the enhancement only if the district court clearly erred. 48\\n To begin with, the district court found—and the trial evidence\\nsupported—that this was a major criminal undertaking. It involved far more\\nthan five participants. As for leadership, the commentary to § 3B1.1 lists\\nfactors for assessing a defendant’s role:\\n • the exercise of decision-making authority;\\n • the nature of participation in the commission of the offense;\\n • the recruitment of accomplices;\\n • the claimed right to a larger share of the fruits of the crime;\\n • the degree of participation in planning or organizing the\\n offense;\\n • the nature and scope of the illegal activity;\\n • and the degree of control and authority exercised over others. 49\\nThe commentary also clarifies that more than one person can qualify as a\\nleader of the same criminal group. 50\\n Ayelotan argues that the second superseding indictment proves that his\\nrole was “peripheral in substance” and “peripheral in duration.” He claims that\\nthe only accusation against him was that he emailed shipping-label\\ninformation.\\n But the district court specifically relied on several § 3B1.1 factors in\\ndetermining leadership roles. At sentencing, the court heard testimony from\\ncase agent Williams. Agent Williams testified that Ayelotan was among the\\n“top people within the group of indicted defendants.” Williams asserted that\\n\\n\\n\\n 47 See United States v. Hebert, 813 F.3d 551, 560 (5th Cir. 2015).\\n 48 Id.\\n 49 U.S. SENTENCING GUIDELINES MANUAL § 3B1.1 cmt. 4.\\n 50 Id.\\n\\n 13\\n\\f Case: 17-60397 Document: 00514858253 Page: 14 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nAyelotan was a “central hub to a number of other co-conspirators on a daily\\nbasis.” Agent Williams also identified Raheem as one of four coconspirators “at\\nthe top of th[e] hierarchy.”\\n Williams based this on their time spent on the conspiracy, their day-to-\\nday involvement, and the number of coconspirators who reported to them. The\\ndistrict court relied on this testimony. And it determined that Ayelotan “was\\ninvolved in almost every scam involved in the offense”; that he “participated in\\nplanning or organizing it”; and that he directly controlled other conspirators.\\nSimilarly, the court credited Williams’s testimony on Raheem’s leadership in\\nthe organization.\\n The district court did not clearly err considering the evidence before it—\\nnot with Ayelotan and not with Raheem.\\n 2. Eighth Amendment\\n Now for the first time on appeal, Ayelotan and Raheem raise an Eighth\\nAmendment argument. They assert that effective life sentences for nonviolent\\ncrimes are cruel and unusual punishment. We review arguments raised for the\\nfirst time on appeal for plain error. 51 Although Ayelotan acknowledges the\\nplain-error standard, he never briefed anything beyond the first step of the\\nplain-error test: whether an error occurred.\\n Yet even if Ayelotan had sufficiently briefed the other steps of the plain-\\nerror analysis, he still wouldn’t be entitled to relief. Yes, in extraordinary\\ncases, term-of-years sentences can be cruel and unusual. In 1992, we held in\\nMcGruder that sentences violate the Eighth Amendment when they’re “grossly\\ndisproportionate” to the convicted conduct. 52\\n\\n\\n\\n\\n 51 E.g., United States v. Mondragon-Santiago, 564 F.3d 357, 361 (5th Cir. 2009).\\n 52 McGruder v. Puckett, 954 F.2d 313, 315 (5th Cir. 1992).\\n 14\\n\\f Case: 17-60397 Document: 00514858253 Page: 15 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\n But as we’ve explained before, this review is narrow. In our 2016 case\\nMills, we underscored that a reviewing court may not “substitute its judgment\\nfor that of the legislature nor the sentencing court.” 53 And four years before\\nthat, in Looney, we acknowledged that under Supreme Court precedent,\\n“successful Eighth Amendment challenges to prison-term lengths will be\\nrare.” 54\\n Ayelotan maintains that an effective life sentence for a nonviolent,\\nfinancial crime is—by definition—grossly disproportionate. Yet he cites no\\ncases finding that lengthy sentences for financial crimes violate the Eighth\\nAmendment. He cites only to the Supreme Court’s 2010 decision in Graham 55\\nand its 1992 decision in Robinson. 56\\n But in Graham, the Supreme Court limited its decision to life sentences\\nfor minors. 57 And in Robinson, the Court held that a law criminalizing\\nnarcotics addiction was unconstitutional. 58 The Court struck down the law\\nbecause its purpose was to stigmatize addicts; not because the sentence was\\ntoo long. 59 Neither decision applies here.\\n Yet our decision in Mills does apply. There, we held that “the Guidelines\\nare a convincing objective indicator of proportionality.” 60 And in Looney, we\\nupheld effective life sentences for the nonviolent offenses of possession with\\nintent to distribute methamphetamine and possession of firearms. 61\\n\\n\\n\\n\\n 53 United States v. Mills, 843 F.3d 210, 218 (5th Cir. 2016) (citations omitted).\\n 54 United States v. Looney, 532 F.3d 392, 396 (5th Cir. 2008).\\n 55 See generally Graham v. Florida, 560 U.S. 48 (2010).\\n 56 See generally Robinson v. California, 370 U.S. 660 (1992).\\n 57 See Graham, 560 U.S. at 81.\\n 58 Robinson, 370 U.S. at 677.\\n 59 Id. at 677 & n.5.\\n 60 Mills, 843 F.3d at 218.\\n 61 Looney, 532 F.3d at 396.\\n\\n 15\\n\\f Case: 17-60397 Document: 00514858253 Page: 16 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\n Ayelotan’s and Raheem’s within-Guidelines sentences didn’t violate the\\nEighth Amendment. The district court did not err, plainly or otherwise.\\n 3. Intended Loss Calculation\\n Raheem and Mewase challenge the intended loss calculation of over $25\\nmillion. In 2012, we laid out the rule for calculating intended losses in Hebron:\\n“The applicable loss is generally the greater of actual loss—which includes only\\nreasonably foreseeable harm resulting from the fraud—and intended loss—\\nwhich includes the harm intended to result from the offense.” 62 And district\\ncourts need only make “a reasonable estimate of the loss” based on the\\nevidence. 63\\n We review these calculations for clear error. 64 In Hull, we explained that\\nwe review the foreseeability of the loss for clear error too. 65 Then in Sanders,\\nwe established that we review the loss calculation itself for clear error. 66 We\\nwon’t overturn these factual findings “unless they are implausible in light of\\nthe record as a whole.” 67\\n Raheem retorts that the record doesn’t show that they “intended to inflict\\na loss” of $25 million or more. First, that misstates the standard. The\\nSentencing Guidelines don’t require the defendant to have intended the\\nspecific loss amount. 68 Instead, the district court simply has to conclude that\\nthe defendant knew or reasonably should have known that the scheme would\\ncause the harm. 69\\n\\n\\n\\n 62 United States v. Hebron, 684 F.3d 559, 560 (5th Cir. 2012); see also United States v.\\nFairley, 880 F.3d 198, 215 (5th Cir. 2018) (quoting Hebron).\\n 63 Id. (citing U.S. SENTENCING GUIDELINES MANUAL § 2B1.1 cmt. n.3(C)).\\n 64 Id.\\n 65 United States v. Hull, 160 F.3d 265, 269 (5th Cir. 1998).\\n 66 United States v. Sanders, 343 F.3d 511, 519 (5th Cir. 2003).\\n 67 Id.\\n 68 U.S. SENTENCING GUIDELINES MANUAL § 2B1.1 cmt. 3.\\n 69 Id.\\n\\n 16\\n\\f Case: 17-60397 Document: 00514858253 Page: 17 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\n And the district court relied on testimony that showed this: “Mr. Raheem\\nand Mr. Ayelotan were directly involved in most, if not all of [the activity used\\nto calculate the loss amount], and to the extent they were not directly involved,\\nit was certainly reasonably foreseeable to them as part of the jointly\\nundertaken criminal activity which was part and parcel to this conspiracy.”\\n Second, the record does show that the intended loss was over $25 million.\\nThe district court considered the PSR’s calculations. And it heard testimony\\nfrom the postal inspector and two case agents. Based on that, the court\\ncalculated the loss at $52 million.\\n Finally, Raheem disputes the district court’s determination that there\\nwere at least 37,817 credit cards involved in the conspiracy. Rather, Raheem\\nurges that “there is no information all of the alleged credit cards were real.”\\nYet the district court heard specific evidence suggesting that the credit card\\nnumbers corresponded to real accounts. For example, Williams testified that\\nthe first six numbers on the cards—generally identifying the financial\\ninstitutions—matched with real institutions; and that the stolen information\\nincluded three-digit CVV codes on the back of each card.\\n In any event, Raheem and his coconspirators’ intended to get their hands\\non valid credit card numbers. Otherwise, their scheme could bear no fruit.\\nPhony credit cards won’t even buy you Monopoly Money—let alone cash\\nadvances. Even if some card numbers were fake, that wouldn’t matter. Again,\\ntheir intent dictates the intended loss.\\n 4. Substantive Reasonableness of Sentence\\n Finally, Raheem and Mewase contend that their sentences are\\nsubstantively unreasonable. But in 2009, we reiterated in Cooks that we\\npresume a within-Guidelines-range sentence is reasonable. 70 And we tend to\\n\\n\\n\\n 70 United States v. Cooks, 589 F.3d 173, 186 (5th Cir. 2009) (cleaned up).\\n 17\\n\\f Case: 17-60397 Document: 00514858253 Page: 18 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\ndefer to the sentencing court. As we noted in our 2011 decision in Scott, “the\\nsentencing court is in a better position to find facts and judge their import\\nunder the § 3553(a) factors.” 71\\n To rebut the presumption, a defendant must show one of three things:\\n(1) the court failed to consider a factor that it should’ve given significant\\nweight; (2) the court gave significant weight to an irrelevant or improper factor;\\nor (3) the court clearly erred in balancing sentencing factors. 72\\n Raheem argues that his sentence exceeds the aim of the § 3553(a)\\nsentencing factors. But his sentence was within-Guidelines. So it’s presumed\\nreasonable. And here, Raheem hasn’t rebutted that presumption.\\n The district court detailed its justifications and discussed the § 3553(a)\\nfactors. The court noted that Raheem was “a leader or organizer” in “a broad\\nand wide-reaching and extensive conspiracy involving criminal conduct that\\nwent on for a number of years”; one that “involved the manipulation and taking\\nadvantage of, whether financially or otherwise, a large number of victims.”\\n Mewase argues that his sentence is unreasonable because of\\n“unwarranted sentencing disparities” between him and some coconspirators\\nwho pleaded guilty. But this doesn’t rebut the presumption of reasonableness\\neither. Mewase offers no proof that he was so similarly situated to\\ncoconspirators who received lesser sentences that the disparities are\\n“unwarranted.” Nor does the PSR suggest that. Rather, many other\\ncoconspirators played much smaller roles, accepted responsibility, or\\ncooperated with the Government.\\n In sum, we have consistently declined to merely reweigh the sentencing\\nfactors. Yes, Raheem’s within-Guidelines sentence is severe. But the district\\n\\n\\n 71 United States v. Scott, 654 F.3d 552, 555 (5th Cir. 2011) (internal quotation marks\\nand citation omitted).\\n 72 Id.\\n\\n 18\\n\\f Case: 17-60397 Document: 00514858253 Page: 19 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\ncourt weighed the appropriate factors. And its sentence isn’t substantively\\nunreasonable. The district court also grounded Mewase’s sentence in an in-\\ndepth consideration of the § 3553 factors. So neither sentence is substantively\\nunreasonable.\\n\\n IV. CONCLUSION\\n The district court committed no error, and we AFFIRM in all respects.\\n\\n\\n\\n\\n 19\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4373188/\", \"author_raw\": \"DON R. WILLETT, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"STEWART"},"judge2":{"kind":"string","value":"DENNIS"},"judge3":{"kind":"string","value":"WILLETT"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4595935/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Plaintiff-Appellee, v. Oladimeji Seun AYELOTAN; Femi Alexander Mewase; Rasaq Aderoju Raheem, Defendants-Appellants.\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-04\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 17-60397 Document: 00514858253 Page: 1 Date Filed: 03/04/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\n United States Court of Appeals\n Fifth Circuit\n\n No. 17-60397 FILED\n March 4, 2019\n Lyle W. Cayce\nUNITED STATES OF AMERICA, Clerk\n\n Plaintiff–Appellee,\n\nv.\n\nOLADIMEJI SEUN AYELOTAN; FEMI ALEXANDER MEWASE; RASAQ\nADEROJU RAHEEM,\n\n Defendants–Appellants.\n\n\n Appeals from the United States District Court\n for the Southern District of Mississippi\n\n\nBefore STEWART, Chief Judge, and DENNIS and WILLETT, Circuit Judges.\nDON R. WILLETT, Circuit Judge:\n Three Africa-based cybercriminals—Oladimeji Ayelotan, Femi Mewase,\nand Rasaq Raheem—masterminded a sprawling international romance scam\nthat stole hearts, and money. Posing as bachelors (and bachelorettes) online,\nthese Nigerian nationals kindled digital romances with scores of lovelorn\nAmericans. The fraudsters sat at overseas computers, prowling the Internet\nand spinning false promises of love and romance, ultimately duping their\nunsuspecting victims into sending money to Nigeria and South Africa.\n Many fauxmance swindlers escape scot-free, their victims, broke and\nbrokenhearted, too embarrassed to come forward. Not this time. A wary target\nreported her suspicions, and the scammers didn’t fare as well in court as they\nhad online. After a 16-day trial, the jury convicted them, and the district court\n\f Case: 17-60397 Document: 00514858253 Page: 2 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\nimposed lengthy prison sentences. This appeal alleges several errors—the\ndistrict court’s imposition of leg restraints during trial; the admission of emails\nand a nonoriginal passport; the dismissal of a juror during trial; and the\nsentences handed down.\n Each argument is meritless, and we AFFIRM.\n\n I. BACKGROUND\n The transnational romance scam worked like this: Ayelotan, Mewase,\nand Raheem—along with their coconspirators—stole personal information\nsuch as names, Social Security numbers, credit card numbers, and bank\naccount numbers. They then impersonated their victims—getting cash\nadvances and transferring funds out of the victims’ accounts.\n But they needed a safe way to transfer the fruits of their crimes. Thus\ntheir digital dalliances. Using dating websites like “seniorpeoplemeet.com,”\nwell-honed conversation scripts, and step-by-step guides, the conspirators\ncultivated online relationships, then sweet-talked their “paramours” into\nlaundering their money. Next, the conspirators would cajole their enamored\nvictims into becoming money mules, conduits for stolen funds, even providing\nprepaid shipping labels for the swindled cash and goods.\n Everything was going according to plan until one prospective money\nmule grew suspicious. She reported her experience to the police, who ran it by\nHomeland Security Investigations (the Department of Homeland Security’s\ninvestigation arm). Agent Todd Williams, posing over email as the target\nvictim, helped unravel the whole scheme.\n The district court held a 16-day trial, during which it put the three\ndefendants in leg restraints. The court also removed and replaced one of the\njurors.\n The jury convicted Ayelotan and Raheem on several counts of conspiracy\nto commit mail fraud, wire fraud, and bank fraud; conspiracy to commit\n 2\n\f Case: 17-60397 Document: 00514858253 Page: 3 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\nidentity theft, use of unauthorized access devices, and theft of government\nproperty; mail fraud; and conspiracy to commit money laundering.\n The jury acquitted Mewase of conspiracy to commit money laundering.\nBut it convicted him of conspiracy to commit mail fraud, wire fraud, and bank\nfraud; and conspiracy to commit identity theft, use of unauthorized access\ndevices, and theft of government property.\n The defendants filed post-trial motions for relief. But the district court\nsentenced each defendant to the statutory maximum for each conviction,\nrunning consecutively.\n\n II. STANDARD OF REVIEW\n The arguments raised on appeal involve varying standards of review. We\nreview decisions to shackle criminal defendants, admit evidence, and remove\njurors for abuse of discretion. 1 And it is an abuse of discretion to apply an\nerroneous view of the law or to clearly err in assessing evidence. 2 We review\nalleged Confrontation Clause violations de novo. 3\n As for sentencing, we review fact findings for clear error and application\nof the Sentencing Guidelines de novo. 4 And as the Supreme Court requires, we\nreview the substantive reasonableness of sentences for abuse of discretion. 5\n Finally, the Supreme Court directs us to review arguments raised for the\nfirst time on appeal for plain error. 6 In Puckett, the Court elaborated that\nunder this standard of review, defendants must first establish an error. 7 Next,\n\n\n\n\n 1 United States v. Ebron, 683 F.3d 105, 125 (5th Cir. 2012); United States v. Yi, 460\nF.3d 623, 634 (5th Cir. 2006); United States v. Hope, 102 F.3d 114, 117 (5th Cir. 1996).\n 2 United States v. Ragsdale, 426 F.3d 765, 774 (5th Cir. 2005).\n 3 United States v. Morgan, 505 F.3d 332, 338 (5th Cir. 2007) (per curiam).\n 4 United States v. Trujillo, 502 F.3d 353, 356 (5th Cir. 2007).\n 5 Gall v. United States, 552 U.S. 38, 51 (2007).\n 6 Puckett v. United States, 556 U.S. 129, 135 (2009).\n 7 Id.\n\n 3\n\f Case: 17-60397 Document: 00514858253 Page: 4 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\nthey must show that it’s clear or obvious. 8 Then, they must prove that the error\naffected their substantial rights. 9 And if they satisfy these three prongs, we\nmay correct the error—if it “seriously affects the fairness, integrity, or public\nreputation of judicial proceedings.” 10\n\n III. DISCUSSION\n Ayelotan, Raheem, and Mewase bring assorted challenges—none\navailing—to their convictions and sentences:\n • Ayelotan and Raheem—the shackling of their legs during trial\n • Raheem and Mewase—the admission of various emails and\n Mewase’s nonoriginal passport\n • Ayelotan and Mewase—the dismissal of a juror\n • All three defendants—their sentences\nA. Shackling the defendants at trial was not an abuse of discretion.\n Ayelotan and Raheem claim that shackling their legs violated their due\nprocess rights. As the Supreme Court explained 14 years ago in Deck, the Fifth\nand Fourteenth Amendments’ due process clauses require courts to have a\n“particular reason” for shackling; “only in the presence of a special need.” 11 And\nthe Court forbids visible restraints altogether unless “justified by an essential\nstate interest” specific to that trial. 12\n What reasons are enough? Some 25 years ago, in Wilkerson, we held that\ncourts may shackle defendants when there’s a danger of harm or escape. 13 As\nwe said then, “[w]e do not underestimate the need to restrain dangerous\ndefendants to prevent courtroom attacks, or the need to give trial courts\n\n\n 8 Id.\n 9 Id.\n 10 Id. (cleaned up).\n 11 Deck v. Missouri, 544 U.S. 622, 626–28 (2005).\n 12 Id. at 628–29 (quoting Holbrook v. Fynn, 475 U.S. 560, 568–69 (1986)).\n 13 Wilkerson v. Whitley, 16 F.3d 64, 68 (5th Cir. 2003).\n\n 4\n\f Case: 17-60397 Document: 00514858253 Page: 5 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\nlatitude in making individualized security determinations.” 14 And a few years\nbefore that, in Ellender, we stated that district courts “may rely heavily on the\nU.S. Marshal’s advice” in considering restraints. 15\n Here, the court had valid reasons: Ayelotan and Raheem posed a danger.\nAnd the facts show that. For example, at Ayelotan’s extradition hearing, he\nand other defendants caused such a ruckus that SWAT had to be called in. The\ndistrict court stressed this concern. And given the extradition escapades, the\nU.S. Marshals expressed unease too—recommending that the court restrain\nthe defendants at trial. The court had a valid, particularized reason for\nshackling the defendants.\n Plus, the defendants’ restraints weren’t visible. Neither Ayelotan nor\nRaheem even claim that the restraints were visible. Neither defendant raises\nany evidence suggesting that the jury saw the restraints. And Raheem asserts\nmerely that it’s impossible to be sure that a juror never saw him in shackles.\n In sum, the district court had compelling reasons for shackling the\ndefendants, and there’s no evidence the jury even saw the restraints. And so\nthe district court didn’t violate the defendants’ due process rights.\nB. The emails and copy of Mewase’s passport were admissible.\n At trial, the Government admitted oodles of emails that the defendants\nsent to their romantic targets. These emails all came from Google and Yahoo!\naccounts. And they revealed the defendants’ fraudulent activities. They also\nincluded instructions for money mules to send cash and progress updates on\ntheir various schemes. 16 The defendants filed pretrial objections to admission\nof the emails. But the district court held that the emails and transmittal\n\n\n\n\n 14 Id.\n 15 United States v. Ellender, 947 F.2d 748, 760 (5th Cir. 1991).\n 16 Id.\n\n 5\n\f Case: 17-60397 Document: 00514858253 Page: 6 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\nrecords, accompanied by Google and Yahoo! records-custodian certificates,\nwere admissible self-authenticating business records.\n On appeal, Raheem and Mewase challenge the admission of these emails\nand records under the Federal Rules of Evidence and the Confrontation\nClause. Mewase also contends that admission of a duplicate copy of his\npassport identification page violated the Best Evidence Rule. Both challenges\nfail.\n 1. Federal Rules of Evidence\n The Federal Rules of Evidence ban hearsay—out-of-court statements\nmade to prove the truth of what’s asserted. 17 But there are exceptions. Here,\neach email represented two “statements” for purposes of the Federal Rules of\nEvidence. First was the transmittal certificate—effectively, the email\nprovider’s statement that one user wrote and sent a message to another user\nat the recorded time. Second, the content of each email is also a statement. We\ntake them in that order.\n The Federal Rules of Evidence except business records from hearsay. 18\nTo qualify, a records custodian with knowledge must testify unless they’re\n“self-authenticating.” 19 Records are self-authenticating if they include a\ncustodian certification that the records “meet[] the requirements of Rule\n803(6)(A)–(C).” 20\n All the email records from this conspiracy included certificates. The\ncertificates stated that Google or Yahoo! recorded the transmittal data\nautomatically when users send emails, as part of the regular practice of a\n\n\n\n FED. R. EVID. 801(c) (“‘Hearsay’ means a statement that: (1) the declarant does not\n 17\n\nmake while testifying at the current trial or hearing; and (2) a party offers in evidence to\nprove the truth of the matter asserted in the statement.”).\n 18 FED. R. EVID. 803(6).\n 19 FED. R. EVID. 803(6); FED. R. EVID. 902(11).\n 20 FED. R. EVID. 902(11).\n\n 6\n\f Case: 17-60397 Document: 00514858253 Page: 7 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\nregularly conducted business activity. This satisfies Rule 803(6)’s\nrequirements for admission. 21 As we explained in our 1991 Wilson decision,\ncertificates from a records custodian that “track the language of Rule 803(6)\nnearly word for word” render the records self-authenticating. 22 Thus, the\ndistrict court didn’t abuse its discretion by finding a valid hearsay exception\nfor the certificates.\n The second possible hearsay is the emails’ substantive content: the\nmessages between the defendants and their coconspirators. But these were\nadmissible too. The Government didn’t offer these statements to prove the\ncontent of them. 23 Same with the e-mule messages.\n Rather, these statements were “the operative words of [the] criminal\naction”—what we called “paradigmatic nonhearsay” in our 1981 case Jones. 24\nThe remaining content in the emails—updates between the coconspirators\nabout their criminal scheme—was admissible as opposing party and\ncoconspirator statements under Rule 801(d). 25\n\n\n\n 21 FED. R. EVID. 803(6) (“The following are not excluded by the rule against hearsay,\nregardless of whether the declarant is available as a witness: A record of an act, event,\ncondition, opinion, or diagnosis if: (A) the record was made at or near the time by—or from\ninformation transmitted by—someone with knowledge; (B) the record was kept in the course\nof a regularly conducted activity of a business, organization, occupation, or calling, whether\nor not for profit; (C) making the record was a regular practice of that activity; (D) all these\nconditions are shown by the testimony of the custodian or another qualified witness, or by a\ncertification that complies with Rule 902(11) or (12) or with a statute permitting certification;\nand (E) the opponent does not show that the source of information or the method or\ncircumstances of preparation indicate a lack of trustworthiness.”).\n 22 Wilson v. Zapata Off-Shore Co., 939 F.2d 260, 272 (5th Cir. 1991).\n 23 FED. R. EVID. 801(c)(2).\n 24 United States v. Jones, 663 F.2d 567, 571 (5th Cir. 1981).\n 25 FED. R. EVID. 801(d)(2) (“A statement that meets the following conditions is not\n\nhearsay: . . . The statement is offered against an opposing party and: (A) was made by the\nparty in an individual or representative capacity; (B) is one the party manifested that it\nadopted or believed to be true; (C) was made by a person whom the party authorized to make\na statement on the subject; (D) was made by the party’s agent or employee on a matter within\nthe scope of that relationship and while it existed; or (E) was made by the party’s\ncoconspirator during and in furtherance of the conspiracy.”).\n 7\n\f Case: 17-60397 Document: 00514858253 Page: 8 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\n 2. Confrontation Clause\n Our Confrontation Clause analysis resembles our Federal Rules of\nEvidence analysis. And likewise, the district court didn’t misstep in admitting\nthe emails and records.\n In 2004, the Supreme Court held in Crawford that the Confrontation\nClause prohibits admitting out-of-court statements as evidence against\ndefendants in a criminal case unless they can cross-examine the declarant. 26\nBut that prohibition applies only if the statements are “testimonial.” 27\n And two years later in Davis, the Court explained that statements are\n“testimonial” if their “primary purpose . . . is to establish or prove past events\npotentially relevant to later criminal prosecution.” 28 Or as the Court explained\nin Melendez-Diaz three years after that, business records must be “for the\nadministration of the [business’s] affairs and not for the purpose of\nestablishing or proving some fact at trial.” 29\n Under this framework, Google and Yahoo!’s transmittal-data records\naren’t testimonial. Consider our Towns decision in 2013. 30 There, we\nconsidered a pharmacy’s prescription-purchase logs. 31 We held that those\nweren’t testimonial. 32 Rather, the pharmacy recorded those logs “ex ante to\ncomply with state regulatory measures, not in response to active\nprosecution.” 33 It’s the same with Google and Yahoo! They didn’t create the\n\n\n\n\n 26 See Crawford v. Washington, 541 U.S. 36, 51–53 (2004).\n 27 Id.\n 28 Davis v. Washington, 547 U.S. 813, 822 (2006); see also United States v. Duron-\n\nCaldera, 737 F.3d 988, 992–93 (5th Cir. 2013) (quoting Davis for that proposition).\n 29 Melendez-Diaz v. Massachusetts, 557 U.S. 305, 324 (2009).\n 30 United States v. Towns, 718 F.3d 404, 411 (5th Cir. 2013).\n 31 Id.\n 32 Id.\n 33 Id.\n\n 8\n\f Case: 17-60397 Document: 00514858253 Page: 9 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\nrecords to prove a particular fact at a particular trial—let alone this trial. The\nrecords are admissible as far as the Confrontation Clause goes.\n So are the coconspirator statements. Take our 2011 decision in\nJackson. 34 In that case, we explained that—as a general matter—\n“coconspirator statements made during the course and in furtherance of a\nconspiracy” aren’t testimonial. 35 So the district court didn’t violate the\ndefendants’ Confrontation Clause rights by admitting this evidence.\n 3. Best Evidence Rule\n Mewase also contends that the passport copy was inadmissible under the\nBest Evidence Rule. True, the Federal Rules of Evidence require using “[a]n\noriginal writing, recording, or photograph” as evidence of that item’s contents\nat trial. 36 But the Rules clarify that “[a] duplicate is admissible to the same\nextent as the original unless a genuine question is raised about the original’s\nauthenticity or the circumstances make it unfair to admit a duplicate.” 37\n Mewase’s original passport went missing during his extradition. And\nMewase acknowledges that it wasn’t the Government’s fault. Even so, he still\nclaims that relying on the duplicate isn’t fair. And yet he doesn’t explain why.\nSo the district court didn’t abuse its discretion in admitting the duplicate.\nC. The district court properly removed and replaced Juror 20.\n Ayelotan and Mewase contend that the district court’s decision to remove\nJuror 20 violated their due process rights. We review the removal and\nreplacement of a juror for abuse of discretion. 38 And as we explained in\n\n\n\n\n 34 United States v. Jackson, 636 F.3d 687, 692 (5th Cir. 2011).\n 35 Id.\n 36 FED. R. EVID. 1002.\n 37 FED. R. EVID. 1003.\n 38 United States v. Huntress, 956 F.2d 1309, 1312 (5th Cir. 1992).\n\n 9\n\f Case: 17-60397 Document: 00514858253 Page: 10 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\nHuntress, a court may not dismiss a juror “without factual support or for a\nlegally irrelevant reason.” 39\n\n\n The Federal Rules of Criminal Procedure allow a judge to remove jurors\nwho cannot perform their duties. 40 We explained what that means long ago.\nForty-plus years ago in Smith, we held that “a juror who cannot remain awake\nduring much of the trial is unable to perform his duty.” 41 And in 2002, we\nexplained in Edwards that other good reasons for removal include a “lack of\ncandor” and an “inability or unwillingness to follow instructions.” 42\n Here, the district court identified legally relevant reasons for removing\nJuror 20. The juror slept through witness testimony; misrepresented this fact\nto the district court when asked; didn’t understand, or else didn’t follow, the\njury instructions; and didn’t deliberate.\n Ample evidence supported these legitimate reasons. Near the end of the\nfirst day of jury deliberations, the foreperson delivered two notes to the court:\n We have one person that is undecided, and we [cannot] get an\n answer from him.\n\n One, we have a juror that has admitted that he slept through some\n of the testimony; two, he doesn’t believe you can’t go to Western\n Union and pick up transaction, his opinion/own notation; three, he\n refuses to follow the judge’s instruction.\nAfter reviewing the notes, the court called in the foreperson, Juror 20, and\nevery other juror one at a time.\n When the district court asked Juror 20 about sleeping through the trial,\nhe admitted that he may have “nodded off.” But he said that if he did, “it was\nvery minimal.” Yet his fellow jurors testified otherwise. Some said that Juror\n\n\n 39 Id.\n 40 FED. R. CRIM. P. 24(c) (permitting removal of jurors who are “unable to perform or\nare disqualified from performing their duties”).\n 41 United States v. Smith, 550 F.2d 277, 285 (5th Cir. 1977).\n 42 United States v. Edwards, 303 F.3d 606, 631–32 (5th Cir. 2002).\n\n 10\n\f Case: 17-60397 Document: 00514858253 Page: 11 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\n20 admitted that he “was asleep some of the time, so [he] may have missed\nthings.” And others said he confessed that “he may not have heard everything\nhe needed to hear” since he fell asleep.\n Many jurors even said they saw him sleeping more than just a “minimal”\namount, including his neighboring juror:\n I sat next to [Juror 20], I noticed that there was quite a few times,\n a lot of times, that I would look over and notice that he was\n asleep. . . . It was more than once a day . . . . I do believe that it\n was enough to miss key information.\nAnd several other jurors believed that Juror 20 simply couldn’t follow the law.\n Juror 19, for example, testified that the jury pointed out specific\ninstructions to Juror 20, which “he refused to follow”—e.g., “considering only\nthe evidence presented” and following “the law that’s in the instructions.”\nAnother juror questioned Juror 20’s comprehension: “He spent three hours\nreading [the Court’s] instructions yesterday, and he got to Page 5. We’ve tried\nto talk to him, and he just refuses.”\n Based on this evidence, the district court removed Juror 20. But Ayelotan\nand Mewase argue that the court really removed Juror 20 because he was a\n“hold-out”; because he “clearly questioned Mr. Ayelotan’s guilt.” True, Juror 20\nresisted convicting. Yet as we noted in Edwards, even “hold-out jurors are not\nimmune from dismissal based upon just cause.” 43\n The district court had legitimate reasons to dismiss Juror 20. And there\nwas strong factual support for those legitimate reasons. Removing Juror 20\nwas not an abuse of discretion.\nD. Sentencing Challenge\n The district court sentenced Ayelotan, Raheem, and Mewase to\npractically interminable prison terms. The court calculated the total intended\n\n\n\n 43 Edwards, 303 F.3d at 634.\n 11\n\f Case: 17-60397 Document: 00514858253 Page: 12 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\nloss of their scheme: over $25 million. At a joint sentencing hearing, the court\nheard testimony from a postal inspector and two case agents from Homeland\nSecurity Investigations. They testified on the loss amount and the defendants’\nroles.\n For Ayelotan, the court imposed a 22-level increase for the intended loss.\nAnd it imposed a 4-level enhancement for his leadership role. This came to a\ntotal Guidelines offense level of 43. Given Ayelotan’s criminal history, his\nGuidelines sentence was life imprisonment. The court reduced that to the\nwithin-Guidelines statutory maximum of 95 years. 44 And it sentenced Ayelotan\nto that.\n For Raheem, the court also assigned a total offense level of 43 for the\nintended loss and his leadership role. His initial sentencing range was life\nimprisonment too. But the court again decreased it. His within-Guidelines\nstatutory maximum was 115 years. 45 And the court sentenced him to that.\n Finally, for Mewase, the court also applied the same 22-level increase for\nthe intended loss. The resulting Guidelines range was 262 to 327 months. The\ncourt reduced that to 262 to 300, the statutory maximum. The court then\nsentenced him to 25 years.\n All three defendants now challenge their sentences on various grounds.\n 1. Leadership Enhancement\n On appeal, Ayelotan and Raheem object to their leadership\nenhancements. 46 And Ayelotan says that the court should’ve given him a\nminor-role reduction.\n As we explained in Hebert, the preponderance of the evidence must show\nthat the defendant was “the organizer or leader of a criminal activity that\n\n\n 44 See U.S. SENTENCING GUIDELINES MANUAL § 5G1.2(b).\n 45 See id.\n 46 Id. § 3B1.1(a).\n\n 12\n\f Case: 17-60397 Document: 00514858253 Page: 13 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\ninvolved five or more participants or was otherwise extensive.” 47 We will\nreverse the enhancement only if the district court clearly erred. 48\n To begin with, the district court found—and the trial evidence\nsupported—that this was a major criminal undertaking. It involved far more\nthan five participants. As for leadership, the commentary to § 3B1.1 lists\nfactors for assessing a defendant’s role:\n • the exercise of decision-making authority;\n • the nature of participation in the commission of the offense;\n • the recruitment of accomplices;\n • the claimed right to a larger share of the fruits of the crime;\n • the degree of participation in planning or organizing the\n offense;\n • the nature and scope of the illegal activity;\n • and the degree of control and authority exercised over others. 49\nThe commentary also clarifies that more than one person can qualify as a\nleader of the same criminal group. 50\n Ayelotan argues that the second superseding indictment proves that his\nrole was “peripheral in substance” and “peripheral in duration.” He claims that\nthe only accusation against him was that he emailed shipping-label\ninformation.\n But the district court specifically relied on several § 3B1.1 factors in\ndetermining leadership roles. At sentencing, the court heard testimony from\ncase agent Williams. Agent Williams testified that Ayelotan was among the\n“top people within the group of indicted defendants.” Williams asserted that\n\n\n\n 47 See United States v. Hebert, 813 F.3d 551, 560 (5th Cir. 2015).\n 48 Id.\n 49 U.S. SENTENCING GUIDELINES MANUAL § 3B1.1 cmt. 4.\n 50 Id.\n\n 13\n\f Case: 17-60397 Document: 00514858253 Page: 14 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\nAyelotan was a “central hub to a number of other co-conspirators on a daily\nbasis.” Agent Williams also identified Raheem as one of four coconspirators “at\nthe top of th[e] hierarchy.”\n Williams based this on their time spent on the conspiracy, their day-to-\nday involvement, and the number of coconspirators who reported to them. The\ndistrict court relied on this testimony. And it determined that Ayelotan “was\ninvolved in almost every scam involved in the offense”; that he “participated in\nplanning or organizing it”; and that he directly controlled other conspirators.\nSimilarly, the court credited Williams’s testimony on Raheem’s leadership in\nthe organization.\n The district court did not clearly err considering the evidence before it—\nnot with Ayelotan and not with Raheem.\n 2. Eighth Amendment\n Now for the first time on appeal, Ayelotan and Raheem raise an Eighth\nAmendment argument. They assert that effective life sentences for nonviolent\ncrimes are cruel and unusual punishment. We review arguments raised for the\nfirst time on appeal for plain error. 51 Although Ayelotan acknowledges the\nplain-error standard, he never briefed anything beyond the first step of the\nplain-error test: whether an error occurred.\n Yet even if Ayelotan had sufficiently briefed the other steps of the plain-\nerror analysis, he still wouldn’t be entitled to relief. Yes, in extraordinary\ncases, term-of-years sentences can be cruel and unusual. In 1992, we held in\nMcGruder that sentences violate the Eighth Amendment when they’re “grossly\ndisproportionate” to the convicted conduct. 52\n\n\n\n\n 51 E.g., United States v. Mondragon-Santiago, 564 F.3d 357, 361 (5th Cir. 2009).\n 52 McGruder v. Puckett, 954 F.2d 313, 315 (5th Cir. 1992).\n 14\n\f Case: 17-60397 Document: 00514858253 Page: 15 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\n But as we’ve explained before, this review is narrow. In our 2016 case\nMills, we underscored that a reviewing court may not “substitute its judgment\nfor that of the legislature nor the sentencing court.” 53 And four years before\nthat, in Looney, we acknowledged that under Supreme Court precedent,\n“successful Eighth Amendment challenges to prison-term lengths will be\nrare.” 54\n Ayelotan maintains that an effective life sentence for a nonviolent,\nfinancial crime is—by definition—grossly disproportionate. Yet he cites no\ncases finding that lengthy sentences for financial crimes violate the Eighth\nAmendment. He cites only to the Supreme Court’s 2010 decision in Graham 55\nand its 1992 decision in Robinson. 56\n But in Graham, the Supreme Court limited its decision to life sentences\nfor minors. 57 And in Robinson, the Court held that a law criminalizing\nnarcotics addiction was unconstitutional. 58 The Court struck down the law\nbecause its purpose was to stigmatize addicts; not because the sentence was\ntoo long. 59 Neither decision applies here.\n Yet our decision in Mills does apply. There, we held that “the Guidelines\nare a convincing objective indicator of proportionality.” 60 And in Looney, we\nupheld effective life sentences for the nonviolent offenses of possession with\nintent to distribute methamphetamine and possession of firearms. 61\n\n\n\n\n 53 United States v. Mills, 843 F.3d 210, 218 (5th Cir. 2016) (citations omitted).\n 54 United States v. Looney, 532 F.3d 392, 396 (5th Cir. 2008).\n 55 See generally Graham v. Florida, 560 U.S. 48 (2010).\n 56 See generally Robinson v. California, 370 U.S. 660 (1992).\n 57 See Graham, 560 U.S. at 81.\n 58 Robinson, 370 U.S. at 677.\n 59 Id. at 677 & n.5.\n 60 Mills, 843 F.3d at 218.\n 61 Looney, 532 F.3d at 396.\n\n 15\n\f Case: 17-60397 Document: 00514858253 Page: 16 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\n Ayelotan’s and Raheem’s within-Guidelines sentences didn’t violate the\nEighth Amendment. The district court did not err, plainly or otherwise.\n 3. Intended Loss Calculation\n Raheem and Mewase challenge the intended loss calculation of over $25\nmillion. In 2012, we laid out the rule for calculating intended losses in Hebron:\n“The applicable loss is generally the greater of actual loss—which includes only\nreasonably foreseeable harm resulting from the fraud—and intended loss—\nwhich includes the harm intended to result from the offense.” 62 And district\ncourts need only make “a reasonable estimate of the loss” based on the\nevidence. 63\n We review these calculations for clear error. 64 In Hull, we explained that\nwe review the foreseeability of the loss for clear error too. 65 Then in Sanders,\nwe established that we review the loss calculation itself for clear error. 66 We\nwon’t overturn these factual findings “unless they are implausible in light of\nthe record as a whole.” 67\n Raheem retorts that the record doesn’t show that they “intended to inflict\na loss” of $25 million or more. First, that misstates the standard. The\nSentencing Guidelines don’t require the defendant to have intended the\nspecific loss amount. 68 Instead, the district court simply has to conclude that\nthe defendant knew or reasonably should have known that the scheme would\ncause the harm. 69\n\n\n\n 62 United States v. Hebron, 684 F.3d 559, 560 (5th Cir. 2012); see also United States v.\nFairley, 880 F.3d 198, 215 (5th Cir. 2018) (quoting Hebron).\n 63 Id. (citing U.S. SENTENCING GUIDELINES MANUAL § 2B1.1 cmt. n.3(C)).\n 64 Id.\n 65 United States v. Hull, 160 F.3d 265, 269 (5th Cir. 1998).\n 66 United States v. Sanders, 343 F.3d 511, 519 (5th Cir. 2003).\n 67 Id.\n 68 U.S. SENTENCING GUIDELINES MANUAL § 2B1.1 cmt. 3.\n 69 Id.\n\n 16\n\f Case: 17-60397 Document: 00514858253 Page: 17 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\n And the district court relied on testimony that showed this: “Mr. Raheem\nand Mr. Ayelotan were directly involved in most, if not all of [the activity used\nto calculate the loss amount], and to the extent they were not directly involved,\nit was certainly reasonably foreseeable to them as part of the jointly\nundertaken criminal activity which was part and parcel to this conspiracy.”\n Second, the record does show that the intended loss was over $25 million.\nThe district court considered the PSR’s calculations. And it heard testimony\nfrom the postal inspector and two case agents. Based on that, the court\ncalculated the loss at $52 million.\n Finally, Raheem disputes the district court’s determination that there\nwere at least 37,817 credit cards involved in the conspiracy. Rather, Raheem\nurges that “there is no information all of the alleged credit cards were real.”\nYet the district court heard specific evidence suggesting that the credit card\nnumbers corresponded to real accounts. For example, Williams testified that\nthe first six numbers on the cards—generally identifying the financial\ninstitutions—matched with real institutions; and that the stolen information\nincluded three-digit CVV codes on the back of each card.\n In any event, Raheem and his coconspirators’ intended to get their hands\non valid credit card numbers. Otherwise, their scheme could bear no fruit.\nPhony credit cards won’t even buy you Monopoly Money—let alone cash\nadvances. Even if some card numbers were fake, that wouldn’t matter. Again,\ntheir intent dictates the intended loss.\n 4. Substantive Reasonableness of Sentence\n Finally, Raheem and Mewase contend that their sentences are\nsubstantively unreasonable. But in 2009, we reiterated in Cooks that we\npresume a within-Guidelines-range sentence is reasonable. 70 And we tend to\n\n\n\n 70 United States v. Cooks, 589 F.3d 173, 186 (5th Cir. 2009) (cleaned up).\n 17\n\f Case: 17-60397 Document: 00514858253 Page: 18 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\ndefer to the sentencing court. As we noted in our 2011 decision in Scott, “the\nsentencing court is in a better position to find facts and judge their import\nunder the § 3553(a) factors.” 71\n To rebut the presumption, a defendant must show one of three things:\n(1) the court failed to consider a factor that it should’ve given significant\nweight; (2) the court gave significant weight to an irrelevant or improper factor;\nor (3) the court clearly erred in balancing sentencing factors. 72\n Raheem argues that his sentence exceeds the aim of the § 3553(a)\nsentencing factors. But his sentence was within-Guidelines. So it’s presumed\nreasonable. And here, Raheem hasn’t rebutted that presumption.\n The district court detailed its justifications and discussed the § 3553(a)\nfactors. The court noted that Raheem was “a leader or organizer” in “a broad\nand wide-reaching and extensive conspiracy involving criminal conduct that\nwent on for a number of years”; one that “involved the manipulation and taking\nadvantage of, whether financially or otherwise, a large number of victims.”\n Mewase argues that his sentence is unreasonable because of\n“unwarranted sentencing disparities” between him and some coconspirators\nwho pleaded guilty. But this doesn’t rebut the presumption of reasonableness\neither. Mewase offers no proof that he was so similarly situated to\ncoconspirators who received lesser sentences that the disparities are\n“unwarranted.” Nor does the PSR suggest that. Rather, many other\ncoconspirators played much smaller roles, accepted responsibility, or\ncooperated with the Government.\n In sum, we have consistently declined to merely reweigh the sentencing\nfactors. Yes, Raheem’s within-Guidelines sentence is severe. But the district\n\n\n 71 United States v. Scott, 654 F.3d 552, 555 (5th Cir. 2011) (internal quotation marks\nand citation omitted).\n 72 Id.\n\n 18\n\f Case: 17-60397 Document: 00514858253 Page: 19 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\ncourt weighed the appropriate factors. And its sentence isn’t substantively\nunreasonable. The district court also grounded Mewase’s sentence in an in-\ndepth consideration of the § 3553 factors. So neither sentence is substantively\nunreasonable.\n\n IV. CONCLUSION\n The district court committed no error, and we AFFIRM in all respects.\n\n\n\n\n 19\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Plaintiff-Appellee, v. Oladimeji Seun AYELOTAN; Femi Alexander Mewase; Rasaq Aderoju Raheem, Defendants-Appellants.\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-04\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 17-60397 Document: 00514858253 Page: 1 Date Filed: 03/04/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n No. 17-60397 FILED\\n March 4, 2019\\n Lyle W. Cayce\\nUNITED STATES OF AMERICA, Clerk\\n\\n Plaintiff–Appellee,\\n\\nv.\\n\\nOLADIMEJI SEUN AYELOTAN; FEMI ALEXANDER MEWASE; RASAQ\\nADEROJU RAHEEM,\\n\\n Defendants–Appellants.\\n\\n\\n Appeals from the United States District Court\\n for the Southern District of Mississippi\\n\\n\\nBefore STEWART, Chief Judge, and DENNIS and WILLETT, Circuit Judges.\\nDON R. WILLETT, Circuit Judge:\\n Three Africa-based cybercriminals—Oladimeji Ayelotan, Femi Mewase,\\nand Rasaq Raheem—masterminded a sprawling international romance scam\\nthat stole hearts, and money. Posing as bachelors (and bachelorettes) online,\\nthese Nigerian nationals kindled digital romances with scores of lovelorn\\nAmericans. The fraudsters sat at overseas computers, prowling the Internet\\nand spinning false promises of love and romance, ultimately duping their\\nunsuspecting victims into sending money to Nigeria and South Africa.\\n Many fauxmance swindlers escape scot-free, their victims, broke and\\nbrokenhearted, too embarrassed to come forward. Not this time. A wary target\\nreported her suspicions, and the scammers didn’t fare as well in court as they\\nhad online. After a 16-day trial, the jury convicted them, and the district court\\n\\f Case: 17-60397 Document: 00514858253 Page: 2 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nimposed lengthy prison sentences. This appeal alleges several errors—the\\ndistrict court’s imposition of leg restraints during trial; the admission of emails\\nand a nonoriginal passport; the dismissal of a juror during trial; and the\\nsentences handed down.\\n Each argument is meritless, and we AFFIRM.\\n\\n I. BACKGROUND\\n The transnational romance scam worked like this: Ayelotan, Mewase,\\nand Raheem—along with their coconspirators—stole personal information\\nsuch as names, Social Security numbers, credit card numbers, and bank\\naccount numbers. They then impersonated their victims—getting cash\\nadvances and transferring funds out of the victims’ accounts.\\n But they needed a safe way to transfer the fruits of their crimes. Thus\\ntheir digital dalliances. Using dating websites like “seniorpeoplemeet.com,”\\nwell-honed conversation scripts, and step-by-step guides, the conspirators\\ncultivated online relationships, then sweet-talked their “paramours” into\\nlaundering their money. Next, the conspirators would cajole their enamored\\nvictims into becoming money mules, conduits for stolen funds, even providing\\nprepaid shipping labels for the swindled cash and goods.\\n Everything was going according to plan until one prospective money\\nmule grew suspicious. She reported her experience to the police, who ran it by\\nHomeland Security Investigations (the Department of Homeland Security’s\\ninvestigation arm). Agent Todd Williams, posing over email as the target\\nvictim, helped unravel the whole scheme.\\n The district court held a 16-day trial, during which it put the three\\ndefendants in leg restraints. The court also removed and replaced one of the\\njurors.\\n The jury convicted Ayelotan and Raheem on several counts of conspiracy\\nto commit mail fraud, wire fraud, and bank fraud; conspiracy to commit\\n 2\\n\\f Case: 17-60397 Document: 00514858253 Page: 3 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nidentity theft, use of unauthorized access devices, and theft of government\\nproperty; mail fraud; and conspiracy to commit money laundering.\\n The jury acquitted Mewase of conspiracy to commit money laundering.\\nBut it convicted him of conspiracy to commit mail fraud, wire fraud, and bank\\nfraud; and conspiracy to commit identity theft, use of unauthorized access\\ndevices, and theft of government property.\\n The defendants filed post-trial motions for relief. But the district court\\nsentenced each defendant to the statutory maximum for each conviction,\\nrunning consecutively.\\n\\n II. STANDARD OF REVIEW\\n The arguments raised on appeal involve varying standards of review. We\\nreview decisions to shackle criminal defendants, admit evidence, and remove\\njurors for abuse of discretion. 1 And it is an abuse of discretion to apply an\\nerroneous view of the law or to clearly err in assessing evidence. 2 We review\\nalleged Confrontation Clause violations de novo. 3\\n As for sentencing, we review fact findings for clear error and application\\nof the Sentencing Guidelines de novo. 4 And as the Supreme Court requires, we\\nreview the substantive reasonableness of sentences for abuse of discretion. 5\\n Finally, the Supreme Court directs us to review arguments raised for the\\nfirst time on appeal for plain error. 6 In Puckett, the Court elaborated that\\nunder this standard of review, defendants must first establish an error. 7 Next,\\n\\n\\n\\n\\n 1 United States v. Ebron, 683 F.3d 105, 125 (5th Cir. 2012); United States v. Yi, 460\\nF.3d 623, 634 (5th Cir. 2006); United States v. Hope, 102 F.3d 114, 117 (5th Cir. 1996).\\n 2 United States v. Ragsdale, 426 F.3d 765, 774 (5th Cir. 2005).\\n 3 United States v. Morgan, 505 F.3d 332, 338 (5th Cir. 2007) (per curiam).\\n 4 United States v. Trujillo, 502 F.3d 353, 356 (5th Cir. 2007).\\n 5 Gall v. United States, 552 U.S. 38, 51 (2007).\\n 6 Puckett v. United States, 556 U.S. 129, 135 (2009).\\n 7 Id.\\n\\n 3\\n\\f Case: 17-60397 Document: 00514858253 Page: 4 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nthey must show that it’s clear or obvious. 8 Then, they must prove that the error\\naffected their substantial rights. 9 And if they satisfy these three prongs, we\\nmay correct the error—if it “seriously affects the fairness, integrity, or public\\nreputation of judicial proceedings.” 10\\n\\n III. DISCUSSION\\n Ayelotan, Raheem, and Mewase bring assorted challenges—none\\navailing—to their convictions and sentences:\\n • Ayelotan and Raheem—the shackling of their legs during trial\\n • Raheem and Mewase—the admission of various emails and\\n Mewase’s nonoriginal passport\\n • Ayelotan and Mewase—the dismissal of a juror\\n • All three defendants—their sentences\\nA. Shackling the defendants at trial was not an abuse of discretion.\\n Ayelotan and Raheem claim that shackling their legs violated their due\\nprocess rights. As the Supreme Court explained 14 years ago in Deck, the Fifth\\nand Fourteenth Amendments’ due process clauses require courts to have a\\n“particular reason” for shackling; “only in the presence of a special need.” 11 And\\nthe Court forbids visible restraints altogether unless “justified by an essential\\nstate interest” specific to that trial. 12\\n What reasons are enough? Some 25 years ago, in Wilkerson, we held that\\ncourts may shackle defendants when there’s a danger of harm or escape. 13 As\\nwe said then, “[w]e do not underestimate the need to restrain dangerous\\ndefendants to prevent courtroom attacks, or the need to give trial courts\\n\\n\\n 8 Id.\\n 9 Id.\\n 10 Id. (cleaned up).\\n 11 Deck v. Missouri, 544 U.S. 622, 626–28 (2005).\\n 12 Id. at 628–29 (quoting Holbrook v. Fynn, 475 U.S. 560, 568–69 (1986)).\\n 13 Wilkerson v. Whitley, 16 F.3d 64, 68 (5th Cir. 2003).\\n\\n 4\\n\\f Case: 17-60397 Document: 00514858253 Page: 5 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nlatitude in making individualized security determinations.” 14 And a few years\\nbefore that, in Ellender, we stated that district courts “may rely heavily on the\\nU.S. Marshal’s advice” in considering restraints. 15\\n Here, the court had valid reasons: Ayelotan and Raheem posed a danger.\\nAnd the facts show that. For example, at Ayelotan’s extradition hearing, he\\nand other defendants caused such a ruckus that SWAT had to be called in. The\\ndistrict court stressed this concern. And given the extradition escapades, the\\nU.S. Marshals expressed unease too—recommending that the court restrain\\nthe defendants at trial. The court had a valid, particularized reason for\\nshackling the defendants.\\n Plus, the defendants’ restraints weren’t visible. Neither Ayelotan nor\\nRaheem even claim that the restraints were visible. Neither defendant raises\\nany evidence suggesting that the jury saw the restraints. And Raheem asserts\\nmerely that it’s impossible to be sure that a juror never saw him in shackles.\\n In sum, the district court had compelling reasons for shackling the\\ndefendants, and there’s no evidence the jury even saw the restraints. And so\\nthe district court didn’t violate the defendants’ due process rights.\\nB. The emails and copy of Mewase’s passport were admissible.\\n At trial, the Government admitted oodles of emails that the defendants\\nsent to their romantic targets. These emails all came from Google and Yahoo!\\naccounts. And they revealed the defendants’ fraudulent activities. They also\\nincluded instructions for money mules to send cash and progress updates on\\ntheir various schemes. 16 The defendants filed pretrial objections to admission\\nof the emails. But the district court held that the emails and transmittal\\n\\n\\n\\n\\n 14 Id.\\n 15 United States v. Ellender, 947 F.2d 748, 760 (5th Cir. 1991).\\n 16 Id.\\n\\n 5\\n\\f Case: 17-60397 Document: 00514858253 Page: 6 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nrecords, accompanied by Google and Yahoo! records-custodian certificates,\\nwere admissible self-authenticating business records.\\n On appeal, Raheem and Mewase challenge the admission of these emails\\nand records under the Federal Rules of Evidence and the Confrontation\\nClause. Mewase also contends that admission of a duplicate copy of his\\npassport identification page violated the Best Evidence Rule. Both challenges\\nfail.\\n 1. Federal Rules of Evidence\\n The Federal Rules of Evidence ban hearsay—out-of-court statements\\nmade to prove the truth of what’s asserted. 17 But there are exceptions. Here,\\neach email represented two “statements” for purposes of the Federal Rules of\\nEvidence. First was the transmittal certificate—effectively, the email\\nprovider’s statement that one user wrote and sent a message to another user\\nat the recorded time. Second, the content of each email is also a statement. We\\ntake them in that order.\\n The Federal Rules of Evidence except business records from hearsay. 18\\nTo qualify, a records custodian with knowledge must testify unless they’re\\n“self-authenticating.” 19 Records are self-authenticating if they include a\\ncustodian certification that the records “meet[] the requirements of Rule\\n803(6)(A)–(C).” 20\\n All the email records from this conspiracy included certificates. The\\ncertificates stated that Google or Yahoo! recorded the transmittal data\\nautomatically when users send emails, as part of the regular practice of a\\n\\n\\n\\n FED. R. EVID. 801(c) (“‘Hearsay’ means a statement that: (1) the declarant does not\\n 17\\n\\nmake while testifying at the current trial or hearing; and (2) a party offers in evidence to\\nprove the truth of the matter asserted in the statement.”).\\n 18 FED. R. EVID. 803(6).\\n 19 FED. R. EVID. 803(6); FED. R. EVID. 902(11).\\n 20 FED. R. EVID. 902(11).\\n\\n 6\\n\\f Case: 17-60397 Document: 00514858253 Page: 7 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nregularly conducted business activity. This satisfies Rule 803(6)’s\\nrequirements for admission. 21 As we explained in our 1991 Wilson decision,\\ncertificates from a records custodian that “track the language of Rule 803(6)\\nnearly word for word” render the records self-authenticating. 22 Thus, the\\ndistrict court didn’t abuse its discretion by finding a valid hearsay exception\\nfor the certificates.\\n The second possible hearsay is the emails’ substantive content: the\\nmessages between the defendants and their coconspirators. But these were\\nadmissible too. The Government didn’t offer these statements to prove the\\ncontent of them. 23 Same with the e-mule messages.\\n Rather, these statements were “the operative words of [the] criminal\\naction”—what we called “paradigmatic nonhearsay” in our 1981 case Jones. 24\\nThe remaining content in the emails—updates between the coconspirators\\nabout their criminal scheme—was admissible as opposing party and\\ncoconspirator statements under Rule 801(d). 25\\n\\n\\n\\n 21 FED. R. EVID. 803(6) (“The following are not excluded by the rule against hearsay,\\nregardless of whether the declarant is available as a witness: A record of an act, event,\\ncondition, opinion, or diagnosis if: (A) the record was made at or near the time by—or from\\ninformation transmitted by—someone with knowledge; (B) the record was kept in the course\\nof a regularly conducted activity of a business, organization, occupation, or calling, whether\\nor not for profit; (C) making the record was a regular practice of that activity; (D) all these\\nconditions are shown by the testimony of the custodian or another qualified witness, or by a\\ncertification that complies with Rule 902(11) or (12) or with a statute permitting certification;\\nand (E) the opponent does not show that the source of information or the method or\\ncircumstances of preparation indicate a lack of trustworthiness.”).\\n 22 Wilson v. Zapata Off-Shore Co., 939 F.2d 260, 272 (5th Cir. 1991).\\n 23 FED. R. EVID. 801(c)(2).\\n 24 United States v. Jones, 663 F.2d 567, 571 (5th Cir. 1981).\\n 25 FED. R. EVID. 801(d)(2) (“A statement that meets the following conditions is not\\n\\nhearsay: . . . The statement is offered against an opposing party and: (A) was made by the\\nparty in an individual or representative capacity; (B) is one the party manifested that it\\nadopted or believed to be true; (C) was made by a person whom the party authorized to make\\na statement on the subject; (D) was made by the party’s agent or employee on a matter within\\nthe scope of that relationship and while it existed; or (E) was made by the party’s\\ncoconspirator during and in furtherance of the conspiracy.”).\\n 7\\n\\f Case: 17-60397 Document: 00514858253 Page: 8 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\n 2. Confrontation Clause\\n Our Confrontation Clause analysis resembles our Federal Rules of\\nEvidence analysis. And likewise, the district court didn’t misstep in admitting\\nthe emails and records.\\n In 2004, the Supreme Court held in Crawford that the Confrontation\\nClause prohibits admitting out-of-court statements as evidence against\\ndefendants in a criminal case unless they can cross-examine the declarant. 26\\nBut that prohibition applies only if the statements are “testimonial.” 27\\n And two years later in Davis, the Court explained that statements are\\n“testimonial” if their “primary purpose . . . is to establish or prove past events\\npotentially relevant to later criminal prosecution.” 28 Or as the Court explained\\nin Melendez-Diaz three years after that, business records must be “for the\\nadministration of the [business’s] affairs and not for the purpose of\\nestablishing or proving some fact at trial.” 29\\n Under this framework, Google and Yahoo!’s transmittal-data records\\naren’t testimonial. Consider our Towns decision in 2013. 30 There, we\\nconsidered a pharmacy’s prescription-purchase logs. 31 We held that those\\nweren’t testimonial. 32 Rather, the pharmacy recorded those logs “ex ante to\\ncomply with state regulatory measures, not in response to active\\nprosecution.” 33 It’s the same with Google and Yahoo! They didn’t create the\\n\\n\\n\\n\\n 26 See Crawford v. Washington, 541 U.S. 36, 51–53 (2004).\\n 27 Id.\\n 28 Davis v. Washington, 547 U.S. 813, 822 (2006); see also United States v. Duron-\\n\\nCaldera, 737 F.3d 988, 992–93 (5th Cir. 2013) (quoting Davis for that proposition).\\n 29 Melendez-Diaz v. Massachusetts, 557 U.S. 305, 324 (2009).\\n 30 United States v. Towns, 718 F.3d 404, 411 (5th Cir. 2013).\\n 31 Id.\\n 32 Id.\\n 33 Id.\\n\\n 8\\n\\f Case: 17-60397 Document: 00514858253 Page: 9 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nrecords to prove a particular fact at a particular trial—let alone this trial. The\\nrecords are admissible as far as the Confrontation Clause goes.\\n So are the coconspirator statements. Take our 2011 decision in\\nJackson. 34 In that case, we explained that—as a general matter—\\n“coconspirator statements made during the course and in furtherance of a\\nconspiracy” aren’t testimonial. 35 So the district court didn’t violate the\\ndefendants’ Confrontation Clause rights by admitting this evidence.\\n 3. Best Evidence Rule\\n Mewase also contends that the passport copy was inadmissible under the\\nBest Evidence Rule. True, the Federal Rules of Evidence require using “[a]n\\noriginal writing, recording, or photograph” as evidence of that item’s contents\\nat trial. 36 But the Rules clarify that “[a] duplicate is admissible to the same\\nextent as the original unless a genuine question is raised about the original’s\\nauthenticity or the circumstances make it unfair to admit a duplicate.” 37\\n Mewase’s original passport went missing during his extradition. And\\nMewase acknowledges that it wasn’t the Government’s fault. Even so, he still\\nclaims that relying on the duplicate isn’t fair. And yet he doesn’t explain why.\\nSo the district court didn’t abuse its discretion in admitting the duplicate.\\nC. The district court properly removed and replaced Juror 20.\\n Ayelotan and Mewase contend that the district court’s decision to remove\\nJuror 20 violated their due process rights. We review the removal and\\nreplacement of a juror for abuse of discretion. 38 And as we explained in\\n\\n\\n\\n\\n 34 United States v. Jackson, 636 F.3d 687, 692 (5th Cir. 2011).\\n 35 Id.\\n 36 FED. R. EVID. 1002.\\n 37 FED. R. EVID. 1003.\\n 38 United States v. Huntress, 956 F.2d 1309, 1312 (5th Cir. 1992).\\n\\n 9\\n\\f Case: 17-60397 Document: 00514858253 Page: 10 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nHuntress, a court may not dismiss a juror “without factual support or for a\\nlegally irrelevant reason.” 39\\n\\n\\n The Federal Rules of Criminal Procedure allow a judge to remove jurors\\nwho cannot perform their duties. 40 We explained what that means long ago.\\nForty-plus years ago in Smith, we held that “a juror who cannot remain awake\\nduring much of the trial is unable to perform his duty.” 41 And in 2002, we\\nexplained in Edwards that other good reasons for removal include a “lack of\\ncandor” and an “inability or unwillingness to follow instructions.” 42\\n Here, the district court identified legally relevant reasons for removing\\nJuror 20. The juror slept through witness testimony; misrepresented this fact\\nto the district court when asked; didn’t understand, or else didn’t follow, the\\njury instructions; and didn’t deliberate.\\n Ample evidence supported these legitimate reasons. Near the end of the\\nfirst day of jury deliberations, the foreperson delivered two notes to the court:\\n We have one person that is undecided, and we [cannot] get an\\n answer from him.\\n\\n One, we have a juror that has admitted that he slept through some\\n of the testimony; two, he doesn’t believe you can’t go to Western\\n Union and pick up transaction, his opinion/own notation; three, he\\n refuses to follow the judge’s instruction.\\nAfter reviewing the notes, the court called in the foreperson, Juror 20, and\\nevery other juror one at a time.\\n When the district court asked Juror 20 about sleeping through the trial,\\nhe admitted that he may have “nodded off.” But he said that if he did, “it was\\nvery minimal.” Yet his fellow jurors testified otherwise. Some said that Juror\\n\\n\\n 39 Id.\\n 40 FED. R. CRIM. P. 24(c) (permitting removal of jurors who are “unable to perform or\\nare disqualified from performing their duties”).\\n 41 United States v. Smith, 550 F.2d 277, 285 (5th Cir. 1977).\\n 42 United States v. Edwards, 303 F.3d 606, 631–32 (5th Cir. 2002).\\n\\n 10\\n\\f Case: 17-60397 Document: 00514858253 Page: 11 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\n20 admitted that he “was asleep some of the time, so [he] may have missed\\nthings.” And others said he confessed that “he may not have heard everything\\nhe needed to hear” since he fell asleep.\\n Many jurors even said they saw him sleeping more than just a “minimal”\\namount, including his neighboring juror:\\n I sat next to [Juror 20], I noticed that there was quite a few times,\\n a lot of times, that I would look over and notice that he was\\n asleep. . . . It was more than once a day . . . . I do believe that it\\n was enough to miss key information.\\nAnd several other jurors believed that Juror 20 simply couldn’t follow the law.\\n Juror 19, for example, testified that the jury pointed out specific\\ninstructions to Juror 20, which “he refused to follow”—e.g., “considering only\\nthe evidence presented” and following “the law that’s in the instructions.”\\nAnother juror questioned Juror 20’s comprehension: “He spent three hours\\nreading [the Court’s] instructions yesterday, and he got to Page 5. We’ve tried\\nto talk to him, and he just refuses.”\\n Based on this evidence, the district court removed Juror 20. But Ayelotan\\nand Mewase argue that the court really removed Juror 20 because he was a\\n“hold-out”; because he “clearly questioned Mr. Ayelotan’s guilt.” True, Juror 20\\nresisted convicting. Yet as we noted in Edwards, even “hold-out jurors are not\\nimmune from dismissal based upon just cause.” 43\\n The district court had legitimate reasons to dismiss Juror 20. And there\\nwas strong factual support for those legitimate reasons. Removing Juror 20\\nwas not an abuse of discretion.\\nD. Sentencing Challenge\\n The district court sentenced Ayelotan, Raheem, and Mewase to\\npractically interminable prison terms. The court calculated the total intended\\n\\n\\n\\n 43 Edwards, 303 F.3d at 634.\\n 11\\n\\f Case: 17-60397 Document: 00514858253 Page: 12 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nloss of their scheme: over $25 million. At a joint sentencing hearing, the court\\nheard testimony from a postal inspector and two case agents from Homeland\\nSecurity Investigations. They testified on the loss amount and the defendants’\\nroles.\\n For Ayelotan, the court imposed a 22-level increase for the intended loss.\\nAnd it imposed a 4-level enhancement for his leadership role. This came to a\\ntotal Guidelines offense level of 43. Given Ayelotan’s criminal history, his\\nGuidelines sentence was life imprisonment. The court reduced that to the\\nwithin-Guidelines statutory maximum of 95 years. 44 And it sentenced Ayelotan\\nto that.\\n For Raheem, the court also assigned a total offense level of 43 for the\\nintended loss and his leadership role. His initial sentencing range was life\\nimprisonment too. But the court again decreased it. His within-Guidelines\\nstatutory maximum was 115 years. 45 And the court sentenced him to that.\\n Finally, for Mewase, the court also applied the same 22-level increase for\\nthe intended loss. The resulting Guidelines range was 262 to 327 months. The\\ncourt reduced that to 262 to 300, the statutory maximum. The court then\\nsentenced him to 25 years.\\n All three defendants now challenge their sentences on various grounds.\\n 1. Leadership Enhancement\\n On appeal, Ayelotan and Raheem object to their leadership\\nenhancements. 46 And Ayelotan says that the court should’ve given him a\\nminor-role reduction.\\n As we explained in Hebert, the preponderance of the evidence must show\\nthat the defendant was “the organizer or leader of a criminal activity that\\n\\n\\n 44 See U.S. SENTENCING GUIDELINES MANUAL § 5G1.2(b).\\n 45 See id.\\n 46 Id. § 3B1.1(a).\\n\\n 12\\n\\f Case: 17-60397 Document: 00514858253 Page: 13 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\ninvolved five or more participants or was otherwise extensive.” 47 We will\\nreverse the enhancement only if the district court clearly erred. 48\\n To begin with, the district court found—and the trial evidence\\nsupported—that this was a major criminal undertaking. It involved far more\\nthan five participants. As for leadership, the commentary to § 3B1.1 lists\\nfactors for assessing a defendant’s role:\\n • the exercise of decision-making authority;\\n • the nature of participation in the commission of the offense;\\n • the recruitment of accomplices;\\n • the claimed right to a larger share of the fruits of the crime;\\n • the degree of participation in planning or organizing the\\n offense;\\n • the nature and scope of the illegal activity;\\n • and the degree of control and authority exercised over others. 49\\nThe commentary also clarifies that more than one person can qualify as a\\nleader of the same criminal group. 50\\n Ayelotan argues that the second superseding indictment proves that his\\nrole was “peripheral in substance” and “peripheral in duration.” He claims that\\nthe only accusation against him was that he emailed shipping-label\\ninformation.\\n But the district court specifically relied on several § 3B1.1 factors in\\ndetermining leadership roles. At sentencing, the court heard testimony from\\ncase agent Williams. Agent Williams testified that Ayelotan was among the\\n“top people within the group of indicted defendants.” Williams asserted that\\n\\n\\n\\n 47 See United States v. Hebert, 813 F.3d 551, 560 (5th Cir. 2015).\\n 48 Id.\\n 49 U.S. SENTENCING GUIDELINES MANUAL § 3B1.1 cmt. 4.\\n 50 Id.\\n\\n 13\\n\\f Case: 17-60397 Document: 00514858253 Page: 14 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nAyelotan was a “central hub to a number of other co-conspirators on a daily\\nbasis.” Agent Williams also identified Raheem as one of four coconspirators “at\\nthe top of th[e] hierarchy.”\\n Williams based this on their time spent on the conspiracy, their day-to-\\nday involvement, and the number of coconspirators who reported to them. The\\ndistrict court relied on this testimony. And it determined that Ayelotan “was\\ninvolved in almost every scam involved in the offense”; that he “participated in\\nplanning or organizing it”; and that he directly controlled other conspirators.\\nSimilarly, the court credited Williams’s testimony on Raheem’s leadership in\\nthe organization.\\n The district court did not clearly err considering the evidence before it—\\nnot with Ayelotan and not with Raheem.\\n 2. Eighth Amendment\\n Now for the first time on appeal, Ayelotan and Raheem raise an Eighth\\nAmendment argument. They assert that effective life sentences for nonviolent\\ncrimes are cruel and unusual punishment. We review arguments raised for the\\nfirst time on appeal for plain error. 51 Although Ayelotan acknowledges the\\nplain-error standard, he never briefed anything beyond the first step of the\\nplain-error test: whether an error occurred.\\n Yet even if Ayelotan had sufficiently briefed the other steps of the plain-\\nerror analysis, he still wouldn’t be entitled to relief. Yes, in extraordinary\\ncases, term-of-years sentences can be cruel and unusual. In 1992, we held in\\nMcGruder that sentences violate the Eighth Amendment when they’re “grossly\\ndisproportionate” to the convicted conduct. 52\\n\\n\\n\\n\\n 51 E.g., United States v. Mondragon-Santiago, 564 F.3d 357, 361 (5th Cir. 2009).\\n 52 McGruder v. Puckett, 954 F.2d 313, 315 (5th Cir. 1992).\\n 14\\n\\f Case: 17-60397 Document: 00514858253 Page: 15 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\n But as we’ve explained before, this review is narrow. In our 2016 case\\nMills, we underscored that a reviewing court may not “substitute its judgment\\nfor that of the legislature nor the sentencing court.” 53 And four years before\\nthat, in Looney, we acknowledged that under Supreme Court precedent,\\n“successful Eighth Amendment challenges to prison-term lengths will be\\nrare.” 54\\n Ayelotan maintains that an effective life sentence for a nonviolent,\\nfinancial crime is—by definition—grossly disproportionate. Yet he cites no\\ncases finding that lengthy sentences for financial crimes violate the Eighth\\nAmendment. He cites only to the Supreme Court’s 2010 decision in Graham 55\\nand its 1992 decision in Robinson. 56\\n But in Graham, the Supreme Court limited its decision to life sentences\\nfor minors. 57 And in Robinson, the Court held that a law criminalizing\\nnarcotics addiction was unconstitutional. 58 The Court struck down the law\\nbecause its purpose was to stigmatize addicts; not because the sentence was\\ntoo long. 59 Neither decision applies here.\\n Yet our decision in Mills does apply. There, we held that “the Guidelines\\nare a convincing objective indicator of proportionality.” 60 And in Looney, we\\nupheld effective life sentences for the nonviolent offenses of possession with\\nintent to distribute methamphetamine and possession of firearms. 61\\n\\n\\n\\n\\n 53 United States v. Mills, 843 F.3d 210, 218 (5th Cir. 2016) (citations omitted).\\n 54 United States v. Looney, 532 F.3d 392, 396 (5th Cir. 2008).\\n 55 See generally Graham v. Florida, 560 U.S. 48 (2010).\\n 56 See generally Robinson v. California, 370 U.S. 660 (1992).\\n 57 See Graham, 560 U.S. at 81.\\n 58 Robinson, 370 U.S. at 677.\\n 59 Id. at 677 & n.5.\\n 60 Mills, 843 F.3d at 218.\\n 61 Looney, 532 F.3d at 396.\\n\\n 15\\n\\f Case: 17-60397 Document: 00514858253 Page: 16 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\n Ayelotan’s and Raheem’s within-Guidelines sentences didn’t violate the\\nEighth Amendment. The district court did not err, plainly or otherwise.\\n 3. Intended Loss Calculation\\n Raheem and Mewase challenge the intended loss calculation of over $25\\nmillion. In 2012, we laid out the rule for calculating intended losses in Hebron:\\n“The applicable loss is generally the greater of actual loss—which includes only\\nreasonably foreseeable harm resulting from the fraud—and intended loss—\\nwhich includes the harm intended to result from the offense.” 62 And district\\ncourts need only make “a reasonable estimate of the loss” based on the\\nevidence. 63\\n We review these calculations for clear error. 64 In Hull, we explained that\\nwe review the foreseeability of the loss for clear error too. 65 Then in Sanders,\\nwe established that we review the loss calculation itself for clear error. 66 We\\nwon’t overturn these factual findings “unless they are implausible in light of\\nthe record as a whole.” 67\\n Raheem retorts that the record doesn’t show that they “intended to inflict\\na loss” of $25 million or more. First, that misstates the standard. The\\nSentencing Guidelines don’t require the defendant to have intended the\\nspecific loss amount. 68 Instead, the district court simply has to conclude that\\nthe defendant knew or reasonably should have known that the scheme would\\ncause the harm. 69\\n\\n\\n\\n 62 United States v. Hebron, 684 F.3d 559, 560 (5th Cir. 2012); see also United States v.\\nFairley, 880 F.3d 198, 215 (5th Cir. 2018) (quoting Hebron).\\n 63 Id. (citing U.S. SENTENCING GUIDELINES MANUAL § 2B1.1 cmt. n.3(C)).\\n 64 Id.\\n 65 United States v. Hull, 160 F.3d 265, 269 (5th Cir. 1998).\\n 66 United States v. Sanders, 343 F.3d 511, 519 (5th Cir. 2003).\\n 67 Id.\\n 68 U.S. SENTENCING GUIDELINES MANUAL § 2B1.1 cmt. 3.\\n 69 Id.\\n\\n 16\\n\\f Case: 17-60397 Document: 00514858253 Page: 17 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\n And the district court relied on testimony that showed this: “Mr. Raheem\\nand Mr. Ayelotan were directly involved in most, if not all of [the activity used\\nto calculate the loss amount], and to the extent they were not directly involved,\\nit was certainly reasonably foreseeable to them as part of the jointly\\nundertaken criminal activity which was part and parcel to this conspiracy.”\\n Second, the record does show that the intended loss was over $25 million.\\nThe district court considered the PSR’s calculations. And it heard testimony\\nfrom the postal inspector and two case agents. Based on that, the court\\ncalculated the loss at $52 million.\\n Finally, Raheem disputes the district court’s determination that there\\nwere at least 37,817 credit cards involved in the conspiracy. Rather, Raheem\\nurges that “there is no information all of the alleged credit cards were real.”\\nYet the district court heard specific evidence suggesting that the credit card\\nnumbers corresponded to real accounts. For example, Williams testified that\\nthe first six numbers on the cards—generally identifying the financial\\ninstitutions—matched with real institutions; and that the stolen information\\nincluded three-digit CVV codes on the back of each card.\\n In any event, Raheem and his coconspirators’ intended to get their hands\\non valid credit card numbers. Otherwise, their scheme could bear no fruit.\\nPhony credit cards won’t even buy you Monopoly Money—let alone cash\\nadvances. Even if some card numbers were fake, that wouldn’t matter. Again,\\ntheir intent dictates the intended loss.\\n 4. Substantive Reasonableness of Sentence\\n Finally, Raheem and Mewase contend that their sentences are\\nsubstantively unreasonable. But in 2009, we reiterated in Cooks that we\\npresume a within-Guidelines-range sentence is reasonable. 70 And we tend to\\n\\n\\n\\n 70 United States v. Cooks, 589 F.3d 173, 186 (5th Cir. 2009) (cleaned up).\\n 17\\n\\f Case: 17-60397 Document: 00514858253 Page: 18 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\ndefer to the sentencing court. As we noted in our 2011 decision in Scott, “the\\nsentencing court is in a better position to find facts and judge their import\\nunder the § 3553(a) factors.” 71\\n To rebut the presumption, a defendant must show one of three things:\\n(1) the court failed to consider a factor that it should’ve given significant\\nweight; (2) the court gave significant weight to an irrelevant or improper factor;\\nor (3) the court clearly erred in balancing sentencing factors. 72\\n Raheem argues that his sentence exceeds the aim of the § 3553(a)\\nsentencing factors. But his sentence was within-Guidelines. So it’s presumed\\nreasonable. And here, Raheem hasn’t rebutted that presumption.\\n The district court detailed its justifications and discussed the § 3553(a)\\nfactors. The court noted that Raheem was “a leader or organizer” in “a broad\\nand wide-reaching and extensive conspiracy involving criminal conduct that\\nwent on for a number of years”; one that “involved the manipulation and taking\\nadvantage of, whether financially or otherwise, a large number of victims.”\\n Mewase argues that his sentence is unreasonable because of\\n“unwarranted sentencing disparities” between him and some coconspirators\\nwho pleaded guilty. But this doesn’t rebut the presumption of reasonableness\\neither. Mewase offers no proof that he was so similarly situated to\\ncoconspirators who received lesser sentences that the disparities are\\n“unwarranted.” Nor does the PSR suggest that. Rather, many other\\ncoconspirators played much smaller roles, accepted responsibility, or\\ncooperated with the Government.\\n In sum, we have consistently declined to merely reweigh the sentencing\\nfactors. Yes, Raheem’s within-Guidelines sentence is severe. But the district\\n\\n\\n 71 United States v. Scott, 654 F.3d 552, 555 (5th Cir. 2011) (internal quotation marks\\nand citation omitted).\\n 72 Id.\\n\\n 18\\n\\f Case: 17-60397 Document: 00514858253 Page: 19 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\ncourt weighed the appropriate factors. And its sentence isn’t substantively\\nunreasonable. The district court also grounded Mewase’s sentence in an in-\\ndepth consideration of the § 3553 factors. So neither sentence is substantively\\nunreasonable.\\n\\n IV. CONCLUSION\\n The district court committed no error, and we AFFIRM in all respects.\\n\\n\\n\\n\\n 19\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1074,"cells":{"id":{"kind":"number","value":4596349,"string":"4,596,349"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"United States v. Oladimeji Ayelotan"},"decision_date":{"kind":"string","value":"2019-03-04"},"docket_number":{"kind":"string","value":"17-60397"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before STEWART, Chief Judge, and DENNIS and WILLETT, Circuit Judges.\", \"parties\": \"\", \"opinions\": [{\"author\": \"DON R. WILLETT, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 17-60397 Document: 00514859557 Page: 1 Date Filed: 03/04/2019\\n\\n\\n\\n\\n REVISED March 4, 2019\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n No. 17-60397 March 4, 2019\\n Lyle W. Cayce\\nUNITED STATES OF AMERICA, Clerk\\n\\n\\n Plaintiff–Appellee,\\n\\nv.\\n\\nOLADIMEJI SEUN AYELOTAN; FEMI ALEXANDER MEWASE; RASAQ\\nADEROJU RAHEEM,\\n\\n Defendants–Appellants.\\n\\n\\n Appeals from the United States District Court\\n for the Southern District of Mississippi\\n\\n\\nBefore STEWART, Chief Judge, and DENNIS and WILLETT, Circuit Judges.\\nDON R. WILLETT, Circuit Judge:\\n Three Africa-based cybercriminals—Oladimeji Ayelotan, Femi Mewase,\\nand Rasaq Raheem—masterminded a sprawling international romance scam\\nthat stole hearts, and money. Posing as bachelors (and bachelorettes) online,\\nthese Nigerian nationals kindled digital romances with scores of lovelorn\\nAmericans. The fraudsters sat at overseas computers, prowling the Internet\\nand spinning false promises of love and romance, ultimately duping their\\nunsuspecting victims into sending money to Nigeria and South Africa.\\n Many fauxmance swindlers escape scot-free, their victims, broke and\\nbrokenhearted, too embarrassed to come forward. Not this time. A wary target\\n\\f Case: 17-60397 Document: 00514859557 Page: 2 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nreported her suspicions, and the scammers didn’t fare as well in court as they\\nhad online. After a 16-day trial, the jury convicted them, and the district court\\nimposed lengthy prison sentences. This appeal alleges several errors—the\\ndistrict court’s imposition of leg restraints during trial; the admission of emails\\nand a nonoriginal passport; the dismissal of a juror during trial; and the\\nsentences handed down.\\n Each argument is meritless, and we AFFIRM.\\n\\n I. BACKGROUND\\n The transnational romance scam worked like this: Ayelotan, Mewase,\\nand Raheem—along with their coconspirators—stole personal information\\nsuch as names, Social Security numbers, credit card numbers, and bank\\naccount numbers. They then impersonated their victims—getting cash\\nadvances and transferring funds out of the victims’ accounts.\\n But they needed a safe way to transfer the fruits of their crimes. Thus\\ntheir digital dalliances. Using dating websites like “seniorpeoplemeet.com,”\\nwell-honed conversation scripts, and step-by-step guides, the conspirators\\ncultivated online relationships, then sweet-talked their “paramours” into\\nlaundering their money. Next, the conspirators would cajole their enamored\\nvictims into becoming money mules, conduits for stolen funds, even providing\\nprepaid shipping labels for the swindled cash and goods.\\n Everything was going according to plan until one prospective money\\nmule grew suspicious. She reported her experience to the police, who ran it by\\nHomeland Security Investigations (the Department of Homeland Security’s\\ninvestigation arm). Agent Todd Williams, posing over email as the target\\nvictim, helped unravel the whole scheme.\\n The district court held a 16-day trial, during which it put the three\\ndefendants in leg restraints. The court also removed and replaced one of the\\njurors.\\n 2\\n\\f Case: 17-60397 Document: 00514859557 Page: 3 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\n The jury convicted Ayelotan and Raheem on several counts of conspiracy\\nto commit mail fraud, wire fraud, and bank fraud; conspiracy to commit\\nidentity theft, use of unauthorized access devices, and theft of government\\nproperty; mail fraud; and conspiracy to commit money laundering.\\n The jury acquitted Mewase of conspiracy to commit money laundering.\\nBut it convicted him of conspiracy to commit mail fraud, wire fraud, and bank\\nfraud; and conspiracy to commit identity theft, use of unauthorized access\\ndevices, and theft of government property.\\n The defendants filed post-trial motions for relief. But the district court\\nsentenced each defendant to the statutory maximum for each conviction,\\nrunning consecutively.\\n\\n II. STANDARD OF REVIEW\\n The arguments raised on appeal involve varying standards of review. We\\nreview decisions to shackle criminal defendants, admit evidence, and remove\\njurors for abuse of discretion. 1 And it is an abuse of discretion to apply an\\nerroneous view of the law or to clearly err in assessing evidence. 2 We review\\nalleged Confrontation Clause violations de novo. 3\\n As for sentencing, we review fact findings for clear error and application\\nof the Sentencing Guidelines de novo. 4 And as the Supreme Court requires, we\\nreview the substantive reasonableness of sentences for abuse of discretion. 5\\n Finally, the Supreme Court directs us to review arguments raised for the\\nfirst time on appeal for plain error. 6 In Puckett, the Court elaborated that\\n\\n\\n\\n 1 United States v. Ebron, 683 F.3d 105, 125 (5th Cir. 2012); United States v. Yi, 460\\nF.3d 623, 634 (5th Cir. 2006); United States v. Hope, 102 F.3d 114, 117 (5th Cir. 1996).\\n 2 United States v. Ragsdale, 426 F.3d 765, 774 (5th Cir. 2005).\\n 3 United States v. Morgan, 505 F.3d 332, 338 (5th Cir. 2007) (per curiam).\\n 4 United States v. Trujillo, 502 F.3d 353, 356 (5th Cir. 2007).\\n 5 Gall v. United States, 552 U.S. 38, 51 (2007).\\n 6 Puckett v. United States, 556 U.S. 129, 135 (2009).\\n\\n 3\\n\\f Case: 17-60397 Document: 00514859557 Page: 4 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nunder this standard of review, defendants must first establish an error. 7 Next,\\nthey must show that it’s clear or obvious. 8 Then, they must prove that the error\\naffected their substantial rights. 9 And if they satisfy these three prongs, we\\nmay correct the error—if it “seriously affects the fairness, integrity, or public\\nreputation of judicial proceedings.” 10\\n\\n III. DISCUSSION\\n Ayelotan, Raheem, and Mewase bring assorted challenges—none\\navailing—to their convictions and sentences:\\n • Ayelotan and Raheem—the shackling of their legs during trial\\n • Raheem and Mewase—the admission of various emails and\\n Mewase’s nonoriginal passport\\n • Ayelotan and Mewase—the dismissal of a juror\\n • All three defendants—their sentences\\nA. Shackling the defendants at trial was not an abuse of discretion.\\n Ayelotan and Raheem claim that shackling their legs violated their due\\nprocess rights. As the Supreme Court explained 14 years ago in Deck, the Fifth\\nand Fourteenth Amendments’ due process clauses require courts to have a\\n“particular reason” for shackling; “only in the presence of a special need.” 11 And\\nthe Court forbids visible restraints altogether unless “justified by an essential\\nstate interest” specific to that trial. 12\\n What reasons are enough? Some 25 years ago, in Wilkerson, we held that\\ncourts may shackle defendants when there’s a danger of harm or escape. 13 As\\n\\n\\n\\n 7 Id.\\n 8 Id.\\n 9 Id.\\n 10 Id. (cleaned up).\\n 11 Deck v. Missouri, 544 U.S. 622, 626–28 (2005).\\n 12 Id. at 628–29 (quoting Holbrook v. Fynn, 475 U.S. 560, 568–69 (1986)).\\n 13 Wilkerson v. Whitley, 16 F.3d 64, 68 (5th Cir. 2003).\\n\\n 4\\n\\f Case: 17-60397 Document: 00514859557 Page: 5 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nwe said then, “[w]e do not underestimate the need to restrain dangerous\\ndefendants to prevent courtroom attacks, or the need to give trial courts\\nlatitude in making individualized security determinations.” 14 And a few years\\nbefore that, in Ellender, we stated that district courts “may rely heavily on the\\nU.S. Marshal’s advice” in considering restraints. 15\\n Here, the court had valid reasons: Ayelotan and Raheem posed a danger.\\nAnd the facts show that. For example, at Ayelotan’s extradition hearing, he\\nand other defendants caused such a ruckus that SWAT had to be called in. The\\ndistrict court stressed this concern. And given the extradition escapades, the\\nU.S. Marshals expressed unease too—recommending that the court restrain\\nthe defendants at trial. The court had a valid, particularized reason for\\nshackling the defendants.\\n Plus, the defendants’ restraints weren’t visible. Neither Ayelotan nor\\nRaheem even claim that the restraints were visible. Neither defendant raises\\nany evidence suggesting that the jury saw the restraints. And Raheem asserts\\nmerely that it’s impossible to be sure that a juror never saw him in shackles.\\n In sum, the district court had compelling reasons for shackling the\\ndefendants, and there’s no evidence the jury even saw the restraints. And so\\nthe district court didn’t violate the defendants’ due process rights.\\nB. The emails and copy of Mewase’s passport were admissible.\\n At trial, the Government admitted oodles of emails that the defendants\\nsent to their romantic targets. These emails all came from Google and Yahoo!\\naccounts. And they revealed the defendants’ fraudulent activities. They also\\nincluded instructions for money mules to send cash and progress updates on\\ntheir various schemes. 16 The defendants filed pretrial objections to admission\\n\\n\\n 14 Id.\\n 15 United States v. Ellender, 947 F.2d 748, 760 (5th Cir. 1991).\\n 16 Id.\\n\\n 5\\n\\f Case: 17-60397 Document: 00514859557 Page: 6 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nof the emails. But the district court held that the emails and transmittal\\nrecords, accompanied by Google and Yahoo! records-custodian certificates,\\nwere admissible self-authenticating business records.\\n On appeal, Raheem and Mewase challenge the admission of these emails\\nand records under the Federal Rules of Evidence and the Confrontation\\nClause. Mewase also contends that admission of a duplicate copy of his\\npassport identification page violated the Best Evidence Rule. Both challenges\\nfail.\\n 1. Federal Rules of Evidence\\n The Federal Rules of Evidence ban hearsay—out-of-court statements\\nmade to prove the truth of what’s asserted. 17 But there are exceptions. Here,\\neach email represented two “statements” for purposes of the Federal Rules of\\nEvidence. First was the transmittal certificate—effectively, the email\\nprovider’s statement that one user wrote and sent a message to another user\\nat the recorded time. Second, the content of each email is also a statement. We\\ntake them in that order.\\n The Federal Rules of Evidence except business records from hearsay. 18\\nTo qualify, a records custodian with knowledge must testify unless they’re\\n“self-authenticating.” 19 Records are self-authenticating if they include a\\ncustodian certification that the records “meet[] the requirements of Rule\\n803(6)(A)–(C).” 20\\n All the email records from this conspiracy included certificates. The\\ncertificates stated that Google or Yahoo! recorded the transmittal data\\n\\n\\n\\n FED. R. EVID. 801(c) (“‘Hearsay’ means a statement that: (1) the declarant does not\\n 17\\n\\nmake while testifying at the current trial or hearing; and (2) a party offers in evidence to\\nprove the truth of the matter asserted in the statement.”).\\n 18 FED. R. EVID. 803(6).\\n 19 FED. R. EVID. 803(6); FED. R. EVID. 902(11).\\n 20 FED. R. EVID. 902(11).\\n\\n 6\\n\\f Case: 17-60397 Document: 00514859557 Page: 7 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nautomatically when users send emails, as part of the regular practice of a\\nregularly conducted business activity. This satisfies Rule 803(6)’s\\nrequirements for admission. 21 As we explained in our 1991 Wilson decision,\\ncertificates from a records custodian that “track the language of Rule 803(6)\\nnearly word for word” render the records self-authenticating. 22 Thus, the\\ndistrict court didn’t abuse its discretion by finding a valid hearsay exception\\nfor the certificates.\\n The second possible hearsay is the emails’ substantive content: the\\nmessages between the defendants and their coconspirators. But these were\\nadmissible too. The Government didn’t offer these statements to prove the\\ncontent of them. 23 Same with the e-mule messages.\\n Rather, these statements were “the operative words of [the] criminal\\naction”—what we called “paradigmatic nonhearsay” in our 1981 case Jones. 24\\nThe remaining content in the emails—updates between the coconspirators\\nabout their criminal scheme—was admissible as opposing party and\\ncoconspirator statements under Rule 801(d). 25\\n\\n\\n\\n 21 FED. R. EVID. 803(6) (“The following are not excluded by the rule against hearsay,\\nregardless of whether the declarant is available as a witness: A record of an act, event,\\ncondition, opinion, or diagnosis if: (A) the record was made at or near the time by—or from\\ninformation transmitted by—someone with knowledge; (B) the record was kept in the course\\nof a regularly conducted activity of a business, organization, occupation, or calling, whether\\nor not for profit; (C) making the record was a regular practice of that activity; (D) all these\\nconditions are shown by the testimony of the custodian or another qualified witness, or by a\\ncertification that complies with Rule 902(11) or (12) or with a statute permitting certification;\\nand (E) the opponent does not show that the source of information or the method or\\ncircumstances of preparation indicate a lack of trustworthiness.”).\\n 22 Wilson v. Zapata Off-Shore Co., 939 F.2d 260, 272 (5th Cir. 1991).\\n 23 FED. R. EVID. 801(c)(2).\\n 24 United States v. Jones, 663 F.2d 567, 571 (5th Cir. 1981).\\n 25 FED. R. EVID. 801(d)(2) (“A statement that meets the following conditions is not\\n\\nhearsay: . . . The statement is offered against an opposing party and: (A) was made by the\\nparty in an individual or representative capacity; (B) is one the party manifested that it\\nadopted or believed to be true; (C) was made by a person whom the party authorized to make\\na statement on the subject; (D) was made by the party’s agent or employee on a matter within\\n 7\\n\\f Case: 17-60397 Document: 00514859557 Page: 8 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\n 2. Confrontation Clause\\n Our Confrontation Clause analysis resembles our Federal Rules of\\nEvidence analysis. And likewise, the district court didn’t misstep in admitting\\nthe emails and records.\\n In 2004, the Supreme Court held in Crawford that the Confrontation\\nClause prohibits admitting out-of-court statements as evidence against\\ndefendants in a criminal case unless they can cross-examine the declarant. 26\\nBut that prohibition applies only if the statements are “testimonial.” 27\\n And two years later in Davis, the Court explained that statements are\\n“testimonial” if their “primary purpose . . . is to establish or prove past events\\npotentially relevant to later criminal prosecution.” 28 Or as the Court explained\\nin Melendez-Diaz three years after that, business records must be “for the\\nadministration of the [business’s] affairs and not for the purpose of\\nestablishing or proving some fact at trial.” 29\\n Under this framework, Google and Yahoo!’s transmittal-data records\\naren’t testimonial. Consider our Towns decision in 2013. 30 There, we\\nconsidered a pharmacy’s prescription-purchase logs. 31 We held that those\\nweren’t testimonial. 32 Rather, the pharmacy recorded those logs “ex ante to\\ncomply with state regulatory measures, not in response to active\\nprosecution.” 33 It’s the same with Google and Yahoo! They didn’t create the\\n\\n\\n\\nthe scope of that relationship and while it existed; or (E) was made by the party’s\\ncoconspirator during and in furtherance of the conspiracy.”).\\n 26 See Crawford v. Washington, 541 U.S. 36, 51–53 (2004).\\n 27 Id.\\n 28 Davis v. Washington, 547 U.S. 813, 822 (2006); see also United States v. Duron-\\n\\nCaldera, 737 F.3d 988, 992–93 (5th Cir. 2013) (quoting Davis for that proposition).\\n 29 Melendez-Diaz v. Massachusetts, 557 U.S. 305, 324 (2009).\\n 30 United States v. Towns, 718 F.3d 404, 411 (5th Cir. 2013).\\n 31 Id.\\n 32 Id.\\n 33 Id.\\n\\n 8\\n\\f Case: 17-60397 Document: 00514859557 Page: 9 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nrecords to prove a particular fact at a particular trial—let alone this trial. The\\nrecords are admissible as far as the Confrontation Clause goes.\\n So are the coconspirator statements. Take our 2011 decision in\\nJackson. 34 In that case, we explained that—as a general matter—\\n“coconspirator statements made during the course and in furtherance of a\\nconspiracy” aren’t testimonial. 35 So the district court didn’t violate the\\ndefendants’ Confrontation Clause rights by admitting this evidence.\\n 3. Best Evidence Rule\\n Mewase also contends that the passport copy was inadmissible under the\\nBest Evidence Rule. True, the Federal Rules of Evidence require using “[a]n\\noriginal writing, recording, or photograph” as evidence of that item’s contents\\nat trial. 36 But the Rules clarify that “[a] duplicate is admissible to the same\\nextent as the original unless a genuine question is raised about the original’s\\nauthenticity or the circumstances make it unfair to admit a duplicate.” 37\\n Mewase’s original passport went missing during his extradition. And\\nMewase acknowledges that it wasn’t the Government’s fault. Even so, he still\\nclaims that relying on the duplicate isn’t fair. And yet he doesn’t explain why.\\nSo the district court didn’t abuse its discretion in admitting the duplicate.\\nC. The district court properly removed and replaced Juror 20.\\n Ayelotan and Mewase contend that the district court’s decision to remove\\nJuror 20 violated their due process rights. We review the removal and\\nreplacement of a juror for abuse of discretion. 38 And as we explained in\\n\\n\\n\\n\\n 34 United States v. Jackson, 636 F.3d 687, 692 (5th Cir. 2011).\\n 35 Id.\\n 36 FED. R. EVID. 1002.\\n 37 FED. R. EVID. 1003.\\n 38 United States v. Huntress, 956 F.2d 1309, 1312 (5th Cir. 1992).\\n\\n 9\\n\\f Case: 17-60397 Document: 00514859557 Page: 10 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nHuntress, a court may not dismiss a juror “without factual support or for a\\nlegally irrelevant reason.” 39\\n\\n\\n The Federal Rules of Criminal Procedure allow a judge to remove jurors\\nwho cannot perform their duties. 40 We explained what that means long ago.\\nForty-plus years ago in Smith, we held that “a juror who cannot remain awake\\nduring much of the trial is unable to perform his duty.” 41 And in 2002, we\\nexplained in Edwards that other good reasons for removal include a “lack of\\ncandor” and an “inability or unwillingness to follow instructions.” 42\\n Here, the district court identified legally relevant reasons for removing\\nJuror 20. The juror slept through witness testimony; misrepresented this fact\\nto the district court when asked; didn’t understand, or else didn’t follow, the\\njury instructions; and didn’t deliberate.\\n Ample evidence supported these legitimate reasons. Near the end of the\\nfirst day of jury deliberations, the foreperson delivered two notes to the court:\\n We have one person that is undecided, and we [cannot] get an\\n answer from him.\\n\\n One, we have a juror that has admitted that he slept through some\\n of the testimony; two, he doesn’t believe you can’t go to Western\\n Union and pick up transaction, his opinion/own notation; three, he\\n refuses to follow the judge’s instruction.\\nAfter reviewing the notes, the court called in the foreperson, Juror 20, and\\nevery other juror one at a time.\\n When the district court asked Juror 20 about sleeping through the trial,\\nhe admitted that he may have “nodded off.” But he said that if he did, “it was\\nvery minimal.” Yet his fellow jurors testified otherwise. Some said that Juror\\n\\n\\n 39 Id.\\n 40 FED. R. CRIM. P. 24(c) (permitting removal of jurors who are “unable to perform or\\nare disqualified from performing their duties”).\\n 41 United States v. Smith, 550 F.2d 277, 285 (5th Cir. 1977).\\n 42 United States v. Edwards, 303 F.3d 606, 631–32 (5th Cir. 2002).\\n\\n 10\\n\\f Case: 17-60397 Document: 00514859557 Page: 11 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\n20 admitted that he “was asleep some of the time, so [he] may have missed\\nthings.” And others said he confessed that “he may not have heard everything\\nhe needed to hear” since he fell asleep.\\n Many jurors even said they saw him sleeping more than just a “minimal”\\namount, including his neighboring juror:\\n I sat next to [Juror 20], I noticed that there was quite a few times,\\n a lot of times, that I would look over and notice that he was\\n asleep. . . . It was more than once a day . . . . I do believe that it\\n was enough to miss key information.\\nAnd several other jurors believed that Juror 20 simply couldn’t follow the law.\\n Juror 19, for example, testified that the jury pointed out specific\\ninstructions to Juror 20, which “he refused to follow”—e.g., “considering only\\nthe evidence presented” and following “the law that’s in the instructions.”\\nAnother juror questioned Juror 20’s comprehension: “He spent three hours\\nreading [the Court’s] instructions yesterday, and he got to Page 5. We’ve tried\\nto talk to him, and he just refuses.”\\n Based on this evidence, the district court removed Juror 20. But Ayelotan\\nand Mewase argue that the court really removed Juror 20 because he was a\\n“hold-out”; because he “clearly questioned Mr. Ayelotan’s guilt.” True, Juror 20\\nresisted convicting. Yet as we noted in Edwards, even “hold-out jurors are not\\nimmune from dismissal based upon just cause.” 43\\n The district court had legitimate reasons to dismiss Juror 20. And there\\nwas strong factual support for those legitimate reasons. Removing Juror 20\\nwas not an abuse of discretion.\\nD. The district court committed no sentencing error.\\n The district court sentenced Ayelotan, Raheem, and Mewase to\\npractically interminable prison terms. The court calculated the total intended\\n\\n\\n\\n 43 Edwards, 303 F.3d at 634.\\n 11\\n\\f Case: 17-60397 Document: 00514859557 Page: 12 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nloss of their scheme: over $25 million. At a joint sentencing hearing, the court\\nheard testimony from a postal inspector and two case agents from Homeland\\nSecurity Investigations. They testified on the loss amount and the defendants’\\nroles.\\n For Ayelotan, the court imposed a 22-level increase for the intended loss.\\nAnd it imposed a 4-level enhancement for his leadership role. This came to a\\ntotal Guidelines offense level of 43. Given Ayelotan’s criminal history, his\\nGuidelines sentence was life imprisonment. The court reduced that to the\\nwithin-Guidelines statutory maximum of 95 years. 44 And it sentenced Ayelotan\\nto that.\\n For Raheem, the court also assigned a total offense level of 43 for the\\nintended loss and his leadership role. His initial sentencing range was life\\nimprisonment too. But the court again decreased it. His within-Guidelines\\nstatutory maximum was 115 years. 45 And the court sentenced him to that.\\n Finally, for Mewase, the court also applied the same 22-level increase for\\nthe intended loss. The resulting Guidelines range was 262 to 327 months. The\\ncourt reduced that to 262 to 300, the statutory maximum. The court then\\nsentenced him to 25 years.\\n All three defendants now challenge their sentences on various grounds.\\n 1. Leadership Enhancement\\n On appeal, Ayelotan and Raheem object to their leadership\\nenhancements. 46 And Ayelotan says that the court should’ve given him a\\nminor-role reduction.\\n As we explained in Hebert, the preponderance of the evidence must show\\nthat the defendant was “the organizer or leader of a criminal activity that\\n\\n\\n 44 See U.S. SENTENCING GUIDELINES MANUAL § 5G1.2(b).\\n 45 See id.\\n 46 Id. § 3B1.1(a).\\n\\n 12\\n\\f Case: 17-60397 Document: 00514859557 Page: 13 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\ninvolved five or more participants or was otherwise extensive.” 47 We will\\nreverse the enhancement only if the district court clearly erred. 48\\n To begin with, the district court found—and the trial evidence\\nsupported—that this was a major criminal undertaking. It involved far more\\nthan five participants. As for leadership, the commentary to § 3B1.1 lists\\nfactors for assessing a defendant’s role:\\n • the exercise of decision-making authority;\\n • the nature of participation in the commission of the offense;\\n • the recruitment of accomplices;\\n • the claimed right to a larger share of the fruits of the crime;\\n • the degree of participation in planning or organizing the\\n offense;\\n • the nature and scope of the illegal activity;\\n • and the degree of control and authority exercised over others. 49\\nThe commentary also clarifies that more than one person can qualify as a\\nleader of the same criminal group. 50\\n Ayelotan argues that the second superseding indictment proves that his\\nrole was “peripheral in substance” and “peripheral in duration.” He claims that\\nthe only accusation against him was that he emailed shipping-label\\ninformation.\\n But the district court specifically relied on several § 3B1.1 factors in\\ndetermining leadership roles. At sentencing, the court heard testimony from\\ncase agent Williams. Agent Williams testified that Ayelotan was among the\\n“top people within the group of indicted defendants.” Williams asserted that\\n\\n\\n\\n 47 See United States v. Hebert, 813 F.3d 551, 560 (5th Cir. 2015).\\n 48 Id.\\n 49 U.S. SENTENCING GUIDELINES MANUAL § 3B1.1 cmt. 4.\\n 50 Id.\\n\\n 13\\n\\f Case: 17-60397 Document: 00514859557 Page: 14 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nAyelotan was a “central hub to a number of other co-conspirators on a daily\\nbasis.” Agent Williams also identified Raheem as one of four coconspirators “at\\nthe top of th[e] hierarchy.”\\n Williams based this on their time spent on the conspiracy, their day-to-\\nday involvement, and the number of coconspirators who reported to them. The\\ndistrict court relied on this testimony. And it determined that Ayelotan “was\\ninvolved in almost every scam involved in the offense”; that he “participated in\\nplanning or organizing it”; and that he directly controlled other conspirators.\\nSimilarly, the court credited Williams’s testimony on Raheem’s leadership in\\nthe organization.\\n The district court did not clearly err considering the evidence before it—\\nnot with Ayelotan and not with Raheem.\\n 2. Eighth Amendment\\n Now for the first time on appeal, Ayelotan and Raheem raise an Eighth\\nAmendment argument. They assert that effective life sentences for nonviolent\\ncrimes are cruel and unusual punishment. We review arguments raised for the\\nfirst time on appeal for plain error. 51 Although Ayelotan acknowledges the\\nplain-error standard, he never briefed anything beyond the first step of the\\nplain-error test: whether an error occurred.\\n Yet even if Ayelotan had sufficiently briefed the other steps of the plain-\\nerror analysis, he still wouldn’t be entitled to relief. Yes, in extraordinary\\ncases, term-of-years sentences can be cruel and unusual. In 1992, we held in\\nMcGruder that sentences violate the Eighth Amendment when they’re “grossly\\ndisproportionate” to the convicted conduct. 52\\n\\n\\n\\n\\n 51 E.g., United States v. Mondragon-Santiago, 564 F.3d 357, 361 (5th Cir. 2009).\\n 52 McGruder v. Puckett, 954 F.2d 313, 315 (5th Cir. 1992).\\n 14\\n\\f Case: 17-60397 Document: 00514859557 Page: 15 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\n But as we’ve explained before, this review is narrow. In our 2016 case\\nMills, we underscored that a reviewing court may not “substitute its judgment\\nfor that of the legislature nor the sentencing court.” 53 And four years before\\nthat, in Looney, we acknowledged that under Supreme Court precedent,\\n“successful Eighth Amendment challenges to prison-term lengths will be\\nrare.” 54\\n Ayelotan maintains that an effective life sentence for a nonviolent,\\nfinancial crime is—by definition—grossly disproportionate. Yet he cites no\\ncases finding that lengthy sentences for financial crimes violate the Eighth\\nAmendment. He cites only to the Supreme Court’s 2010 decision in Graham 55\\nand its 1992 decision in Robinson. 56\\n But in Graham, the Supreme Court limited its decision to life sentences\\nfor minors. 57 And in Robinson, the Court held that a law criminalizing\\nnarcotics addiction was unconstitutional. 58 The Court struck down the law\\nbecause its purpose was to stigmatize addicts; not because the sentence was\\ntoo long. 59 Neither decision applies here.\\n Yet our decision in Mills does apply. There, we held that “the Guidelines\\nare a convincing objective indicator of proportionality.” 60 And in Looney, we\\nupheld effective life sentences for the nonviolent offenses of possession with\\nintent to distribute methamphetamine and possession of firearms. 61\\n\\n\\n\\n\\n 53 United States v. Mills, 843 F.3d 210, 218 (5th Cir. 2016) (citations omitted).\\n 54 United States v. Looney, 532 F.3d 392, 396 (5th Cir. 2008).\\n 55 See generally Graham v. Florida, 560 U.S. 48 (2010).\\n 56 See generally Robinson v. California, 370 U.S. 660 (1992).\\n 57 See Graham, 560 U.S. at 81.\\n 58 Robinson, 370 U.S. at 677.\\n 59 Id. at 677 & n.5.\\n 60 Mills, 843 F.3d at 218.\\n 61 Looney, 532 F.3d at 396.\\n\\n 15\\n\\f Case: 17-60397 Document: 00514859557 Page: 16 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\n Ayelotan’s and Raheem’s within-Guidelines sentences didn’t violate the\\nEighth Amendment. The district court did not err, plainly or otherwise.\\n 3. Intended Loss Calculation\\n Raheem and Mewase challenge the intended loss calculation of over $25\\nmillion. In 2012, we laid out the rule for calculating intended losses in Hebron:\\n“The applicable loss is generally the greater of actual loss—which includes only\\nreasonably foreseeable harm resulting from the fraud—and intended loss—\\nwhich includes the harm intended to result from the offense.” 62 And district\\ncourts need only make “a reasonable estimate of the loss” based on the\\nevidence. 63\\n We review these calculations for clear error. 64 In Hull, we explained that\\nwe review the foreseeability of the loss for clear error too. 65 Then in Sanders,\\nwe established that we review the loss calculation itself for clear error. 66 We\\nwon’t overturn these factual findings “unless they are implausible in light of\\nthe record as a whole.” 67\\n Raheem retorts that the record doesn’t show that they “intended to inflict\\na loss” of $25 million or more. First, that misstates the standard. The\\nSentencing Guidelines don’t require the defendant to have intended the\\nspecific loss amount. 68 Instead, the district court simply has to conclude that\\nthe defendant knew or reasonably should have known that the scheme would\\ncause the harm. 69\\n\\n\\n\\n 62 United States v. Hebron, 684 F.3d 559, 560 (5th Cir. 2012); see also United States v.\\nFairley, 880 F.3d 198, 215 (5th Cir. 2018) (quoting Hebron).\\n 63 Id. (citing U.S. SENTENCING GUIDELINES MANUAL § 2B1.1 cmt. n.3(C)).\\n 64 Id.\\n 65 United States v. Hull, 160 F.3d 265, 269 (5th Cir. 1998).\\n 66 United States v. Sanders, 343 F.3d 511, 519 (5th Cir. 2003).\\n 67 Id.\\n 68 U.S. SENTENCING GUIDELINES MANUAL § 2B1.1 cmt. 3.\\n 69 Id.\\n\\n 16\\n\\f Case: 17-60397 Document: 00514859557 Page: 17 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\n And the district court relied on testimony that showed this: “Mr. Raheem\\nand Mr. Ayelotan were directly involved in most, if not all of [the activity used\\nto calculate the loss amount], and to the extent they were not directly involved,\\nit was certainly reasonably foreseeable to them as part of the jointly\\nundertaken criminal activity which was part and parcel to this conspiracy.”\\n Second, the record does show that the intended loss was over $25 million.\\nThe district court considered the PSR’s calculations. And it heard testimony\\nfrom the postal inspector and two case agents. Based on that, the court\\ncalculated the loss at $52 million.\\n Finally, Raheem disputes the district court’s determination that there\\nwere at least 37,817 credit cards involved in the conspiracy. Rather, Raheem\\nurges that “there is no information all of the alleged credit cards were real.”\\nYet the district court heard specific evidence suggesting that the credit card\\nnumbers corresponded to real accounts. For example, Williams testified that\\nthe first six numbers on the cards—generally identifying the financial\\ninstitutions—matched with real institutions; and that the stolen information\\nincluded three-digit CVV codes on the back of each card.\\n In any event, Raheem and his coconspirators’ intended to get their hands\\non valid credit card numbers. Otherwise, their scheme could bear no fruit.\\nPhony credit cards won’t even buy you Monopoly Money—let alone cash\\nadvances. Even if some card numbers were fake, that wouldn’t matter. Again,\\ntheir intent dictates the intended loss.\\n 4. Substantive Reasonableness of Sentence\\n Finally, Raheem and Mewase contend that their sentences are\\nsubstantively unreasonable. But in 2009, we reiterated in Cooks that we\\npresume a within-Guidelines-range sentence is reasonable. 70 And we tend to\\n\\n\\n\\n 70 United States v. Cooks, 589 F.3d 173, 186 (5th Cir. 2009) (cleaned up).\\n 17\\n\\f Case: 17-60397 Document: 00514859557 Page: 18 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\ndefer to the sentencing court. As we noted in our 2011 decision in Scott, “the\\nsentencing court is in a better position to find facts and judge their import\\nunder the § 3553(a) factors.” 71\\n To rebut the presumption, a defendant must show one of three things:\\n(1) the court failed to consider a factor that it should’ve given significant\\nweight; (2) the court gave significant weight to an irrelevant or improper factor;\\nor (3) the court clearly erred in balancing sentencing factors. 72\\n Raheem argues that his sentence exceeds the aim of the § 3553(a)\\nsentencing factors. But his sentence was within-Guidelines. So it’s presumed\\nreasonable. And here, Raheem hasn’t rebutted that presumption.\\n The district court detailed its justifications and discussed the § 3553(a)\\nfactors. The court noted that Raheem was “a leader or organizer” in “a broad\\nand wide-reaching and extensive conspiracy involving criminal conduct that\\nwent on for a number of years”; one that “involved the manipulation and taking\\nadvantage of, whether financially or otherwise, a large number of victims.”\\n Mewase argues that his sentence is unreasonable because of\\n“unwarranted sentencing disparities” between him and some coconspirators\\nwho pleaded guilty. But this doesn’t rebut the presumption of reasonableness\\neither. Mewase offers no proof that he was so similarly situated to\\ncoconspirators who received lesser sentences that the disparities are\\n“unwarranted.” Nor does the PSR suggest that. Rather, many other\\ncoconspirators played much smaller roles, accepted responsibility, or\\ncooperated with the Government.\\n In sum, we have consistently declined to merely reweigh the sentencing\\nfactors. Yes, Raheem’s within-Guidelines sentence is severe. But the district\\n\\n\\n 71 United States v. Scott, 654 F.3d 552, 555 (5th Cir. 2011) (internal quotation marks\\nand citation omitted).\\n 72 Id.\\n\\n 18\\n\\f Case: 17-60397 Document: 00514859557 Page: 19 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\ncourt weighed the appropriate factors. And its sentence isn’t substantively\\nunreasonable. The district court also grounded Mewase’s sentence in an in-\\ndepth consideration of the § 3553 factors. So neither sentence is substantively\\nunreasonable.\\n\\n IV. CONCLUSION\\n The district court committed no error, and we AFFIRM in all respects.\\n\\n\\n\\n\\n 19\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4373602/\", \"author_raw\": \"DON R. WILLETT, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"STEWART"},"judge2":{"kind":"string","value":"DENNIS"},"judge3":{"kind":"string","value":"WILLETT"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"STEWART\": \", Chief\", \"DENNIS\": \", Circuit\", \"WILLETT\": \", Circuit\"}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4596349/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: United States v. Oladimeji Ayelotan\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-04\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 17-60397 Document: 00514859557 Page: 1 Date Filed: 03/04/2019\n\n\n\n\n REVISED March 4, 2019\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\n United States Court of Appeals\n Fifth Circuit\n\n FILED\n No. 17-60397 March 4, 2019\n Lyle W. Cayce\nUNITED STATES OF AMERICA, Clerk\n\n\n Plaintiff–Appellee,\n\nv.\n\nOLADIMEJI SEUN AYELOTAN; FEMI ALEXANDER MEWASE; RASAQ\nADEROJU RAHEEM,\n\n Defendants–Appellants.\n\n\n Appeals from the United States District Court\n for the Southern District of Mississippi\n\n\nBefore STEWART, Chief Judge, and DENNIS and WILLETT, Circuit Judges.\nDON R. WILLETT, Circuit Judge:\n Three Africa-based cybercriminals—Oladimeji Ayelotan, Femi Mewase,\nand Rasaq Raheem—masterminded a sprawling international romance scam\nthat stole hearts, and money. Posing as bachelors (and bachelorettes) online,\nthese Nigerian nationals kindled digital romances with scores of lovelorn\nAmericans. The fraudsters sat at overseas computers, prowling the Internet\nand spinning false promises of love and romance, ultimately duping their\nunsuspecting victims into sending money to Nigeria and South Africa.\n Many fauxmance swindlers escape scot-free, their victims, broke and\nbrokenhearted, too embarrassed to come forward. Not this time. A wary target\n\f Case: 17-60397 Document: 00514859557 Page: 2 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\nreported her suspicions, and the scammers didn’t fare as well in court as they\nhad online. After a 16-day trial, the jury convicted them, and the district court\nimposed lengthy prison sentences. This appeal alleges several errors—the\ndistrict court’s imposition of leg restraints during trial; the admission of emails\nand a nonoriginal passport; the dismissal of a juror during trial; and the\nsentences handed down.\n Each argument is meritless, and we AFFIRM.\n\n I. BACKGROUND\n The transnational romance scam worked like this: Ayelotan, Mewase,\nand Raheem—along with their coconspirators—stole personal information\nsuch as names, Social Security numbers, credit card numbers, and bank\naccount numbers. They then impersonated their victims—getting cash\nadvances and transferring funds out of the victims’ accounts.\n But they needed a safe way to transfer the fruits of their crimes. Thus\ntheir digital dalliances. Using dating websites like “seniorpeoplemeet.com,”\nwell-honed conversation scripts, and step-by-step guides, the conspirators\ncultivated online relationships, then sweet-talked their “paramours” into\nlaundering their money. Next, the conspirators would cajole their enamored\nvictims into becoming money mules, conduits for stolen funds, even providing\nprepaid shipping labels for the swindled cash and goods.\n Everything was going according to plan until one prospective money\nmule grew suspicious. She reported her experience to the police, who ran it by\nHomeland Security Investigations (the Department of Homeland Security’s\ninvestigation arm). Agent Todd Williams, posing over email as the target\nvictim, helped unravel the whole scheme.\n The district court held a 16-day trial, during which it put the three\ndefendants in leg restraints. The court also removed and replaced one of the\njurors.\n 2\n\f Case: 17-60397 Document: 00514859557 Page: 3 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\n The jury convicted Ayelotan and Raheem on several counts of conspiracy\nto commit mail fraud, wire fraud, and bank fraud; conspiracy to commit\nidentity theft, use of unauthorized access devices, and theft of government\nproperty; mail fraud; and conspiracy to commit money laundering.\n The jury acquitted Mewase of conspiracy to commit money laundering.\nBut it convicted him of conspiracy to commit mail fraud, wire fraud, and bank\nfraud; and conspiracy to commit identity theft, use of unauthorized access\ndevices, and theft of government property.\n The defendants filed post-trial motions for relief. But the district court\nsentenced each defendant to the statutory maximum for each conviction,\nrunning consecutively.\n\n II. STANDARD OF REVIEW\n The arguments raised on appeal involve varying standards of review. We\nreview decisions to shackle criminal defendants, admit evidence, and remove\njurors for abuse of discretion. 1 And it is an abuse of discretion to apply an\nerroneous view of the law or to clearly err in assessing evidence. 2 We review\nalleged Confrontation Clause violations de novo. 3\n As for sentencing, we review fact findings for clear error and application\nof the Sentencing Guidelines de novo. 4 And as the Supreme Court requires, we\nreview the substantive reasonableness of sentences for abuse of discretion. 5\n Finally, the Supreme Court directs us to review arguments raised for the\nfirst time on appeal for plain error. 6 In Puckett, the Court elaborated that\n\n\n\n 1 United States v. Ebron, 683 F.3d 105, 125 (5th Cir. 2012); United States v. Yi, 460\nF.3d 623, 634 (5th Cir. 2006); United States v. Hope, 102 F.3d 114, 117 (5th Cir. 1996).\n 2 United States v. Ragsdale, 426 F.3d 765, 774 (5th Cir. 2005).\n 3 United States v. Morgan, 505 F.3d 332, 338 (5th Cir. 2007) (per curiam).\n 4 United States v. Trujillo, 502 F.3d 353, 356 (5th Cir. 2007).\n 5 Gall v. United States, 552 U.S. 38, 51 (2007).\n 6 Puckett v. United States, 556 U.S. 129, 135 (2009).\n\n 3\n\f Case: 17-60397 Document: 00514859557 Page: 4 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\nunder this standard of review, defendants must first establish an error. 7 Next,\nthey must show that it’s clear or obvious. 8 Then, they must prove that the error\naffected their substantial rights. 9 And if they satisfy these three prongs, we\nmay correct the error—if it “seriously affects the fairness, integrity, or public\nreputation of judicial proceedings.” 10\n\n III. DISCUSSION\n Ayelotan, Raheem, and Mewase bring assorted challenges—none\navailing—to their convictions and sentences:\n • Ayelotan and Raheem—the shackling of their legs during trial\n • Raheem and Mewase—the admission of various emails and\n Mewase’s nonoriginal passport\n • Ayelotan and Mewase—the dismissal of a juror\n • All three defendants—their sentences\nA. Shackling the defendants at trial was not an abuse of discretion.\n Ayelotan and Raheem claim that shackling their legs violated their due\nprocess rights. As the Supreme Court explained 14 years ago in Deck, the Fifth\nand Fourteenth Amendments’ due process clauses require courts to have a\n“particular reason” for shackling; “only in the presence of a special need.” 11 And\nthe Court forbids visible restraints altogether unless “justified by an essential\nstate interest” specific to that trial. 12\n What reasons are enough? Some 25 years ago, in Wilkerson, we held that\ncourts may shackle defendants when there’s a danger of harm or escape. 13 As\n\n\n\n 7 Id.\n 8 Id.\n 9 Id.\n 10 Id. (cleaned up).\n 11 Deck v. Missouri, 544 U.S. 622, 626–28 (2005).\n 12 Id. at 628–29 (quoting Holbrook v. Fynn, 475 U.S. 560, 568–69 (1986)).\n 13 Wilkerson v. Whitley, 16 F.3d 64, 68 (5th Cir. 2003).\n\n 4\n\f Case: 17-60397 Document: 00514859557 Page: 5 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\nwe said then, “[w]e do not underestimate the need to restrain dangerous\ndefendants to prevent courtroom attacks, or the need to give trial courts\nlatitude in making individualized security determinations.” 14 And a few years\nbefore that, in Ellender, we stated that district courts “may rely heavily on the\nU.S. Marshal’s advice” in considering restraints. 15\n Here, the court had valid reasons: Ayelotan and Raheem posed a danger.\nAnd the facts show that. For example, at Ayelotan’s extradition hearing, he\nand other defendants caused such a ruckus that SWAT had to be called in. The\ndistrict court stressed this concern. And given the extradition escapades, the\nU.S. Marshals expressed unease too—recommending that the court restrain\nthe defendants at trial. The court had a valid, particularized reason for\nshackling the defendants.\n Plus, the defendants’ restraints weren’t visible. Neither Ayelotan nor\nRaheem even claim that the restraints were visible. Neither defendant raises\nany evidence suggesting that the jury saw the restraints. And Raheem asserts\nmerely that it’s impossible to be sure that a juror never saw him in shackles.\n In sum, the district court had compelling reasons for shackling the\ndefendants, and there’s no evidence the jury even saw the restraints. And so\nthe district court didn’t violate the defendants’ due process rights.\nB. The emails and copy of Mewase’s passport were admissible.\n At trial, the Government admitted oodles of emails that the defendants\nsent to their romantic targets. These emails all came from Google and Yahoo!\naccounts. And they revealed the defendants’ fraudulent activities. They also\nincluded instructions for money mules to send cash and progress updates on\ntheir various schemes. 16 The defendants filed pretrial objections to admission\n\n\n 14 Id.\n 15 United States v. Ellender, 947 F.2d 748, 760 (5th Cir. 1991).\n 16 Id.\n\n 5\n\f Case: 17-60397 Document: 00514859557 Page: 6 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\nof the emails. But the district court held that the emails and transmittal\nrecords, accompanied by Google and Yahoo! records-custodian certificates,\nwere admissible self-authenticating business records.\n On appeal, Raheem and Mewase challenge the admission of these emails\nand records under the Federal Rules of Evidence and the Confrontation\nClause. Mewase also contends that admission of a duplicate copy of his\npassport identification page violated the Best Evidence Rule. Both challenges\nfail.\n 1. Federal Rules of Evidence\n The Federal Rules of Evidence ban hearsay—out-of-court statements\nmade to prove the truth of what’s asserted. 17 But there are exceptions. Here,\neach email represented two “statements” for purposes of the Federal Rules of\nEvidence. First was the transmittal certificate—effectively, the email\nprovider’s statement that one user wrote and sent a message to another user\nat the recorded time. Second, the content of each email is also a statement. We\ntake them in that order.\n The Federal Rules of Evidence except business records from hearsay. 18\nTo qualify, a records custodian with knowledge must testify unless they’re\n“self-authenticating.” 19 Records are self-authenticating if they include a\ncustodian certification that the records “meet[] the requirements of Rule\n803(6)(A)–(C).” 20\n All the email records from this conspiracy included certificates. The\ncertificates stated that Google or Yahoo! recorded the transmittal data\n\n\n\n FED. R. EVID. 801(c) (“‘Hearsay’ means a statement that: (1) the declarant does not\n 17\n\nmake while testifying at the current trial or hearing; and (2) a party offers in evidence to\nprove the truth of the matter asserted in the statement.”).\n 18 FED. R. EVID. 803(6).\n 19 FED. R. EVID. 803(6); FED. R. EVID. 902(11).\n 20 FED. R. EVID. 902(11).\n\n 6\n\f Case: 17-60397 Document: 00514859557 Page: 7 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\nautomatically when users send emails, as part of the regular practice of a\nregularly conducted business activity. This satisfies Rule 803(6)’s\nrequirements for admission. 21 As we explained in our 1991 Wilson decision,\ncertificates from a records custodian that “track the language of Rule 803(6)\nnearly word for word” render the records self-authenticating. 22 Thus, the\ndistrict court didn’t abuse its discretion by finding a valid hearsay exception\nfor the certificates.\n The second possible hearsay is the emails’ substantive content: the\nmessages between the defendants and their coconspirators. But these were\nadmissible too. The Government didn’t offer these statements to prove the\ncontent of them. 23 Same with the e-mule messages.\n Rather, these statements were “the operative words of [the] criminal\naction”—what we called “paradigmatic nonhearsay” in our 1981 case Jones. 24\nThe remaining content in the emails—updates between the coconspirators\nabout their criminal scheme—was admissible as opposing party and\ncoconspirator statements under Rule 801(d). 25\n\n\n\n 21 FED. R. EVID. 803(6) (“The following are not excluded by the rule against hearsay,\nregardless of whether the declarant is available as a witness: A record of an act, event,\ncondition, opinion, or diagnosis if: (A) the record was made at or near the time by—or from\ninformation transmitted by—someone with knowledge; (B) the record was kept in the course\nof a regularly conducted activity of a business, organization, occupation, or calling, whether\nor not for profit; (C) making the record was a regular practice of that activity; (D) all these\nconditions are shown by the testimony of the custodian or another qualified witness, or by a\ncertification that complies with Rule 902(11) or (12) or with a statute permitting certification;\nand (E) the opponent does not show that the source of information or the method or\ncircumstances of preparation indicate a lack of trustworthiness.”).\n 22 Wilson v. Zapata Off-Shore Co., 939 F.2d 260, 272 (5th Cir. 1991).\n 23 FED. R. EVID. 801(c)(2).\n 24 United States v. Jones, 663 F.2d 567, 571 (5th Cir. 1981).\n 25 FED. R. EVID. 801(d)(2) (“A statement that meets the following conditions is not\n\nhearsay: . . . The statement is offered against an opposing party and: (A) was made by the\nparty in an individual or representative capacity; (B) is one the party manifested that it\nadopted or believed to be true; (C) was made by a person whom the party authorized to make\na statement on the subject; (D) was made by the party’s agent or employee on a matter within\n 7\n\f Case: 17-60397 Document: 00514859557 Page: 8 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\n 2. Confrontation Clause\n Our Confrontation Clause analysis resembles our Federal Rules of\nEvidence analysis. And likewise, the district court didn’t misstep in admitting\nthe emails and records.\n In 2004, the Supreme Court held in Crawford that the Confrontation\nClause prohibits admitting out-of-court statements as evidence against\ndefendants in a criminal case unless they can cross-examine the declarant. 26\nBut that prohibition applies only if the statements are “testimonial.” 27\n And two years later in Davis, the Court explained that statements are\n“testimonial” if their “primary purpose . . . is to establish or prove past events\npotentially relevant to later criminal prosecution.” 28 Or as the Court explained\nin Melendez-Diaz three years after that, business records must be “for the\nadministration of the [business’s] affairs and not for the purpose of\nestablishing or proving some fact at trial.” 29\n Under this framework, Google and Yahoo!’s transmittal-data records\naren’t testimonial. Consider our Towns decision in 2013. 30 There, we\nconsidered a pharmacy’s prescription-purchase logs. 31 We held that those\nweren’t testimonial. 32 Rather, the pharmacy recorded those logs “ex ante to\ncomply with state regulatory measures, not in response to active\nprosecution.” 33 It’s the same with Google and Yahoo! They didn’t create the\n\n\n\nthe scope of that relationship and while it existed; or (E) was made by the party’s\ncoconspirator during and in furtherance of the conspiracy.”).\n 26 See Crawford v. Washington, 541 U.S. 36, 51–53 (2004).\n 27 Id.\n 28 Davis v. Washington, 547 U.S. 813, 822 (2006); see also United States v. Duron-\n\nCaldera, 737 F.3d 988, 992–93 (5th Cir. 2013) (quoting Davis for that proposition).\n 29 Melendez-Diaz v. Massachusetts, 557 U.S. 305, 324 (2009).\n 30 United States v. Towns, 718 F.3d 404, 411 (5th Cir. 2013).\n 31 Id.\n 32 Id.\n 33 Id.\n\n 8\n\f Case: 17-60397 Document: 00514859557 Page: 9 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\nrecords to prove a particular fact at a particular trial—let alone this trial. The\nrecords are admissible as far as the Confrontation Clause goes.\n So are the coconspirator statements. Take our 2011 decision in\nJackson. 34 In that case, we explained that—as a general matter—\n“coconspirator statements made during the course and in furtherance of a\nconspiracy” aren’t testimonial. 35 So the district court didn’t violate the\ndefendants’ Confrontation Clause rights by admitting this evidence.\n 3. Best Evidence Rule\n Mewase also contends that the passport copy was inadmissible under the\nBest Evidence Rule. True, the Federal Rules of Evidence require using “[a]n\noriginal writing, recording, or photograph” as evidence of that item’s contents\nat trial. 36 But the Rules clarify that “[a] duplicate is admissible to the same\nextent as the original unless a genuine question is raised about the original’s\nauthenticity or the circumstances make it unfair to admit a duplicate.” 37\n Mewase’s original passport went missing during his extradition. And\nMewase acknowledges that it wasn’t the Government’s fault. Even so, he still\nclaims that relying on the duplicate isn’t fair. And yet he doesn’t explain why.\nSo the district court didn’t abuse its discretion in admitting the duplicate.\nC. The district court properly removed and replaced Juror 20.\n Ayelotan and Mewase contend that the district court’s decision to remove\nJuror 20 violated their due process rights. We review the removal and\nreplacement of a juror for abuse of discretion. 38 And as we explained in\n\n\n\n\n 34 United States v. Jackson, 636 F.3d 687, 692 (5th Cir. 2011).\n 35 Id.\n 36 FED. R. EVID. 1002.\n 37 FED. R. EVID. 1003.\n 38 United States v. Huntress, 956 F.2d 1309, 1312 (5th Cir. 1992).\n\n 9\n\f Case: 17-60397 Document: 00514859557 Page: 10 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\nHuntress, a court may not dismiss a juror “without factual support or for a\nlegally irrelevant reason.” 39\n\n\n The Federal Rules of Criminal Procedure allow a judge to remove jurors\nwho cannot perform their duties. 40 We explained what that means long ago.\nForty-plus years ago in Smith, we held that “a juror who cannot remain awake\nduring much of the trial is unable to perform his duty.” 41 And in 2002, we\nexplained in Edwards that other good reasons for removal include a “lack of\ncandor” and an “inability or unwillingness to follow instructions.” 42\n Here, the district court identified legally relevant reasons for removing\nJuror 20. The juror slept through witness testimony; misrepresented this fact\nto the district court when asked; didn’t understand, or else didn’t follow, the\njury instructions; and didn’t deliberate.\n Ample evidence supported these legitimate reasons. Near the end of the\nfirst day of jury deliberations, the foreperson delivered two notes to the court:\n We have one person that is undecided, and we [cannot] get an\n answer from him.\n\n One, we have a juror that has admitted that he slept through some\n of the testimony; two, he doesn’t believe you can’t go to Western\n Union and pick up transaction, his opinion/own notation; three, he\n refuses to follow the judge’s instruction.\nAfter reviewing the notes, the court called in the foreperson, Juror 20, and\nevery other juror one at a time.\n When the district court asked Juror 20 about sleeping through the trial,\nhe admitted that he may have “nodded off.” But he said that if he did, “it was\nvery minimal.” Yet his fellow jurors testified otherwise. Some said that Juror\n\n\n 39 Id.\n 40 FED. R. CRIM. P. 24(c) (permitting removal of jurors who are “unable to perform or\nare disqualified from performing their duties”).\n 41 United States v. Smith, 550 F.2d 277, 285 (5th Cir. 1977).\n 42 United States v. Edwards, 303 F.3d 606, 631–32 (5th Cir. 2002).\n\n 10\n\f Case: 17-60397 Document: 00514859557 Page: 11 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\n20 admitted that he “was asleep some of the time, so [he] may have missed\nthings.” And others said he confessed that “he may not have heard everything\nhe needed to hear” since he fell asleep.\n Many jurors even said they saw him sleeping more than just a “minimal”\namount, including his neighboring juror:\n I sat next to [Juror 20], I noticed that there was quite a few times,\n a lot of times, that I would look over and notice that he was\n asleep. . . . It was more than once a day . . . . I do believe that it\n was enough to miss key information.\nAnd several other jurors believed that Juror 20 simply couldn’t follow the law.\n Juror 19, for example, testified that the jury pointed out specific\ninstructions to Juror 20, which “he refused to follow”—e.g., “considering only\nthe evidence presented” and following “the law that’s in the instructions.”\nAnother juror questioned Juror 20’s comprehension: “He spent three hours\nreading [the Court’s] instructions yesterday, and he got to Page 5. We’ve tried\nto talk to him, and he just refuses.”\n Based on this evidence, the district court removed Juror 20. But Ayelotan\nand Mewase argue that the court really removed Juror 20 because he was a\n“hold-out”; because he “clearly questioned Mr. Ayelotan’s guilt.” True, Juror 20\nresisted convicting. Yet as we noted in Edwards, even “hold-out jurors are not\nimmune from dismissal based upon just cause.” 43\n The district court had legitimate reasons to dismiss Juror 20. And there\nwas strong factual support for those legitimate reasons. Removing Juror 20\nwas not an abuse of discretion.\nD. The district court committed no sentencing error.\n The district court sentenced Ayelotan, Raheem, and Mewase to\npractically interminable prison terms. The court calculated the total intended\n\n\n\n 43 Edwards, 303 F.3d at 634.\n 11\n\f Case: 17-60397 Document: 00514859557 Page: 12 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\nloss of their scheme: over $25 million. At a joint sentencing hearing, the court\nheard testimony from a postal inspector and two case agents from Homeland\nSecurity Investigations. They testified on the loss amount and the defendants’\nroles.\n For Ayelotan, the court imposed a 22-level increase for the intended loss.\nAnd it imposed a 4-level enhancement for his leadership role. This came to a\ntotal Guidelines offense level of 43. Given Ayelotan’s criminal history, his\nGuidelines sentence was life imprisonment. The court reduced that to the\nwithin-Guidelines statutory maximum of 95 years. 44 And it sentenced Ayelotan\nto that.\n For Raheem, the court also assigned a total offense level of 43 for the\nintended loss and his leadership role. His initial sentencing range was life\nimprisonment too. But the court again decreased it. His within-Guidelines\nstatutory maximum was 115 years. 45 And the court sentenced him to that.\n Finally, for Mewase, the court also applied the same 22-level increase for\nthe intended loss. The resulting Guidelines range was 262 to 327 months. The\ncourt reduced that to 262 to 300, the statutory maximum. The court then\nsentenced him to 25 years.\n All three defendants now challenge their sentences on various grounds.\n 1. Leadership Enhancement\n On appeal, Ayelotan and Raheem object to their leadership\nenhancements. 46 And Ayelotan says that the court should’ve given him a\nminor-role reduction.\n As we explained in Hebert, the preponderance of the evidence must show\nthat the defendant was “the organizer or leader of a criminal activity that\n\n\n 44 See U.S. SENTENCING GUIDELINES MANUAL § 5G1.2(b).\n 45 See id.\n 46 Id. § 3B1.1(a).\n\n 12\n\f Case: 17-60397 Document: 00514859557 Page: 13 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\ninvolved five or more participants or was otherwise extensive.” 47 We will\nreverse the enhancement only if the district court clearly erred. 48\n To begin with, the district court found—and the trial evidence\nsupported—that this was a major criminal undertaking. It involved far more\nthan five participants. As for leadership, the commentary to § 3B1.1 lists\nfactors for assessing a defendant’s role:\n • the exercise of decision-making authority;\n • the nature of participation in the commission of the offense;\n • the recruitment of accomplices;\n • the claimed right to a larger share of the fruits of the crime;\n • the degree of participation in planning or organizing the\n offense;\n • the nature and scope of the illegal activity;\n • and the degree of control and authority exercised over others. 49\nThe commentary also clarifies that more than one person can qualify as a\nleader of the same criminal group. 50\n Ayelotan argues that the second superseding indictment proves that his\nrole was “peripheral in substance” and “peripheral in duration.” He claims that\nthe only accusation against him was that he emailed shipping-label\ninformation.\n But the district court specifically relied on several § 3B1.1 factors in\ndetermining leadership roles. At sentencing, the court heard testimony from\ncase agent Williams. Agent Williams testified that Ayelotan was among the\n“top people within the group of indicted defendants.” Williams asserted that\n\n\n\n 47 See United States v. Hebert, 813 F.3d 551, 560 (5th Cir. 2015).\n 48 Id.\n 49 U.S. SENTENCING GUIDELINES MANUAL § 3B1.1 cmt. 4.\n 50 Id.\n\n 13\n\f Case: 17-60397 Document: 00514859557 Page: 14 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\nAyelotan was a “central hub to a number of other co-conspirators on a daily\nbasis.” Agent Williams also identified Raheem as one of four coconspirators “at\nthe top of th[e] hierarchy.”\n Williams based this on their time spent on the conspiracy, their day-to-\nday involvement, and the number of coconspirators who reported to them. The\ndistrict court relied on this testimony. And it determined that Ayelotan “was\ninvolved in almost every scam involved in the offense”; that he “participated in\nplanning or organizing it”; and that he directly controlled other conspirators.\nSimilarly, the court credited Williams’s testimony on Raheem’s leadership in\nthe organization.\n The district court did not clearly err considering the evidence before it—\nnot with Ayelotan and not with Raheem.\n 2. Eighth Amendment\n Now for the first time on appeal, Ayelotan and Raheem raise an Eighth\nAmendment argument. They assert that effective life sentences for nonviolent\ncrimes are cruel and unusual punishment. We review arguments raised for the\nfirst time on appeal for plain error. 51 Although Ayelotan acknowledges the\nplain-error standard, he never briefed anything beyond the first step of the\nplain-error test: whether an error occurred.\n Yet even if Ayelotan had sufficiently briefed the other steps of the plain-\nerror analysis, he still wouldn’t be entitled to relief. Yes, in extraordinary\ncases, term-of-years sentences can be cruel and unusual. In 1992, we held in\nMcGruder that sentences violate the Eighth Amendment when they’re “grossly\ndisproportionate” to the convicted conduct. 52\n\n\n\n\n 51 E.g., United States v. Mondragon-Santiago, 564 F.3d 357, 361 (5th Cir. 2009).\n 52 McGruder v. Puckett, 954 F.2d 313, 315 (5th Cir. 1992).\n 14\n\f Case: 17-60397 Document: 00514859557 Page: 15 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\n But as we’ve explained before, this review is narrow. In our 2016 case\nMills, we underscored that a reviewing court may not “substitute its judgment\nfor that of the legislature nor the sentencing court.” 53 And four years before\nthat, in Looney, we acknowledged that under Supreme Court precedent,\n“successful Eighth Amendment challenges to prison-term lengths will be\nrare.” 54\n Ayelotan maintains that an effective life sentence for a nonviolent,\nfinancial crime is—by definition—grossly disproportionate. Yet he cites no\ncases finding that lengthy sentences for financial crimes violate the Eighth\nAmendment. He cites only to the Supreme Court’s 2010 decision in Graham 55\nand its 1992 decision in Robinson. 56\n But in Graham, the Supreme Court limited its decision to life sentences\nfor minors. 57 And in Robinson, the Court held that a law criminalizing\nnarcotics addiction was unconstitutional. 58 The Court struck down the law\nbecause its purpose was to stigmatize addicts; not because the sentence was\ntoo long. 59 Neither decision applies here.\n Yet our decision in Mills does apply. There, we held that “the Guidelines\nare a convincing objective indicator of proportionality.” 60 And in Looney, we\nupheld effective life sentences for the nonviolent offenses of possession with\nintent to distribute methamphetamine and possession of firearms. 61\n\n\n\n\n 53 United States v. Mills, 843 F.3d 210, 218 (5th Cir. 2016) (citations omitted).\n 54 United States v. Looney, 532 F.3d 392, 396 (5th Cir. 2008).\n 55 See generally Graham v. Florida, 560 U.S. 48 (2010).\n 56 See generally Robinson v. California, 370 U.S. 660 (1992).\n 57 See Graham, 560 U.S. at 81.\n 58 Robinson, 370 U.S. at 677.\n 59 Id. at 677 & n.5.\n 60 Mills, 843 F.3d at 218.\n 61 Looney, 532 F.3d at 396.\n\n 15\n\f Case: 17-60397 Document: 00514859557 Page: 16 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\n Ayelotan’s and Raheem’s within-Guidelines sentences didn’t violate the\nEighth Amendment. The district court did not err, plainly or otherwise.\n 3. Intended Loss Calculation\n Raheem and Mewase challenge the intended loss calculation of over $25\nmillion. In 2012, we laid out the rule for calculating intended losses in Hebron:\n“The applicable loss is generally the greater of actual loss—which includes only\nreasonably foreseeable harm resulting from the fraud—and intended loss—\nwhich includes the harm intended to result from the offense.” 62 And district\ncourts need only make “a reasonable estimate of the loss” based on the\nevidence. 63\n We review these calculations for clear error. 64 In Hull, we explained that\nwe review the foreseeability of the loss for clear error too. 65 Then in Sanders,\nwe established that we review the loss calculation itself for clear error. 66 We\nwon’t overturn these factual findings “unless they are implausible in light of\nthe record as a whole.” 67\n Raheem retorts that the record doesn’t show that they “intended to inflict\na loss” of $25 million or more. First, that misstates the standard. The\nSentencing Guidelines don’t require the defendant to have intended the\nspecific loss amount. 68 Instead, the district court simply has to conclude that\nthe defendant knew or reasonably should have known that the scheme would\ncause the harm. 69\n\n\n\n 62 United States v. Hebron, 684 F.3d 559, 560 (5th Cir. 2012); see also United States v.\nFairley, 880 F.3d 198, 215 (5th Cir. 2018) (quoting Hebron).\n 63 Id. (citing U.S. SENTENCING GUIDELINES MANUAL § 2B1.1 cmt. n.3(C)).\n 64 Id.\n 65 United States v. Hull, 160 F.3d 265, 269 (5th Cir. 1998).\n 66 United States v. Sanders, 343 F.3d 511, 519 (5th Cir. 2003).\n 67 Id.\n 68 U.S. SENTENCING GUIDELINES MANUAL § 2B1.1 cmt. 3.\n 69 Id.\n\n 16\n\f Case: 17-60397 Document: 00514859557 Page: 17 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\n And the district court relied on testimony that showed this: “Mr. Raheem\nand Mr. Ayelotan were directly involved in most, if not all of [the activity used\nto calculate the loss amount], and to the extent they were not directly involved,\nit was certainly reasonably foreseeable to them as part of the jointly\nundertaken criminal activity which was part and parcel to this conspiracy.”\n Second, the record does show that the intended loss was over $25 million.\nThe district court considered the PSR’s calculations. And it heard testimony\nfrom the postal inspector and two case agents. Based on that, the court\ncalculated the loss at $52 million.\n Finally, Raheem disputes the district court’s determination that there\nwere at least 37,817 credit cards involved in the conspiracy. Rather, Raheem\nurges that “there is no information all of the alleged credit cards were real.”\nYet the district court heard specific evidence suggesting that the credit card\nnumbers corresponded to real accounts. For example, Williams testified that\nthe first six numbers on the cards—generally identifying the financial\ninstitutions—matched with real institutions; and that the stolen information\nincluded three-digit CVV codes on the back of each card.\n In any event, Raheem and his coconspirators’ intended to get their hands\non valid credit card numbers. Otherwise, their scheme could bear no fruit.\nPhony credit cards won’t even buy you Monopoly Money—let alone cash\nadvances. Even if some card numbers were fake, that wouldn’t matter. Again,\ntheir intent dictates the intended loss.\n 4. Substantive Reasonableness of Sentence\n Finally, Raheem and Mewase contend that their sentences are\nsubstantively unreasonable. But in 2009, we reiterated in Cooks that we\npresume a within-Guidelines-range sentence is reasonable. 70 And we tend to\n\n\n\n 70 United States v. Cooks, 589 F.3d 173, 186 (5th Cir. 2009) (cleaned up).\n 17\n\f Case: 17-60397 Document: 00514859557 Page: 18 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\ndefer to the sentencing court. As we noted in our 2011 decision in Scott, “the\nsentencing court is in a better position to find facts and judge their import\nunder the § 3553(a) factors.” 71\n To rebut the presumption, a defendant must show one of three things:\n(1) the court failed to consider a factor that it should’ve given significant\nweight; (2) the court gave significant weight to an irrelevant or improper factor;\nor (3) the court clearly erred in balancing sentencing factors. 72\n Raheem argues that his sentence exceeds the aim of the § 3553(a)\nsentencing factors. But his sentence was within-Guidelines. So it’s presumed\nreasonable. And here, Raheem hasn’t rebutted that presumption.\n The district court detailed its justifications and discussed the § 3553(a)\nfactors. The court noted that Raheem was “a leader or organizer” in “a broad\nand wide-reaching and extensive conspiracy involving criminal conduct that\nwent on for a number of years”; one that “involved the manipulation and taking\nadvantage of, whether financially or otherwise, a large number of victims.”\n Mewase argues that his sentence is unreasonable because of\n“unwarranted sentencing disparities” between him and some coconspirators\nwho pleaded guilty. But this doesn’t rebut the presumption of reasonableness\neither. Mewase offers no proof that he was so similarly situated to\ncoconspirators who received lesser sentences that the disparities are\n“unwarranted.” Nor does the PSR suggest that. Rather, many other\ncoconspirators played much smaller roles, accepted responsibility, or\ncooperated with the Government.\n In sum, we have consistently declined to merely reweigh the sentencing\nfactors. Yes, Raheem’s within-Guidelines sentence is severe. But the district\n\n\n 71 United States v. Scott, 654 F.3d 552, 555 (5th Cir. 2011) (internal quotation marks\nand citation omitted).\n 72 Id.\n\n 18\n\f Case: 17-60397 Document: 00514859557 Page: 19 Date Filed: 03/04/2019\n\n\n\n No. 17-60397\ncourt weighed the appropriate factors. And its sentence isn’t substantively\nunreasonable. The district court also grounded Mewase’s sentence in an in-\ndepth consideration of the § 3553 factors. So neither sentence is substantively\nunreasonable.\n\n IV. CONCLUSION\n The district court committed no error, and we AFFIRM in all respects.\n\n\n\n\n 19\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: United States v. Oladimeji Ayelotan\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-04\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 17-60397 Document: 00514859557 Page: 1 Date Filed: 03/04/2019\\n\\n\\n\\n\\n REVISED March 4, 2019\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n No. 17-60397 March 4, 2019\\n Lyle W. Cayce\\nUNITED STATES OF AMERICA, Clerk\\n\\n\\n Plaintiff–Appellee,\\n\\nv.\\n\\nOLADIMEJI SEUN AYELOTAN; FEMI ALEXANDER MEWASE; RASAQ\\nADEROJU RAHEEM,\\n\\n Defendants–Appellants.\\n\\n\\n Appeals from the United States District Court\\n for the Southern District of Mississippi\\n\\n\\nBefore STEWART, Chief Judge, and DENNIS and WILLETT, Circuit Judges.\\nDON R. WILLETT, Circuit Judge:\\n Three Africa-based cybercriminals—Oladimeji Ayelotan, Femi Mewase,\\nand Rasaq Raheem—masterminded a sprawling international romance scam\\nthat stole hearts, and money. Posing as bachelors (and bachelorettes) online,\\nthese Nigerian nationals kindled digital romances with scores of lovelorn\\nAmericans. The fraudsters sat at overseas computers, prowling the Internet\\nand spinning false promises of love and romance, ultimately duping their\\nunsuspecting victims into sending money to Nigeria and South Africa.\\n Many fauxmance swindlers escape scot-free, their victims, broke and\\nbrokenhearted, too embarrassed to come forward. Not this time. A wary target\\n\\f Case: 17-60397 Document: 00514859557 Page: 2 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nreported her suspicions, and the scammers didn’t fare as well in court as they\\nhad online. After a 16-day trial, the jury convicted them, and the district court\\nimposed lengthy prison sentences. This appeal alleges several errors—the\\ndistrict court’s imposition of leg restraints during trial; the admission of emails\\nand a nonoriginal passport; the dismissal of a juror during trial; and the\\nsentences handed down.\\n Each argument is meritless, and we AFFIRM.\\n\\n I. BACKGROUND\\n The transnational romance scam worked like this: Ayelotan, Mewase,\\nand Raheem—along with their coconspirators—stole personal information\\nsuch as names, Social Security numbers, credit card numbers, and bank\\naccount numbers. They then impersonated their victims—getting cash\\nadvances and transferring funds out of the victims’ accounts.\\n But they needed a safe way to transfer the fruits of their crimes. Thus\\ntheir digital dalliances. Using dating websites like “seniorpeoplemeet.com,”\\nwell-honed conversation scripts, and step-by-step guides, the conspirators\\ncultivated online relationships, then sweet-talked their “paramours” into\\nlaundering their money. Next, the conspirators would cajole their enamored\\nvictims into becoming money mules, conduits for stolen funds, even providing\\nprepaid shipping labels for the swindled cash and goods.\\n Everything was going according to plan until one prospective money\\nmule grew suspicious. She reported her experience to the police, who ran it by\\nHomeland Security Investigations (the Department of Homeland Security’s\\ninvestigation arm). Agent Todd Williams, posing over email as the target\\nvictim, helped unravel the whole scheme.\\n The district court held a 16-day trial, during which it put the three\\ndefendants in leg restraints. The court also removed and replaced one of the\\njurors.\\n 2\\n\\f Case: 17-60397 Document: 00514859557 Page: 3 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\n The jury convicted Ayelotan and Raheem on several counts of conspiracy\\nto commit mail fraud, wire fraud, and bank fraud; conspiracy to commit\\nidentity theft, use of unauthorized access devices, and theft of government\\nproperty; mail fraud; and conspiracy to commit money laundering.\\n The jury acquitted Mewase of conspiracy to commit money laundering.\\nBut it convicted him of conspiracy to commit mail fraud, wire fraud, and bank\\nfraud; and conspiracy to commit identity theft, use of unauthorized access\\ndevices, and theft of government property.\\n The defendants filed post-trial motions for relief. But the district court\\nsentenced each defendant to the statutory maximum for each conviction,\\nrunning consecutively.\\n\\n II. STANDARD OF REVIEW\\n The arguments raised on appeal involve varying standards of review. We\\nreview decisions to shackle criminal defendants, admit evidence, and remove\\njurors for abuse of discretion. 1 And it is an abuse of discretion to apply an\\nerroneous view of the law or to clearly err in assessing evidence. 2 We review\\nalleged Confrontation Clause violations de novo. 3\\n As for sentencing, we review fact findings for clear error and application\\nof the Sentencing Guidelines de novo. 4 And as the Supreme Court requires, we\\nreview the substantive reasonableness of sentences for abuse of discretion. 5\\n Finally, the Supreme Court directs us to review arguments raised for the\\nfirst time on appeal for plain error. 6 In Puckett, the Court elaborated that\\n\\n\\n\\n 1 United States v. Ebron, 683 F.3d 105, 125 (5th Cir. 2012); United States v. Yi, 460\\nF.3d 623, 634 (5th Cir. 2006); United States v. Hope, 102 F.3d 114, 117 (5th Cir. 1996).\\n 2 United States v. Ragsdale, 426 F.3d 765, 774 (5th Cir. 2005).\\n 3 United States v. Morgan, 505 F.3d 332, 338 (5th Cir. 2007) (per curiam).\\n 4 United States v. Trujillo, 502 F.3d 353, 356 (5th Cir. 2007).\\n 5 Gall v. United States, 552 U.S. 38, 51 (2007).\\n 6 Puckett v. United States, 556 U.S. 129, 135 (2009).\\n\\n 3\\n\\f Case: 17-60397 Document: 00514859557 Page: 4 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nunder this standard of review, defendants must first establish an error. 7 Next,\\nthey must show that it’s clear or obvious. 8 Then, they must prove that the error\\naffected their substantial rights. 9 And if they satisfy these three prongs, we\\nmay correct the error—if it “seriously affects the fairness, integrity, or public\\nreputation of judicial proceedings.” 10\\n\\n III. DISCUSSION\\n Ayelotan, Raheem, and Mewase bring assorted challenges—none\\navailing—to their convictions and sentences:\\n • Ayelotan and Raheem—the shackling of their legs during trial\\n • Raheem and Mewase—the admission of various emails and\\n Mewase’s nonoriginal passport\\n • Ayelotan and Mewase—the dismissal of a juror\\n • All three defendants—their sentences\\nA. Shackling the defendants at trial was not an abuse of discretion.\\n Ayelotan and Raheem claim that shackling their legs violated their due\\nprocess rights. As the Supreme Court explained 14 years ago in Deck, the Fifth\\nand Fourteenth Amendments’ due process clauses require courts to have a\\n“particular reason” for shackling; “only in the presence of a special need.” 11 And\\nthe Court forbids visible restraints altogether unless “justified by an essential\\nstate interest” specific to that trial. 12\\n What reasons are enough? Some 25 years ago, in Wilkerson, we held that\\ncourts may shackle defendants when there’s a danger of harm or escape. 13 As\\n\\n\\n\\n 7 Id.\\n 8 Id.\\n 9 Id.\\n 10 Id. (cleaned up).\\n 11 Deck v. Missouri, 544 U.S. 622, 626–28 (2005).\\n 12 Id. at 628–29 (quoting Holbrook v. Fynn, 475 U.S. 560, 568–69 (1986)).\\n 13 Wilkerson v. Whitley, 16 F.3d 64, 68 (5th Cir. 2003).\\n\\n 4\\n\\f Case: 17-60397 Document: 00514859557 Page: 5 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nwe said then, “[w]e do not underestimate the need to restrain dangerous\\ndefendants to prevent courtroom attacks, or the need to give trial courts\\nlatitude in making individualized security determinations.” 14 And a few years\\nbefore that, in Ellender, we stated that district courts “may rely heavily on the\\nU.S. Marshal’s advice” in considering restraints. 15\\n Here, the court had valid reasons: Ayelotan and Raheem posed a danger.\\nAnd the facts show that. For example, at Ayelotan’s extradition hearing, he\\nand other defendants caused such a ruckus that SWAT had to be called in. The\\ndistrict court stressed this concern. And given the extradition escapades, the\\nU.S. Marshals expressed unease too—recommending that the court restrain\\nthe defendants at trial. The court had a valid, particularized reason for\\nshackling the defendants.\\n Plus, the defendants’ restraints weren’t visible. Neither Ayelotan nor\\nRaheem even claim that the restraints were visible. Neither defendant raises\\nany evidence suggesting that the jury saw the restraints. And Raheem asserts\\nmerely that it’s impossible to be sure that a juror never saw him in shackles.\\n In sum, the district court had compelling reasons for shackling the\\ndefendants, and there’s no evidence the jury even saw the restraints. And so\\nthe district court didn’t violate the defendants’ due process rights.\\nB. The emails and copy of Mewase’s passport were admissible.\\n At trial, the Government admitted oodles of emails that the defendants\\nsent to their romantic targets. These emails all came from Google and Yahoo!\\naccounts. And they revealed the defendants’ fraudulent activities. They also\\nincluded instructions for money mules to send cash and progress updates on\\ntheir various schemes. 16 The defendants filed pretrial objections to admission\\n\\n\\n 14 Id.\\n 15 United States v. Ellender, 947 F.2d 748, 760 (5th Cir. 1991).\\n 16 Id.\\n\\n 5\\n\\f Case: 17-60397 Document: 00514859557 Page: 6 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nof the emails. But the district court held that the emails and transmittal\\nrecords, accompanied by Google and Yahoo! records-custodian certificates,\\nwere admissible self-authenticating business records.\\n On appeal, Raheem and Mewase challenge the admission of these emails\\nand records under the Federal Rules of Evidence and the Confrontation\\nClause. Mewase also contends that admission of a duplicate copy of his\\npassport identification page violated the Best Evidence Rule. Both challenges\\nfail.\\n 1. Federal Rules of Evidence\\n The Federal Rules of Evidence ban hearsay—out-of-court statements\\nmade to prove the truth of what’s asserted. 17 But there are exceptions. Here,\\neach email represented two “statements” for purposes of the Federal Rules of\\nEvidence. First was the transmittal certificate—effectively, the email\\nprovider’s statement that one user wrote and sent a message to another user\\nat the recorded time. Second, the content of each email is also a statement. We\\ntake them in that order.\\n The Federal Rules of Evidence except business records from hearsay. 18\\nTo qualify, a records custodian with knowledge must testify unless they’re\\n“self-authenticating.” 19 Records are self-authenticating if they include a\\ncustodian certification that the records “meet[] the requirements of Rule\\n803(6)(A)–(C).” 20\\n All the email records from this conspiracy included certificates. The\\ncertificates stated that Google or Yahoo! recorded the transmittal data\\n\\n\\n\\n FED. R. EVID. 801(c) (“‘Hearsay’ means a statement that: (1) the declarant does not\\n 17\\n\\nmake while testifying at the current trial or hearing; and (2) a party offers in evidence to\\nprove the truth of the matter asserted in the statement.”).\\n 18 FED. R. EVID. 803(6).\\n 19 FED. R. EVID. 803(6); FED. R. EVID. 902(11).\\n 20 FED. R. EVID. 902(11).\\n\\n 6\\n\\f Case: 17-60397 Document: 00514859557 Page: 7 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nautomatically when users send emails, as part of the regular practice of a\\nregularly conducted business activity. This satisfies Rule 803(6)’s\\nrequirements for admission. 21 As we explained in our 1991 Wilson decision,\\ncertificates from a records custodian that “track the language of Rule 803(6)\\nnearly word for word” render the records self-authenticating. 22 Thus, the\\ndistrict court didn’t abuse its discretion by finding a valid hearsay exception\\nfor the certificates.\\n The second possible hearsay is the emails’ substantive content: the\\nmessages between the defendants and their coconspirators. But these were\\nadmissible too. The Government didn’t offer these statements to prove the\\ncontent of them. 23 Same with the e-mule messages.\\n Rather, these statements were “the operative words of [the] criminal\\naction”—what we called “paradigmatic nonhearsay” in our 1981 case Jones. 24\\nThe remaining content in the emails—updates between the coconspirators\\nabout their criminal scheme—was admissible as opposing party and\\ncoconspirator statements under Rule 801(d). 25\\n\\n\\n\\n 21 FED. R. EVID. 803(6) (“The following are not excluded by the rule against hearsay,\\nregardless of whether the declarant is available as a witness: A record of an act, event,\\ncondition, opinion, or diagnosis if: (A) the record was made at or near the time by—or from\\ninformation transmitted by—someone with knowledge; (B) the record was kept in the course\\nof a regularly conducted activity of a business, organization, occupation, or calling, whether\\nor not for profit; (C) making the record was a regular practice of that activity; (D) all these\\nconditions are shown by the testimony of the custodian or another qualified witness, or by a\\ncertification that complies with Rule 902(11) or (12) or with a statute permitting certification;\\nand (E) the opponent does not show that the source of information or the method or\\ncircumstances of preparation indicate a lack of trustworthiness.”).\\n 22 Wilson v. Zapata Off-Shore Co., 939 F.2d 260, 272 (5th Cir. 1991).\\n 23 FED. R. EVID. 801(c)(2).\\n 24 United States v. Jones, 663 F.2d 567, 571 (5th Cir. 1981).\\n 25 FED. R. EVID. 801(d)(2) (“A statement that meets the following conditions is not\\n\\nhearsay: . . . The statement is offered against an opposing party and: (A) was made by the\\nparty in an individual or representative capacity; (B) is one the party manifested that it\\nadopted or believed to be true; (C) was made by a person whom the party authorized to make\\na statement on the subject; (D) was made by the party’s agent or employee on a matter within\\n 7\\n\\f Case: 17-60397 Document: 00514859557 Page: 8 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\n 2. Confrontation Clause\\n Our Confrontation Clause analysis resembles our Federal Rules of\\nEvidence analysis. And likewise, the district court didn’t misstep in admitting\\nthe emails and records.\\n In 2004, the Supreme Court held in Crawford that the Confrontation\\nClause prohibits admitting out-of-court statements as evidence against\\ndefendants in a criminal case unless they can cross-examine the declarant. 26\\nBut that prohibition applies only if the statements are “testimonial.” 27\\n And two years later in Davis, the Court explained that statements are\\n“testimonial” if their “primary purpose . . . is to establish or prove past events\\npotentially relevant to later criminal prosecution.” 28 Or as the Court explained\\nin Melendez-Diaz three years after that, business records must be “for the\\nadministration of the [business’s] affairs and not for the purpose of\\nestablishing or proving some fact at trial.” 29\\n Under this framework, Google and Yahoo!’s transmittal-data records\\naren’t testimonial. Consider our Towns decision in 2013. 30 There, we\\nconsidered a pharmacy’s prescription-purchase logs. 31 We held that those\\nweren’t testimonial. 32 Rather, the pharmacy recorded those logs “ex ante to\\ncomply with state regulatory measures, not in response to active\\nprosecution.” 33 It’s the same with Google and Yahoo! They didn’t create the\\n\\n\\n\\nthe scope of that relationship and while it existed; or (E) was made by the party’s\\ncoconspirator during and in furtherance of the conspiracy.”).\\n 26 See Crawford v. Washington, 541 U.S. 36, 51–53 (2004).\\n 27 Id.\\n 28 Davis v. Washington, 547 U.S. 813, 822 (2006); see also United States v. Duron-\\n\\nCaldera, 737 F.3d 988, 992–93 (5th Cir. 2013) (quoting Davis for that proposition).\\n 29 Melendez-Diaz v. Massachusetts, 557 U.S. 305, 324 (2009).\\n 30 United States v. Towns, 718 F.3d 404, 411 (5th Cir. 2013).\\n 31 Id.\\n 32 Id.\\n 33 Id.\\n\\n 8\\n\\f Case: 17-60397 Document: 00514859557 Page: 9 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nrecords to prove a particular fact at a particular trial—let alone this trial. The\\nrecords are admissible as far as the Confrontation Clause goes.\\n So are the coconspirator statements. Take our 2011 decision in\\nJackson. 34 In that case, we explained that—as a general matter—\\n“coconspirator statements made during the course and in furtherance of a\\nconspiracy” aren’t testimonial. 35 So the district court didn’t violate the\\ndefendants’ Confrontation Clause rights by admitting this evidence.\\n 3. Best Evidence Rule\\n Mewase also contends that the passport copy was inadmissible under the\\nBest Evidence Rule. True, the Federal Rules of Evidence require using “[a]n\\noriginal writing, recording, or photograph” as evidence of that item’s contents\\nat trial. 36 But the Rules clarify that “[a] duplicate is admissible to the same\\nextent as the original unless a genuine question is raised about the original’s\\nauthenticity or the circumstances make it unfair to admit a duplicate.” 37\\n Mewase’s original passport went missing during his extradition. And\\nMewase acknowledges that it wasn’t the Government’s fault. Even so, he still\\nclaims that relying on the duplicate isn’t fair. And yet he doesn’t explain why.\\nSo the district court didn’t abuse its discretion in admitting the duplicate.\\nC. The district court properly removed and replaced Juror 20.\\n Ayelotan and Mewase contend that the district court’s decision to remove\\nJuror 20 violated their due process rights. We review the removal and\\nreplacement of a juror for abuse of discretion. 38 And as we explained in\\n\\n\\n\\n\\n 34 United States v. Jackson, 636 F.3d 687, 692 (5th Cir. 2011).\\n 35 Id.\\n 36 FED. R. EVID. 1002.\\n 37 FED. R. EVID. 1003.\\n 38 United States v. Huntress, 956 F.2d 1309, 1312 (5th Cir. 1992).\\n\\n 9\\n\\f Case: 17-60397 Document: 00514859557 Page: 10 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nHuntress, a court may not dismiss a juror “without factual support or for a\\nlegally irrelevant reason.” 39\\n\\n\\n The Federal Rules of Criminal Procedure allow a judge to remove jurors\\nwho cannot perform their duties. 40 We explained what that means long ago.\\nForty-plus years ago in Smith, we held that “a juror who cannot remain awake\\nduring much of the trial is unable to perform his duty.” 41 And in 2002, we\\nexplained in Edwards that other good reasons for removal include a “lack of\\ncandor” and an “inability or unwillingness to follow instructions.” 42\\n Here, the district court identified legally relevant reasons for removing\\nJuror 20. The juror slept through witness testimony; misrepresented this fact\\nto the district court when asked; didn’t understand, or else didn’t follow, the\\njury instructions; and didn’t deliberate.\\n Ample evidence supported these legitimate reasons. Near the end of the\\nfirst day of jury deliberations, the foreperson delivered two notes to the court:\\n We have one person that is undecided, and we [cannot] get an\\n answer from him.\\n\\n One, we have a juror that has admitted that he slept through some\\n of the testimony; two, he doesn’t believe you can’t go to Western\\n Union and pick up transaction, his opinion/own notation; three, he\\n refuses to follow the judge’s instruction.\\nAfter reviewing the notes, the court called in the foreperson, Juror 20, and\\nevery other juror one at a time.\\n When the district court asked Juror 20 about sleeping through the trial,\\nhe admitted that he may have “nodded off.” But he said that if he did, “it was\\nvery minimal.” Yet his fellow jurors testified otherwise. Some said that Juror\\n\\n\\n 39 Id.\\n 40 FED. R. CRIM. P. 24(c) (permitting removal of jurors who are “unable to perform or\\nare disqualified from performing their duties”).\\n 41 United States v. Smith, 550 F.2d 277, 285 (5th Cir. 1977).\\n 42 United States v. Edwards, 303 F.3d 606, 631–32 (5th Cir. 2002).\\n\\n 10\\n\\f Case: 17-60397 Document: 00514859557 Page: 11 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\n20 admitted that he “was asleep some of the time, so [he] may have missed\\nthings.” And others said he confessed that “he may not have heard everything\\nhe needed to hear” since he fell asleep.\\n Many jurors even said they saw him sleeping more than just a “minimal”\\namount, including his neighboring juror:\\n I sat next to [Juror 20], I noticed that there was quite a few times,\\n a lot of times, that I would look over and notice that he was\\n asleep. . . . It was more than once a day . . . . I do believe that it\\n was enough to miss key information.\\nAnd several other jurors believed that Juror 20 simply couldn’t follow the law.\\n Juror 19, for example, testified that the jury pointed out specific\\ninstructions to Juror 20, which “he refused to follow”—e.g., “considering only\\nthe evidence presented” and following “the law that’s in the instructions.”\\nAnother juror questioned Juror 20’s comprehension: “He spent three hours\\nreading [the Court’s] instructions yesterday, and he got to Page 5. We’ve tried\\nto talk to him, and he just refuses.”\\n Based on this evidence, the district court removed Juror 20. But Ayelotan\\nand Mewase argue that the court really removed Juror 20 because he was a\\n“hold-out”; because he “clearly questioned Mr. Ayelotan’s guilt.” True, Juror 20\\nresisted convicting. Yet as we noted in Edwards, even “hold-out jurors are not\\nimmune from dismissal based upon just cause.” 43\\n The district court had legitimate reasons to dismiss Juror 20. And there\\nwas strong factual support for those legitimate reasons. Removing Juror 20\\nwas not an abuse of discretion.\\nD. The district court committed no sentencing error.\\n The district court sentenced Ayelotan, Raheem, and Mewase to\\npractically interminable prison terms. The court calculated the total intended\\n\\n\\n\\n 43 Edwards, 303 F.3d at 634.\\n 11\\n\\f Case: 17-60397 Document: 00514859557 Page: 12 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nloss of their scheme: over $25 million. At a joint sentencing hearing, the court\\nheard testimony from a postal inspector and two case agents from Homeland\\nSecurity Investigations. They testified on the loss amount and the defendants’\\nroles.\\n For Ayelotan, the court imposed a 22-level increase for the intended loss.\\nAnd it imposed a 4-level enhancement for his leadership role. This came to a\\ntotal Guidelines offense level of 43. Given Ayelotan’s criminal history, his\\nGuidelines sentence was life imprisonment. The court reduced that to the\\nwithin-Guidelines statutory maximum of 95 years. 44 And it sentenced Ayelotan\\nto that.\\n For Raheem, the court also assigned a total offense level of 43 for the\\nintended loss and his leadership role. His initial sentencing range was life\\nimprisonment too. But the court again decreased it. His within-Guidelines\\nstatutory maximum was 115 years. 45 And the court sentenced him to that.\\n Finally, for Mewase, the court also applied the same 22-level increase for\\nthe intended loss. The resulting Guidelines range was 262 to 327 months. The\\ncourt reduced that to 262 to 300, the statutory maximum. The court then\\nsentenced him to 25 years.\\n All three defendants now challenge their sentences on various grounds.\\n 1. Leadership Enhancement\\n On appeal, Ayelotan and Raheem object to their leadership\\nenhancements. 46 And Ayelotan says that the court should’ve given him a\\nminor-role reduction.\\n As we explained in Hebert, the preponderance of the evidence must show\\nthat the defendant was “the organizer or leader of a criminal activity that\\n\\n\\n 44 See U.S. SENTENCING GUIDELINES MANUAL § 5G1.2(b).\\n 45 See id.\\n 46 Id. § 3B1.1(a).\\n\\n 12\\n\\f Case: 17-60397 Document: 00514859557 Page: 13 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\ninvolved five or more participants or was otherwise extensive.” 47 We will\\nreverse the enhancement only if the district court clearly erred. 48\\n To begin with, the district court found—and the trial evidence\\nsupported—that this was a major criminal undertaking. It involved far more\\nthan five participants. As for leadership, the commentary to § 3B1.1 lists\\nfactors for assessing a defendant’s role:\\n • the exercise of decision-making authority;\\n • the nature of participation in the commission of the offense;\\n • the recruitment of accomplices;\\n • the claimed right to a larger share of the fruits of the crime;\\n • the degree of participation in planning or organizing the\\n offense;\\n • the nature and scope of the illegal activity;\\n • and the degree of control and authority exercised over others. 49\\nThe commentary also clarifies that more than one person can qualify as a\\nleader of the same criminal group. 50\\n Ayelotan argues that the second superseding indictment proves that his\\nrole was “peripheral in substance” and “peripheral in duration.” He claims that\\nthe only accusation against him was that he emailed shipping-label\\ninformation.\\n But the district court specifically relied on several § 3B1.1 factors in\\ndetermining leadership roles. At sentencing, the court heard testimony from\\ncase agent Williams. Agent Williams testified that Ayelotan was among the\\n“top people within the group of indicted defendants.” Williams asserted that\\n\\n\\n\\n 47 See United States v. Hebert, 813 F.3d 551, 560 (5th Cir. 2015).\\n 48 Id.\\n 49 U.S. SENTENCING GUIDELINES MANUAL § 3B1.1 cmt. 4.\\n 50 Id.\\n\\n 13\\n\\f Case: 17-60397 Document: 00514859557 Page: 14 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\nAyelotan was a “central hub to a number of other co-conspirators on a daily\\nbasis.” Agent Williams also identified Raheem as one of four coconspirators “at\\nthe top of th[e] hierarchy.”\\n Williams based this on their time spent on the conspiracy, their day-to-\\nday involvement, and the number of coconspirators who reported to them. The\\ndistrict court relied on this testimony. And it determined that Ayelotan “was\\ninvolved in almost every scam involved in the offense”; that he “participated in\\nplanning or organizing it”; and that he directly controlled other conspirators.\\nSimilarly, the court credited Williams’s testimony on Raheem’s leadership in\\nthe organization.\\n The district court did not clearly err considering the evidence before it—\\nnot with Ayelotan and not with Raheem.\\n 2. Eighth Amendment\\n Now for the first time on appeal, Ayelotan and Raheem raise an Eighth\\nAmendment argument. They assert that effective life sentences for nonviolent\\ncrimes are cruel and unusual punishment. We review arguments raised for the\\nfirst time on appeal for plain error. 51 Although Ayelotan acknowledges the\\nplain-error standard, he never briefed anything beyond the first step of the\\nplain-error test: whether an error occurred.\\n Yet even if Ayelotan had sufficiently briefed the other steps of the plain-\\nerror analysis, he still wouldn’t be entitled to relief. Yes, in extraordinary\\ncases, term-of-years sentences can be cruel and unusual. In 1992, we held in\\nMcGruder that sentences violate the Eighth Amendment when they’re “grossly\\ndisproportionate” to the convicted conduct. 52\\n\\n\\n\\n\\n 51 E.g., United States v. Mondragon-Santiago, 564 F.3d 357, 361 (5th Cir. 2009).\\n 52 McGruder v. Puckett, 954 F.2d 313, 315 (5th Cir. 1992).\\n 14\\n\\f Case: 17-60397 Document: 00514859557 Page: 15 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\n But as we’ve explained before, this review is narrow. In our 2016 case\\nMills, we underscored that a reviewing court may not “substitute its judgment\\nfor that of the legislature nor the sentencing court.” 53 And four years before\\nthat, in Looney, we acknowledged that under Supreme Court precedent,\\n“successful Eighth Amendment challenges to prison-term lengths will be\\nrare.” 54\\n Ayelotan maintains that an effective life sentence for a nonviolent,\\nfinancial crime is—by definition—grossly disproportionate. Yet he cites no\\ncases finding that lengthy sentences for financial crimes violate the Eighth\\nAmendment. He cites only to the Supreme Court’s 2010 decision in Graham 55\\nand its 1992 decision in Robinson. 56\\n But in Graham, the Supreme Court limited its decision to life sentences\\nfor minors. 57 And in Robinson, the Court held that a law criminalizing\\nnarcotics addiction was unconstitutional. 58 The Court struck down the law\\nbecause its purpose was to stigmatize addicts; not because the sentence was\\ntoo long. 59 Neither decision applies here.\\n Yet our decision in Mills does apply. There, we held that “the Guidelines\\nare a convincing objective indicator of proportionality.” 60 And in Looney, we\\nupheld effective life sentences for the nonviolent offenses of possession with\\nintent to distribute methamphetamine and possession of firearms. 61\\n\\n\\n\\n\\n 53 United States v. Mills, 843 F.3d 210, 218 (5th Cir. 2016) (citations omitted).\\n 54 United States v. Looney, 532 F.3d 392, 396 (5th Cir. 2008).\\n 55 See generally Graham v. Florida, 560 U.S. 48 (2010).\\n 56 See generally Robinson v. California, 370 U.S. 660 (1992).\\n 57 See Graham, 560 U.S. at 81.\\n 58 Robinson, 370 U.S. at 677.\\n 59 Id. at 677 & n.5.\\n 60 Mills, 843 F.3d at 218.\\n 61 Looney, 532 F.3d at 396.\\n\\n 15\\n\\f Case: 17-60397 Document: 00514859557 Page: 16 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\n Ayelotan’s and Raheem’s within-Guidelines sentences didn’t violate the\\nEighth Amendment. The district court did not err, plainly or otherwise.\\n 3. Intended Loss Calculation\\n Raheem and Mewase challenge the intended loss calculation of over $25\\nmillion. In 2012, we laid out the rule for calculating intended losses in Hebron:\\n“The applicable loss is generally the greater of actual loss—which includes only\\nreasonably foreseeable harm resulting from the fraud—and intended loss—\\nwhich includes the harm intended to result from the offense.” 62 And district\\ncourts need only make “a reasonable estimate of the loss” based on the\\nevidence. 63\\n We review these calculations for clear error. 64 In Hull, we explained that\\nwe review the foreseeability of the loss for clear error too. 65 Then in Sanders,\\nwe established that we review the loss calculation itself for clear error. 66 We\\nwon’t overturn these factual findings “unless they are implausible in light of\\nthe record as a whole.” 67\\n Raheem retorts that the record doesn’t show that they “intended to inflict\\na loss” of $25 million or more. First, that misstates the standard. The\\nSentencing Guidelines don’t require the defendant to have intended the\\nspecific loss amount. 68 Instead, the district court simply has to conclude that\\nthe defendant knew or reasonably should have known that the scheme would\\ncause the harm. 69\\n\\n\\n\\n 62 United States v. Hebron, 684 F.3d 559, 560 (5th Cir. 2012); see also United States v.\\nFairley, 880 F.3d 198, 215 (5th Cir. 2018) (quoting Hebron).\\n 63 Id. (citing U.S. SENTENCING GUIDELINES MANUAL § 2B1.1 cmt. n.3(C)).\\n 64 Id.\\n 65 United States v. Hull, 160 F.3d 265, 269 (5th Cir. 1998).\\n 66 United States v. Sanders, 343 F.3d 511, 519 (5th Cir. 2003).\\n 67 Id.\\n 68 U.S. SENTENCING GUIDELINES MANUAL § 2B1.1 cmt. 3.\\n 69 Id.\\n\\n 16\\n\\f Case: 17-60397 Document: 00514859557 Page: 17 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\n And the district court relied on testimony that showed this: “Mr. Raheem\\nand Mr. Ayelotan were directly involved in most, if not all of [the activity used\\nto calculate the loss amount], and to the extent they were not directly involved,\\nit was certainly reasonably foreseeable to them as part of the jointly\\nundertaken criminal activity which was part and parcel to this conspiracy.”\\n Second, the record does show that the intended loss was over $25 million.\\nThe district court considered the PSR’s calculations. And it heard testimony\\nfrom the postal inspector and two case agents. Based on that, the court\\ncalculated the loss at $52 million.\\n Finally, Raheem disputes the district court’s determination that there\\nwere at least 37,817 credit cards involved in the conspiracy. Rather, Raheem\\nurges that “there is no information all of the alleged credit cards were real.”\\nYet the district court heard specific evidence suggesting that the credit card\\nnumbers corresponded to real accounts. For example, Williams testified that\\nthe first six numbers on the cards—generally identifying the financial\\ninstitutions—matched with real institutions; and that the stolen information\\nincluded three-digit CVV codes on the back of each card.\\n In any event, Raheem and his coconspirators’ intended to get their hands\\non valid credit card numbers. Otherwise, their scheme could bear no fruit.\\nPhony credit cards won’t even buy you Monopoly Money—let alone cash\\nadvances. Even if some card numbers were fake, that wouldn’t matter. Again,\\ntheir intent dictates the intended loss.\\n 4. Substantive Reasonableness of Sentence\\n Finally, Raheem and Mewase contend that their sentences are\\nsubstantively unreasonable. But in 2009, we reiterated in Cooks that we\\npresume a within-Guidelines-range sentence is reasonable. 70 And we tend to\\n\\n\\n\\n 70 United States v. Cooks, 589 F.3d 173, 186 (5th Cir. 2009) (cleaned up).\\n 17\\n\\f Case: 17-60397 Document: 00514859557 Page: 18 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\ndefer to the sentencing court. As we noted in our 2011 decision in Scott, “the\\nsentencing court is in a better position to find facts and judge their import\\nunder the § 3553(a) factors.” 71\\n To rebut the presumption, a defendant must show one of three things:\\n(1) the court failed to consider a factor that it should’ve given significant\\nweight; (2) the court gave significant weight to an irrelevant or improper factor;\\nor (3) the court clearly erred in balancing sentencing factors. 72\\n Raheem argues that his sentence exceeds the aim of the § 3553(a)\\nsentencing factors. But his sentence was within-Guidelines. So it’s presumed\\nreasonable. And here, Raheem hasn’t rebutted that presumption.\\n The district court detailed its justifications and discussed the § 3553(a)\\nfactors. The court noted that Raheem was “a leader or organizer” in “a broad\\nand wide-reaching and extensive conspiracy involving criminal conduct that\\nwent on for a number of years”; one that “involved the manipulation and taking\\nadvantage of, whether financially or otherwise, a large number of victims.”\\n Mewase argues that his sentence is unreasonable because of\\n“unwarranted sentencing disparities” between him and some coconspirators\\nwho pleaded guilty. But this doesn’t rebut the presumption of reasonableness\\neither. Mewase offers no proof that he was so similarly situated to\\ncoconspirators who received lesser sentences that the disparities are\\n“unwarranted.” Nor does the PSR suggest that. Rather, many other\\ncoconspirators played much smaller roles, accepted responsibility, or\\ncooperated with the Government.\\n In sum, we have consistently declined to merely reweigh the sentencing\\nfactors. Yes, Raheem’s within-Guidelines sentence is severe. But the district\\n\\n\\n 71 United States v. Scott, 654 F.3d 552, 555 (5th Cir. 2011) (internal quotation marks\\nand citation omitted).\\n 72 Id.\\n\\n 18\\n\\f Case: 17-60397 Document: 00514859557 Page: 19 Date Filed: 03/04/2019\\n\\n\\n\\n No. 17-60397\\ncourt weighed the appropriate factors. And its sentence isn’t substantively\\nunreasonable. The district court also grounded Mewase’s sentence in an in-\\ndepth consideration of the § 3553 factors. So neither sentence is substantively\\nunreasonable.\\n\\n IV. CONCLUSION\\n The district court committed no error, and we AFFIRM in all respects.\\n\\n\\n\\n\\n 19\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1075,"cells":{"id":{"kind":"number","value":4597537,"string":"4,597,537"},"name":{"kind":"string","value":"Norma Yanet FUENTES-PENA; Erik Aristedes Vijil-Fuentes; Judith Daniela Vijil-Fuentes, Petitioners v. William P. BARR, U. S. Attorney General, Respondent"},"name_abbreviation":{"kind":"string","value":"Norma Fuentes-Pena v. William Barr, U. S. A"},"decision_date":{"kind":"string","value":"2019-03-06"},"docket_number":{"kind":"string","value":"17-60637"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Jolly, Dennis, Higginson\", \"parties\": \"\", \"opinions\": [{\"author\": \"E. GRADY JOLLY, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 17-60637 Document: 00514860849 Page: 1 Date Filed: 03/06/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n March 6, 2019\\n No. 17-60637 Lyle W. Cayce\\n Clerk\\n\\nNORMA YANET FUENTES-PENA; ERIK ARISTEDES VIJIL-FUENTES;\\nJUDITH DANIELA VIJIL-FUENTES,\\n\\n Petitioners\\n\\nv.\\n\\nWILLIAM P. BARR, U. S. ATTORNEY GENERAL,\\n\\n Respondent\\n\\n\\n\\n\\n Petition for Review of an Order of the\\n Board of Immigration Appeals\\n\\n\\nBefore JOLLY, DENNIS, and HIGGINSON, Circuit Judges.\\nE. GRADY JOLLY, Circuit Judge:\\n Petitioner Norma Yanet Fuentes-Pena and her two minor children seek\\nreview of a final order by the Board of Immigration Appeals (BIA) denying her\\nmotion to reopen removal proceedings. She contends that the BIA abused its\\ndiscretion by refusing to reopen her removal proceedings because she never\\nreceived notice of her removal hearing. The government argues that Fuentes-\\nPena did not receive notice because she moved without informing the\\nimmigration court of her new address. Because Fuentes-Pena updated her\\naddress with Immigration and Customs Enforcement (ICE), we VACATE the\\norder of the BIA and REMAND for further proceedings.\\n\\f Case: 17-60637 Document: 00514860849 Page: 2 Date Filed: 03/06/2019\\n\\n\\n\\n No. 17-60637\\n I.\\n Norma Yanet Fuentes-Pena is a native and citizen of El Salvador who\\nentered the United States near Hidalgo, Texas, with her two children. Upon\\nher release from immigration detention, the Department of Homeland Security\\n(DHS) personally served Fuentes-Pena with a Notice to Appear (NTA),\\ncharging her with removability as an alien present in the United States\\nwithout being admitted or paroled. The NTA advised Fuentes-Pena that she\\nwas to appear before an immigration judge (IJ) in Miami, Florida on a date\\nand at a time to be later determined. Fuentes-Pena’s children were “riders” on\\nher immigration case. Accompanying the NTA was a notice from ICE, an\\nagency within DHS, stating that the NTA would “be filed with the Office of the\\nImmigration Judge with jurisdiction over the residential address [she]\\nprovided to ICE upon [her] release.”\\n Upon release from DHS custody, Fuentes-Pena, as required by law,\\nprovided an address for further communication, which was in Duncanville,\\nTexas. Fuentes-Pena received an EOIR-33 form and acknowledged that she\\nneeded to use that form to inform the “Office of the Immigration Judge” and\\nICE of any change in her address within five days. The NTA also stated: “If\\nyou do not submit EOIR-33 and do not otherwise provide an address at which\\nyou may be reached during proceedings, then the Government shall not be\\nrequired to provide you with written notice of your hearing.” Several months\\nlater, in March 2016, Fuentes-Pena moved to Massachusetts and informed\\nonly ICE of her change of address. On June 1, 2016, the NTA, furnished by\\nICE, was stamped as received by the immigration court in Dallas, Texas. On\\nJune 7, 2016, a hearing notice from the immigration court was mailed to the\\nDuncanville, Texas address that she had provided when she was released,\\nadvising Fuentes-Pena that a hearing was scheduled for June 20, 2016, in\\nDallas, Texas. Fuentes-Pena, however, failed to appear for the scheduled\\n 2\\n\\f Case: 17-60637 Document: 00514860849 Page: 3 Date Filed: 03/06/2019\\n\\n\\n\\n No. 17-60637\\nhearing. Consequently, the IJ found her removable as charged in the NTA\\nand, in absentia, ordered her removed to El Salvador. The IJ’s in absentia\\nremoval order was also mailed to Fuentes-Pena at the Duncanville, Texas\\naddress.\\n On November 15, 2016, Fuentes-Pena filed a motion to reopen and\\nrescind the in absentia order of removal. In her motion, Fuentes-Pena argued\\nthat, although she had failed to apprise the immigration court of the change in\\nher address, she had met her obligation to provide a current address by giving\\nher new address to the ICE office in Massachusetts. Alternatively, Fuentes-\\nPena argued that exceptional circumstances warranted the reopening of her\\nremoval proceedings because she “did everything she could to remain apprised\\nof her court hearing and her failure to appear was beyond her control.” Finally,\\nFuentes-Pena requested that the IJ reopen her case sua sponte if it found that\\nreopening was not warranted on any other grounds.\\n The IJ issued a written decision denying Fuentes-Pena’s motion to\\nreopen. The IJ found that it was not required to provide written notice of the\\nhearing. While Fuentes-Pena had apprised ICE of her change in address, she\\ndid not meet her obligation to inform the immigration court, despite the fact\\nthat the NTA specified this obligation. Further, the IJ found that the NTA had\\nprovided Fuentes-Pena with “constructive” notice of the hearing. The IJ\\ndetermined that Fuentes-Pena did not show exceptional circumstances, such\\nas “battery, extreme cruelty, or serious illness,” and it declined to reopen her\\ncase sua sponte because it did not present an “exceptional situation.”\\n Fuentes-Pena appealed the IJ’s decision. On appeal, Fuentes-Pena\\nreiterated her earlier arguments. The BIA issued an order dismissing\\nFuentes-Pena’s appeal. The BIA found that the hearing notice was properly\\nmailed to Fuentes-Pena’s address of record. Further, the BIA noted that the\\nNTA informed Fuentes-Pena of her obligation to update her address and the\\n 3\\n\\f Case: 17-60637 Document: 00514860849 Page: 4 Date Filed: 03/06/2019\\n\\n\\n\\n No. 17-60637\\nconsequences of missing her hearing. Finally, the BIA found that Fuentes-\\nPena did not establish exceptional circumstances based on the “totality of the\\ncircumstances” and that the IJ did not err by refusing to reopen her case sua\\nsponte. Fuentes-Pena filed a timely petition for review. See 8 U.S.C.\\n§ 1252(b)(1).\\n II.\\n When considering a petition for review, we have the authority to review\\nonly the BIA’s decision, not the IJ’s decision, unless the IJ’s decision has some\\nimpact on the BIA’s decision. See Mikhael v. INS, 115 F.3d 299, 302 (5th Cir.\\n1997). Here, the BIA referenced the IJ’s decision and found that the IJ\\ncommitted no error. We review the denial of a motion to reopen under a highly\\ndeferential abuse-of-discretion standard. See Zhao v. Gonzales, 404 F.3d 295,\\n303 (5th Cir. 2005). Motions to reopen immigration proceedings are disfavored\\nbecause “as a general matter, every delay works to the advantage of the\\ndeportable alien who wishes merely to remain in the United States.” INS v.\\nDoherty, 502 U.S. 314, 323 (1992). On petition for review of a BIA decision, we\\nreview factual findings for substantial evidence, meaning that we will accept\\nthe BIA’s factual findings “unless the evidence is so compelling that no\\nreasonable fact finder could fail to find otherwise.” Lopez-Gomez v. Ashcroft,\\n263 F.3d 442, 444 (5th Cir. 2001) (internal citation and quotation marks\\nomitted). We review constitutional claims and questions of law de novo. See\\nSattani v. Holder, 749 F.3d 368, 370 (5th Cir. 2014).\\n III.\\n In her petition for review, Fuentes-Pena argues that the BIA abused its\\ndiscretion by affirming the IJ’s order denying her motion to reopen. 1 We agree.\\n\\n\\n\\n 1Because we find that the BIA abused its discretion by affirming the IJ’s order, we do\\nnot reach Fuentes-Pena’s second argument, that the immigration court violated her right to\\n 4\\n\\f Case: 17-60637 Document: 00514860849 Page: 5 Date Filed: 03/06/2019\\n\\n\\n\\n No. 17-60637\\n An alien must be provided with written notice of the time and place at\\nwhich a removal hearing will be held. 8 U.S.C. § 1229(a)(1)(G)(i). Service of\\nthe notice may be by mail. Id. § 1229(c); see also 8 C.F.R. § 1003.13 (allowing\\nservice by “regular mail”). Any alien who fails to appear at a deportation\\nhearing after written notice or fails to provide an address shall be ordered\\nremoved in absentia if DHS establishes by clear, unequivocal, and convincing\\nevidence that the alien is removable and that the alien was provided with the\\nwritten notice required under 8 U.S.C. § 1229(a)(1)–(2). See id.\\n§ 1229a(b)(5)(A). “The written notice by the Attorney General shall be\\nconsidered sufficient . . . if provided at the most recent address provided under\\nsection 1229(a)(1)(F) of this title.” Id. § 1229a(b)(5)(A). Section 1229(a)(1)(F),\\nin turn, requires that an “alien must provide the Attorney General\\nimmediately with a written record of any change of the alien’s address.” Id. §\\n1229(a)(1)(F)(ii).\\n Written notice of the deportation hearing is not required if the alien fails\\nto satisfy the requirement in 8 U.S.C. § 1229(a)(1)(F) to provide an address\\nwhere “the alien may be contacted respecting [removal] proceedings.” See id.\\n§ 1229(a)(2)(B). A deportation order may be rescinded through a motion to\\nreopen if the alien demonstrates that they “did not receive notice in accordance\\nwith paragraph (1) or (2) of section 1229(a).” Id. § 1229a(b)(5)(C)(ii). On a\\nmotion to reopen, it is the alien’s burden to demonstrate that they did not\\nreceive notice in accordance with section 1229(a). See id. We have held that\\nan alien’s failure to receive actual notice of a removal hearing due to their\\nneglect of their obligation to inform the immigration court of their current\\n\\n\\n\\n\\ndue process by failing to properly notify her of the hearing when it sent notice of the hearing\\nto the address she provided ICE upon her release.\\n 5\\n\\f Case: 17-60637 Document: 00514860849 Page: 6 Date Filed: 03/06/2019\\n\\n\\n\\n No. 17-60637\\naddress does not mean that the alien did not receive the statutorily required\\nnotice. Gomez-Palacios v. Holder, 560 F.3d 354, 360–61 (5th Cir. 2009). 2\\n Nonetheless, we find that Gomez-Palacios is distinguishable. Unlike the\\nalien in Gomez-Palacios, Fuentes-Pena notified ICE of her change of address\\nbefore ICE filed the NTA with the immigration court. This means that the\\ngovernment cannot rely on 8 CFR § 1003.15(d), which requires aliens to notify\\nthe immigration court of any change of address only after the NTA has been\\nfiled by the government.\\n The government, however, instead attempts to support the BIA’s\\ndecision by pointing directly to the statute. 8 U.S.C. § 1229(a)(1)(F) required\\nFuentes-Pena to “provide the Attorney General immediately with a written\\nrecord of any change” to her address. We must determine whether Fuentes-\\nPena satisfied this obligation by notifying ICE of her new address.\\n Section 1229 was enacted before the creation of the Department of\\nHomeland Security. Prior to that statutory change, removal proceedings were\\nprosecuted by the Immigration and Naturalization Service (INS), which indeed\\nwas an agency within the Department of Justice (DOJ). But when the DHS\\nwas created, the INS was dissolved and most of its functions were moved out\\nof the DOJ and into the DHS. 6 U.S.C. § 557 facilitated this transition by\\nproviding that:\\n With respect to any function transferred by or under this chapter\\n (including under a reorganization plan that becomes effective\\n under section 542 of this title) and exercised on or after the\\n effective date of this chapter, reference in any other Federal law to\\n\\n\\n 2 In Pereira v. Sessions, handed down after the initial briefing was concluded in this\\ncase, the Supreme Court addressed a “narrow question” regarding the effect of an NTA that\\ndoes not specify the time or place of the removal hearing on the trigger for the “stop-time\\nrule” for the purposes of a cancellation of removal. 138 S.Ct. 2105, 2110 (2018). We recently\\nheld that this decision does not affect our holding in Gomez-Palacios. See Mauricio-Benitez\\nv. Sessions, 908 F.3d 144, 148 n.1 (5th Cir. 2018).\\n\\n 6\\n\\f Case: 17-60637 Document: 00514860849 Page: 7 Date Filed: 03/06/2019\\n\\n\\n\\n No. 17-60637\\n any department, commission, or agency or any officer or office the\\n functions of which are so transferred shall be deemed to refer to\\n the Secretary, other official, or component of the Department to\\n which such function is so transferred.\\nThe former INS was responsible for providing aliens with the statutorily\\nrequired NTA and for filing the NTA, containing the alien’s current address,\\nwith the immigration court. Both functions are now performed by ICE. In\\nmost cases, the immigration court then has the responsibility to send the\\nprecise hearing information to the alien’s address on file. See 8 C.F.R.\\n§ 1003.18. Because ICE is now responsible for providing the alien’s address to\\nthe immigration court when it files the NTA, we read 8 U.S.C. §1229, through\\nthe lens of 6 U.S.C. § 557, to require the alien to provide a change of address\\nto ICE at least until the NTA has been filed with the immigration court. 3 As\\nsuch, by notifying ICE of her change of address before it filed the NTA with the\\nimmigration court, Fuentes-Pena satisfied her statutory obligation to provide\\nnotice of her change of address, and her failure to attend her removal hearing\\nis excused. The BIA abused its discretion by refusing to reopen removal\\nproceedings against her.\\n IV.\\n In sum, we hold that the BIA abused its discretion in refusing to reopen\\nFuentes-Pena’s removal proceedings. Under these circumstances, Fuentes-\\nPena satisfied her obligation to provide her new address to the “Attorney\\nGeneral” by notifying ICE of her change of address. We VACATE the decision\\nof the BIA and REMAND the case for further proceedings not inconsistent with\\nthis opinion.\\n\\n\\n\\n\\n 3 We express no opinion on an alien’s statutory obligations after the NTA has been\\nfiled with the immigration court.\\n 7\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4374790/\", \"author_raw\": \"E. GRADY JOLLY, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"JOLLY"},"judge2":{"kind":"string","value":"DENNIS"},"judge3":{"kind":"string","value":"HIGGINSON"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4597537/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Norma Yanet FUENTES-PENA; Erik Aristedes Vijil-Fuentes; Judith Daniela Vijil-Fuentes, Petitioners v. William P. BARR, U. S. Attorney General, Respondent\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-06\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 17-60637 Document: 00514860849 Page: 1 Date Filed: 03/06/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\n United States Court of Appeals\n Fifth Circuit\n\n FILED\n March 6, 2019\n No. 17-60637 Lyle W. Cayce\n Clerk\n\nNORMA YANET FUENTES-PENA; ERIK ARISTEDES VIJIL-FUENTES;\nJUDITH DANIELA VIJIL-FUENTES,\n\n Petitioners\n\nv.\n\nWILLIAM P. BARR, U. S. ATTORNEY GENERAL,\n\n Respondent\n\n\n\n\n Petition for Review of an Order of the\n Board of Immigration Appeals\n\n\nBefore JOLLY, DENNIS, and HIGGINSON, Circuit Judges.\nE. GRADY JOLLY, Circuit Judge:\n Petitioner Norma Yanet Fuentes-Pena and her two minor children seek\nreview of a final order by the Board of Immigration Appeals (BIA) denying her\nmotion to reopen removal proceedings. She contends that the BIA abused its\ndiscretion by refusing to reopen her removal proceedings because she never\nreceived notice of her removal hearing. The government argues that Fuentes-\nPena did not receive notice because she moved without informing the\nimmigration court of her new address. Because Fuentes-Pena updated her\naddress with Immigration and Customs Enforcement (ICE), we VACATE the\norder of the BIA and REMAND for further proceedings.\n\f Case: 17-60637 Document: 00514860849 Page: 2 Date Filed: 03/06/2019\n\n\n\n No. 17-60637\n I.\n Norma Yanet Fuentes-Pena is a native and citizen of El Salvador who\nentered the United States near Hidalgo, Texas, with her two children. Upon\nher release from immigration detention, the Department of Homeland Security\n(DHS) personally served Fuentes-Pena with a Notice to Appear (NTA),\ncharging her with removability as an alien present in the United States\nwithout being admitted or paroled. The NTA advised Fuentes-Pena that she\nwas to appear before an immigration judge (IJ) in Miami, Florida on a date\nand at a time to be later determined. Fuentes-Pena’s children were “riders” on\nher immigration case. Accompanying the NTA was a notice from ICE, an\nagency within DHS, stating that the NTA would “be filed with the Office of the\nImmigration Judge with jurisdiction over the residential address [she]\nprovided to ICE upon [her] release.”\n Upon release from DHS custody, Fuentes-Pena, as required by law,\nprovided an address for further communication, which was in Duncanville,\nTexas. Fuentes-Pena received an EOIR-33 form and acknowledged that she\nneeded to use that form to inform the “Office of the Immigration Judge” and\nICE of any change in her address within five days. The NTA also stated: “If\nyou do not submit EOIR-33 and do not otherwise provide an address at which\nyou may be reached during proceedings, then the Government shall not be\nrequired to provide you with written notice of your hearing.” Several months\nlater, in March 2016, Fuentes-Pena moved to Massachusetts and informed\nonly ICE of her change of address. On June 1, 2016, the NTA, furnished by\nICE, was stamped as received by the immigration court in Dallas, Texas. On\nJune 7, 2016, a hearing notice from the immigration court was mailed to the\nDuncanville, Texas address that she had provided when she was released,\nadvising Fuentes-Pena that a hearing was scheduled for June 20, 2016, in\nDallas, Texas. Fuentes-Pena, however, failed to appear for the scheduled\n 2\n\f Case: 17-60637 Document: 00514860849 Page: 3 Date Filed: 03/06/2019\n\n\n\n No. 17-60637\nhearing. Consequently, the IJ found her removable as charged in the NTA\nand, in absentia, ordered her removed to El Salvador. The IJ’s in absentia\nremoval order was also mailed to Fuentes-Pena at the Duncanville, Texas\naddress.\n On November 15, 2016, Fuentes-Pena filed a motion to reopen and\nrescind the in absentia order of removal. In her motion, Fuentes-Pena argued\nthat, although she had failed to apprise the immigration court of the change in\nher address, she had met her obligation to provide a current address by giving\nher new address to the ICE office in Massachusetts. Alternatively, Fuentes-\nPena argued that exceptional circumstances warranted the reopening of her\nremoval proceedings because she “did everything she could to remain apprised\nof her court hearing and her failure to appear was beyond her control.” Finally,\nFuentes-Pena requested that the IJ reopen her case sua sponte if it found that\nreopening was not warranted on any other grounds.\n The IJ issued a written decision denying Fuentes-Pena’s motion to\nreopen. The IJ found that it was not required to provide written notice of the\nhearing. While Fuentes-Pena had apprised ICE of her change in address, she\ndid not meet her obligation to inform the immigration court, despite the fact\nthat the NTA specified this obligation. Further, the IJ found that the NTA had\nprovided Fuentes-Pena with “constructive” notice of the hearing. The IJ\ndetermined that Fuentes-Pena did not show exceptional circumstances, such\nas “battery, extreme cruelty, or serious illness,” and it declined to reopen her\ncase sua sponte because it did not present an “exceptional situation.”\n Fuentes-Pena appealed the IJ’s decision. On appeal, Fuentes-Pena\nreiterated her earlier arguments. The BIA issued an order dismissing\nFuentes-Pena’s appeal. The BIA found that the hearing notice was properly\nmailed to Fuentes-Pena’s address of record. Further, the BIA noted that the\nNTA informed Fuentes-Pena of her obligation to update her address and the\n 3\n\f Case: 17-60637 Document: 00514860849 Page: 4 Date Filed: 03/06/2019\n\n\n\n No. 17-60637\nconsequences of missing her hearing. Finally, the BIA found that Fuentes-\nPena did not establish exceptional circumstances based on the “totality of the\ncircumstances” and that the IJ did not err by refusing to reopen her case sua\nsponte. Fuentes-Pena filed a timely petition for review. See 8 U.S.C.\n§ 1252(b)(1).\n II.\n When considering a petition for review, we have the authority to review\nonly the BIA’s decision, not the IJ’s decision, unless the IJ’s decision has some\nimpact on the BIA’s decision. See Mikhael v. INS, 115 F.3d 299, 302 (5th Cir.\n1997). Here, the BIA referenced the IJ’s decision and found that the IJ\ncommitted no error. We review the denial of a motion to reopen under a highly\ndeferential abuse-of-discretion standard. See Zhao v. Gonzales, 404 F.3d 295,\n303 (5th Cir. 2005). Motions to reopen immigration proceedings are disfavored\nbecause “as a general matter, every delay works to the advantage of the\ndeportable alien who wishes merely to remain in the United States.” INS v.\nDoherty, 502 U.S. 314, 323 (1992). On petition for review of a BIA decision, we\nreview factual findings for substantial evidence, meaning that we will accept\nthe BIA’s factual findings “unless the evidence is so compelling that no\nreasonable fact finder could fail to find otherwise.” Lopez-Gomez v. Ashcroft,\n263 F.3d 442, 444 (5th Cir. 2001) (internal citation and quotation marks\nomitted). We review constitutional claims and questions of law de novo. See\nSattani v. Holder, 749 F.3d 368, 370 (5th Cir. 2014).\n III.\n In her petition for review, Fuentes-Pena argues that the BIA abused its\ndiscretion by affirming the IJ’s order denying her motion to reopen. 1 We agree.\n\n\n\n 1Because we find that the BIA abused its discretion by affirming the IJ’s order, we do\nnot reach Fuentes-Pena’s second argument, that the immigration court violated her right to\n 4\n\f Case: 17-60637 Document: 00514860849 Page: 5 Date Filed: 03/06/2019\n\n\n\n No. 17-60637\n An alien must be provided with written notice of the time and place at\nwhich a removal hearing will be held. 8 U.S.C. § 1229(a)(1)(G)(i). Service of\nthe notice may be by mail. Id. § 1229(c); see also 8 C.F.R. § 1003.13 (allowing\nservice by “regular mail”). Any alien who fails to appear at a deportation\nhearing after written notice or fails to provide an address shall be ordered\nremoved in absentia if DHS establishes by clear, unequivocal, and convincing\nevidence that the alien is removable and that the alien was provided with the\nwritten notice required under 8 U.S.C. § 1229(a)(1)–(2). See id.\n§ 1229a(b)(5)(A). “The written notice by the Attorney General shall be\nconsidered sufficient . . . if provided at the most recent address provided under\nsection 1229(a)(1)(F) of this title.” Id. § 1229a(b)(5)(A). Section 1229(a)(1)(F),\nin turn, requires that an “alien must provide the Attorney General\nimmediately with a written record of any change of the alien’s address.” Id. §\n1229(a)(1)(F)(ii).\n Written notice of the deportation hearing is not required if the alien fails\nto satisfy the requirement in 8 U.S.C. § 1229(a)(1)(F) to provide an address\nwhere “the alien may be contacted respecting [removal] proceedings.” See id.\n§ 1229(a)(2)(B). A deportation order may be rescinded through a motion to\nreopen if the alien demonstrates that they “did not receive notice in accordance\nwith paragraph (1) or (2) of section 1229(a).” Id. § 1229a(b)(5)(C)(ii). On a\nmotion to reopen, it is the alien’s burden to demonstrate that they did not\nreceive notice in accordance with section 1229(a). See id. We have held that\nan alien’s failure to receive actual notice of a removal hearing due to their\nneglect of their obligation to inform the immigration court of their current\n\n\n\n\ndue process by failing to properly notify her of the hearing when it sent notice of the hearing\nto the address she provided ICE upon her release.\n 5\n\f Case: 17-60637 Document: 00514860849 Page: 6 Date Filed: 03/06/2019\n\n\n\n No. 17-60637\naddress does not mean that the alien did not receive the statutorily required\nnotice. Gomez-Palacios v. Holder, 560 F.3d 354, 360–61 (5th Cir. 2009). 2\n Nonetheless, we find that Gomez-Palacios is distinguishable. Unlike the\nalien in Gomez-Palacios, Fuentes-Pena notified ICE of her change of address\nbefore ICE filed the NTA with the immigration court. This means that the\ngovernment cannot rely on 8 CFR § 1003.15(d), which requires aliens to notify\nthe immigration court of any change of address only after the NTA has been\nfiled by the government.\n The government, however, instead attempts to support the BIA’s\ndecision by pointing directly to the statute. 8 U.S.C. § 1229(a)(1)(F) required\nFuentes-Pena to “provide the Attorney General immediately with a written\nrecord of any change” to her address. We must determine whether Fuentes-\nPena satisfied this obligation by notifying ICE of her new address.\n Section 1229 was enacted before the creation of the Department of\nHomeland Security. Prior to that statutory change, removal proceedings were\nprosecuted by the Immigration and Naturalization Service (INS), which indeed\nwas an agency within the Department of Justice (DOJ). But when the DHS\nwas created, the INS was dissolved and most of its functions were moved out\nof the DOJ and into the DHS. 6 U.S.C. § 557 facilitated this transition by\nproviding that:\n With respect to any function transferred by or under this chapter\n (including under a reorganization plan that becomes effective\n under section 542 of this title) and exercised on or after the\n effective date of this chapter, reference in any other Federal law to\n\n\n 2 In Pereira v. Sessions, handed down after the initial briefing was concluded in this\ncase, the Supreme Court addressed a “narrow question” regarding the effect of an NTA that\ndoes not specify the time or place of the removal hearing on the trigger for the “stop-time\nrule” for the purposes of a cancellation of removal. 138 S.Ct. 2105, 2110 (2018). We recently\nheld that this decision does not affect our holding in Gomez-Palacios. See Mauricio-Benitez\nv. Sessions, 908 F.3d 144, 148 n.1 (5th Cir. 2018).\n\n 6\n\f Case: 17-60637 Document: 00514860849 Page: 7 Date Filed: 03/06/2019\n\n\n\n No. 17-60637\n any department, commission, or agency or any officer or office the\n functions of which are so transferred shall be deemed to refer to\n the Secretary, other official, or component of the Department to\n which such function is so transferred.\nThe former INS was responsible for providing aliens with the statutorily\nrequired NTA and for filing the NTA, containing the alien’s current address,\nwith the immigration court. Both functions are now performed by ICE. In\nmost cases, the immigration court then has the responsibility to send the\nprecise hearing information to the alien’s address on file. See 8 C.F.R.\n§ 1003.18. Because ICE is now responsible for providing the alien’s address to\nthe immigration court when it files the NTA, we read 8 U.S.C. §1229, through\nthe lens of 6 U.S.C. § 557, to require the alien to provide a change of address\nto ICE at least until the NTA has been filed with the immigration court. 3 As\nsuch, by notifying ICE of her change of address before it filed the NTA with the\nimmigration court, Fuentes-Pena satisfied her statutory obligation to provide\nnotice of her change of address, and her failure to attend her removal hearing\nis excused. The BIA abused its discretion by refusing to reopen removal\nproceedings against her.\n IV.\n In sum, we hold that the BIA abused its discretion in refusing to reopen\nFuentes-Pena’s removal proceedings. Under these circumstances, Fuentes-\nPena satisfied her obligation to provide her new address to the “Attorney\nGeneral” by notifying ICE of her change of address. We VACATE the decision\nof the BIA and REMAND the case for further proceedings not inconsistent with\nthis opinion.\n\n\n\n\n 3 We express no opinion on an alien’s statutory obligations after the NTA has been\nfiled with the immigration court.\n 7\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Norma Yanet FUENTES-PENA; Erik Aristedes Vijil-Fuentes; Judith Daniela Vijil-Fuentes, Petitioners v. William P. BARR, U. S. Attorney General, Respondent\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-06\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 17-60637 Document: 00514860849 Page: 1 Date Filed: 03/06/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n March 6, 2019\\n No. 17-60637 Lyle W. Cayce\\n Clerk\\n\\nNORMA YANET FUENTES-PENA; ERIK ARISTEDES VIJIL-FUENTES;\\nJUDITH DANIELA VIJIL-FUENTES,\\n\\n Petitioners\\n\\nv.\\n\\nWILLIAM P. BARR, U. S. ATTORNEY GENERAL,\\n\\n Respondent\\n\\n\\n\\n\\n Petition for Review of an Order of the\\n Board of Immigration Appeals\\n\\n\\nBefore JOLLY, DENNIS, and HIGGINSON, Circuit Judges.\\nE. GRADY JOLLY, Circuit Judge:\\n Petitioner Norma Yanet Fuentes-Pena and her two minor children seek\\nreview of a final order by the Board of Immigration Appeals (BIA) denying her\\nmotion to reopen removal proceedings. She contends that the BIA abused its\\ndiscretion by refusing to reopen her removal proceedings because she never\\nreceived notice of her removal hearing. The government argues that Fuentes-\\nPena did not receive notice because she moved without informing the\\nimmigration court of her new address. Because Fuentes-Pena updated her\\naddress with Immigration and Customs Enforcement (ICE), we VACATE the\\norder of the BIA and REMAND for further proceedings.\\n\\f Case: 17-60637 Document: 00514860849 Page: 2 Date Filed: 03/06/2019\\n\\n\\n\\n No. 17-60637\\n I.\\n Norma Yanet Fuentes-Pena is a native and citizen of El Salvador who\\nentered the United States near Hidalgo, Texas, with her two children. Upon\\nher release from immigration detention, the Department of Homeland Security\\n(DHS) personally served Fuentes-Pena with a Notice to Appear (NTA),\\ncharging her with removability as an alien present in the United States\\nwithout being admitted or paroled. The NTA advised Fuentes-Pena that she\\nwas to appear before an immigration judge (IJ) in Miami, Florida on a date\\nand at a time to be later determined. Fuentes-Pena’s children were “riders” on\\nher immigration case. Accompanying the NTA was a notice from ICE, an\\nagency within DHS, stating that the NTA would “be filed with the Office of the\\nImmigration Judge with jurisdiction over the residential address [she]\\nprovided to ICE upon [her] release.”\\n Upon release from DHS custody, Fuentes-Pena, as required by law,\\nprovided an address for further communication, which was in Duncanville,\\nTexas. Fuentes-Pena received an EOIR-33 form and acknowledged that she\\nneeded to use that form to inform the “Office of the Immigration Judge” and\\nICE of any change in her address within five days. The NTA also stated: “If\\nyou do not submit EOIR-33 and do not otherwise provide an address at which\\nyou may be reached during proceedings, then the Government shall not be\\nrequired to provide you with written notice of your hearing.” Several months\\nlater, in March 2016, Fuentes-Pena moved to Massachusetts and informed\\nonly ICE of her change of address. On June 1, 2016, the NTA, furnished by\\nICE, was stamped as received by the immigration court in Dallas, Texas. On\\nJune 7, 2016, a hearing notice from the immigration court was mailed to the\\nDuncanville, Texas address that she had provided when she was released,\\nadvising Fuentes-Pena that a hearing was scheduled for June 20, 2016, in\\nDallas, Texas. Fuentes-Pena, however, failed to appear for the scheduled\\n 2\\n\\f Case: 17-60637 Document: 00514860849 Page: 3 Date Filed: 03/06/2019\\n\\n\\n\\n No. 17-60637\\nhearing. Consequently, the IJ found her removable as charged in the NTA\\nand, in absentia, ordered her removed to El Salvador. The IJ’s in absentia\\nremoval order was also mailed to Fuentes-Pena at the Duncanville, Texas\\naddress.\\n On November 15, 2016, Fuentes-Pena filed a motion to reopen and\\nrescind the in absentia order of removal. In her motion, Fuentes-Pena argued\\nthat, although she had failed to apprise the immigration court of the change in\\nher address, she had met her obligation to provide a current address by giving\\nher new address to the ICE office in Massachusetts. Alternatively, Fuentes-\\nPena argued that exceptional circumstances warranted the reopening of her\\nremoval proceedings because she “did everything she could to remain apprised\\nof her court hearing and her failure to appear was beyond her control.” Finally,\\nFuentes-Pena requested that the IJ reopen her case sua sponte if it found that\\nreopening was not warranted on any other grounds.\\n The IJ issued a written decision denying Fuentes-Pena’s motion to\\nreopen. The IJ found that it was not required to provide written notice of the\\nhearing. While Fuentes-Pena had apprised ICE of her change in address, she\\ndid not meet her obligation to inform the immigration court, despite the fact\\nthat the NTA specified this obligation. Further, the IJ found that the NTA had\\nprovided Fuentes-Pena with “constructive” notice of the hearing. The IJ\\ndetermined that Fuentes-Pena did not show exceptional circumstances, such\\nas “battery, extreme cruelty, or serious illness,” and it declined to reopen her\\ncase sua sponte because it did not present an “exceptional situation.”\\n Fuentes-Pena appealed the IJ’s decision. On appeal, Fuentes-Pena\\nreiterated her earlier arguments. The BIA issued an order dismissing\\nFuentes-Pena’s appeal. The BIA found that the hearing notice was properly\\nmailed to Fuentes-Pena’s address of record. Further, the BIA noted that the\\nNTA informed Fuentes-Pena of her obligation to update her address and the\\n 3\\n\\f Case: 17-60637 Document: 00514860849 Page: 4 Date Filed: 03/06/2019\\n\\n\\n\\n No. 17-60637\\nconsequences of missing her hearing. Finally, the BIA found that Fuentes-\\nPena did not establish exceptional circumstances based on the “totality of the\\ncircumstances” and that the IJ did not err by refusing to reopen her case sua\\nsponte. Fuentes-Pena filed a timely petition for review. See 8 U.S.C.\\n§ 1252(b)(1).\\n II.\\n When considering a petition for review, we have the authority to review\\nonly the BIA’s decision, not the IJ’s decision, unless the IJ’s decision has some\\nimpact on the BIA’s decision. See Mikhael v. INS, 115 F.3d 299, 302 (5th Cir.\\n1997). Here, the BIA referenced the IJ’s decision and found that the IJ\\ncommitted no error. We review the denial of a motion to reopen under a highly\\ndeferential abuse-of-discretion standard. See Zhao v. Gonzales, 404 F.3d 295,\\n303 (5th Cir. 2005). Motions to reopen immigration proceedings are disfavored\\nbecause “as a general matter, every delay works to the advantage of the\\ndeportable alien who wishes merely to remain in the United States.” INS v.\\nDoherty, 502 U.S. 314, 323 (1992). On petition for review of a BIA decision, we\\nreview factual findings for substantial evidence, meaning that we will accept\\nthe BIA’s factual findings “unless the evidence is so compelling that no\\nreasonable fact finder could fail to find otherwise.” Lopez-Gomez v. Ashcroft,\\n263 F.3d 442, 444 (5th Cir. 2001) (internal citation and quotation marks\\nomitted). We review constitutional claims and questions of law de novo. See\\nSattani v. Holder, 749 F.3d 368, 370 (5th Cir. 2014).\\n III.\\n In her petition for review, Fuentes-Pena argues that the BIA abused its\\ndiscretion by affirming the IJ’s order denying her motion to reopen. 1 We agree.\\n\\n\\n\\n 1Because we find that the BIA abused its discretion by affirming the IJ’s order, we do\\nnot reach Fuentes-Pena’s second argument, that the immigration court violated her right to\\n 4\\n\\f Case: 17-60637 Document: 00514860849 Page: 5 Date Filed: 03/06/2019\\n\\n\\n\\n No. 17-60637\\n An alien must be provided with written notice of the time and place at\\nwhich a removal hearing will be held. 8 U.S.C. § 1229(a)(1)(G)(i). Service of\\nthe notice may be by mail. Id. § 1229(c); see also 8 C.F.R. § 1003.13 (allowing\\nservice by “regular mail”). Any alien who fails to appear at a deportation\\nhearing after written notice or fails to provide an address shall be ordered\\nremoved in absentia if DHS establishes by clear, unequivocal, and convincing\\nevidence that the alien is removable and that the alien was provided with the\\nwritten notice required under 8 U.S.C. § 1229(a)(1)–(2). See id.\\n§ 1229a(b)(5)(A). “The written notice by the Attorney General shall be\\nconsidered sufficient . . . if provided at the most recent address provided under\\nsection 1229(a)(1)(F) of this title.” Id. § 1229a(b)(5)(A). Section 1229(a)(1)(F),\\nin turn, requires that an “alien must provide the Attorney General\\nimmediately with a written record of any change of the alien’s address.” Id. §\\n1229(a)(1)(F)(ii).\\n Written notice of the deportation hearing is not required if the alien fails\\nto satisfy the requirement in 8 U.S.C. § 1229(a)(1)(F) to provide an address\\nwhere “the alien may be contacted respecting [removal] proceedings.” See id.\\n§ 1229(a)(2)(B). A deportation order may be rescinded through a motion to\\nreopen if the alien demonstrates that they “did not receive notice in accordance\\nwith paragraph (1) or (2) of section 1229(a).” Id. § 1229a(b)(5)(C)(ii). On a\\nmotion to reopen, it is the alien’s burden to demonstrate that they did not\\nreceive notice in accordance with section 1229(a). See id. We have held that\\nan alien’s failure to receive actual notice of a removal hearing due to their\\nneglect of their obligation to inform the immigration court of their current\\n\\n\\n\\n\\ndue process by failing to properly notify her of the hearing when it sent notice of the hearing\\nto the address she provided ICE upon her release.\\n 5\\n\\f Case: 17-60637 Document: 00514860849 Page: 6 Date Filed: 03/06/2019\\n\\n\\n\\n No. 17-60637\\naddress does not mean that the alien did not receive the statutorily required\\nnotice. Gomez-Palacios v. Holder, 560 F.3d 354, 360–61 (5th Cir. 2009). 2\\n Nonetheless, we find that Gomez-Palacios is distinguishable. Unlike the\\nalien in Gomez-Palacios, Fuentes-Pena notified ICE of her change of address\\nbefore ICE filed the NTA with the immigration court. This means that the\\ngovernment cannot rely on 8 CFR § 1003.15(d), which requires aliens to notify\\nthe immigration court of any change of address only after the NTA has been\\nfiled by the government.\\n The government, however, instead attempts to support the BIA’s\\ndecision by pointing directly to the statute. 8 U.S.C. § 1229(a)(1)(F) required\\nFuentes-Pena to “provide the Attorney General immediately with a written\\nrecord of any change” to her address. We must determine whether Fuentes-\\nPena satisfied this obligation by notifying ICE of her new address.\\n Section 1229 was enacted before the creation of the Department of\\nHomeland Security. Prior to that statutory change, removal proceedings were\\nprosecuted by the Immigration and Naturalization Service (INS), which indeed\\nwas an agency within the Department of Justice (DOJ). But when the DHS\\nwas created, the INS was dissolved and most of its functions were moved out\\nof the DOJ and into the DHS. 6 U.S.C. § 557 facilitated this transition by\\nproviding that:\\n With respect to any function transferred by or under this chapter\\n (including under a reorganization plan that becomes effective\\n under section 542 of this title) and exercised on or after the\\n effective date of this chapter, reference in any other Federal law to\\n\\n\\n 2 In Pereira v. Sessions, handed down after the initial briefing was concluded in this\\ncase, the Supreme Court addressed a “narrow question” regarding the effect of an NTA that\\ndoes not specify the time or place of the removal hearing on the trigger for the “stop-time\\nrule” for the purposes of a cancellation of removal. 138 S.Ct. 2105, 2110 (2018). We recently\\nheld that this decision does not affect our holding in Gomez-Palacios. See Mauricio-Benitez\\nv. Sessions, 908 F.3d 144, 148 n.1 (5th Cir. 2018).\\n\\n 6\\n\\f Case: 17-60637 Document: 00514860849 Page: 7 Date Filed: 03/06/2019\\n\\n\\n\\n No. 17-60637\\n any department, commission, or agency or any officer or office the\\n functions of which are so transferred shall be deemed to refer to\\n the Secretary, other official, or component of the Department to\\n which such function is so transferred.\\nThe former INS was responsible for providing aliens with the statutorily\\nrequired NTA and for filing the NTA, containing the alien’s current address,\\nwith the immigration court. Both functions are now performed by ICE. In\\nmost cases, the immigration court then has the responsibility to send the\\nprecise hearing information to the alien’s address on file. See 8 C.F.R.\\n§ 1003.18. Because ICE is now responsible for providing the alien’s address to\\nthe immigration court when it files the NTA, we read 8 U.S.C. §1229, through\\nthe lens of 6 U.S.C. § 557, to require the alien to provide a change of address\\nto ICE at least until the NTA has been filed with the immigration court. 3 As\\nsuch, by notifying ICE of her change of address before it filed the NTA with the\\nimmigration court, Fuentes-Pena satisfied her statutory obligation to provide\\nnotice of her change of address, and her failure to attend her removal hearing\\nis excused. The BIA abused its discretion by refusing to reopen removal\\nproceedings against her.\\n IV.\\n In sum, we hold that the BIA abused its discretion in refusing to reopen\\nFuentes-Pena’s removal proceedings. Under these circumstances, Fuentes-\\nPena satisfied her obligation to provide her new address to the “Attorney\\nGeneral” by notifying ICE of her change of address. We VACATE the decision\\nof the BIA and REMAND the case for further proceedings not inconsistent with\\nthis opinion.\\n\\n\\n\\n\\n 3 We express no opinion on an alien’s statutory obligations after the NTA has been\\nfiled with the immigration court.\\n 7\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1076,"cells":{"id":{"kind":"number","value":4597542,"string":"4,597,542"},"name":{"kind":"string","value":"JATERA CORPORATION; Esther Randle Moore, Plaintiffs-Appellants v. US BANK NATIONAL ASSOCIATION, AS TRUSTEE, in Trust FOR the REGISTERED HOLDERS OF CITIGROUP MORTGAGE LOAN TRUST, Asset-Backed Pass-Through Certificates, Series 2005-HE3; Select Portfolio Servicing, Incorporated, Defendants-Appellees"},"name_abbreviation":{"kind":"string","value":"Jatera Corporation v. US Bank National Asso"},"decision_date":{"kind":"string","value":"2019-03-06"},"docket_number":{"kind":"string","value":"18-10248"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before SMITH, BARKSDALE, and HO, Circuit Judges.\", \"parties\": \"\", \"opinions\": [{\"author\": \"RHESA HAWKINS BARKSDALE, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 18-10248 Document: 00514861432 Page: 1 Date Filed: 03/06/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n No. 18-10248 March 6, 2019\\n Lyle W. Cayce\\nJATERA CORPORATION; ESTHER RANDLE MOORE, Clerk\\n\\n\\n Plaintiffs - Appellants\\n\\nv.\\n\\nUS BANK NATIONAL ASSOCIATION, As Trustee, in Trust for the\\nRegistered Holders of Citigroup Mortgage Loan Trust, Asset-Backed Pass-\\nThrough Certificates, Series 2005-HE3; SELECT PORTFOLIO SERVICING,\\nINCORPORATED,\\n\\n Defendants - Appellees\\n\\n\\n\\n\\n Appeal from the United States District Court\\n for the Northern District of Texas\\n\\n\\nBefore SMITH, BARKSDALE, and HO, Circuit Judges.\\nRHESA HAWKINS BARKSDALE, Circuit Judge:\\n At issue in this diversity action is whether Texas law provides a\\ndetrimental-reliance exception to a lender’s right to unilaterally withdraw a\\nnotice of acceleration; and, if so, whether Jatera Corporation and Esther\\nRandle Moore detrimentally relied on the notice of acceleration by U.S. Bank\\nNational Association (Bank) and Select Portfolio Servicing, Inc. (SPS).\\nAppellants challenge the district court’s, on cross-motions for summary\\njudgment, denying Appellants’ motion and granting Appellees’. AFFIRMED.\\n\\f Case: 18-10248 Document: 00514861432 Page: 2 Date Filed: 03/06/2019\\n\\n\\n\\n No. 18-10248\\n I.\\n In 2005, Moore and her husband purchased a house located in Dallas,\\nTexas (the property), by signing a Texas home equity fixed/adjustable rate note\\nin the amount of $99,200, secured by a Texas home equity security instrument.\\nThrough a series of transfers and assignments, the Bank became the owner\\nand holder of the note and security interest.\\n After her husband died in April 2008, all interest in the property was\\ntransferred to Moore, who soon defaulted on her mortgage payments. In March\\n2010, the Bank’s then loan servicer notified Moore of its intent to accelerate\\nthe note (acceleration notice), demanding full payment of the debt\\n($116,575.80).\\n After the Bank filed suit in state court in 2011 to obtain a court order\\npermitting foreclosure on the property, Moore signed an agreed final judgment\\nin November 2011, consenting to foreclosure. In January 2012, Moore vacated\\nthe property and signed a one-year lease for an apartment.\\n The Bank’s new loan servicer, SPS, sent a new notice of default to Moore\\nin November 2012, informing her: she could cure her default by making a\\npayment of $38,343.99; but, if payment was not received by December 2012,\\nthe note would be re-accelerated.\\n In March 2015, Moore conveyed her interest in the property to Scojo\\nSolutions, LLC, through a special warranty deed. One month later, Scojo\\ntransferred its interest in the property to Jatera Corporation.\\n After SPS re-initiated the foreclosure proceedings originally pursued by\\nthe Bank, Jatera filed this action against the Bank and SPS in state court,\\nseeking a judgment declaring the lien on the property void because Appellees\\nfailed to initiate foreclosure proceedings within the four-year statute of\\nlimitations. In response, Appellees removed this action to federal court on the\\nbasis of diversity jurisdiction.\\n 2\\n\\f Case: 18-10248 Document: 00514861432 Page: 3 Date Filed: 03/06/2019\\n\\n\\n\\n No. 18-10248\\n In district court, Jatera amended its complaint, asserting that Moore’s\\ndetrimental reliance on the acceleration notice prevented Appellees from\\nabandoning the acceleration in November 2012. Moore was joined as a\\nplaintiff. She filed a complaint seeking a judgment declaring the lien on the\\nproperty void, and/or quieting title in Jatera’s name (also on grounds of her\\ndetrimental reliance).\\n The parties filed cross-motions for summary judgment on all claims.\\nRegarding Moore’s claims, the district court held Moore no longer retained an\\ninterest in the property, and, therefore, lacked standing. Concerning Jatera’s\\nclaims, the court noted the uncertainty surrounding the detrimental-reliance\\nexception under Texas law, but held that, in any event, detrimental reliance\\nruns to the benefit of the party asserting it, and Jatera had failed to show it\\ndetrimentally relied on the acceleration notice. Accordingly, the court denied\\nAppellants’ motion and granted Appellees’.\\n II.\\n Appellants contend the district court erred in denying their summary-\\njudgment motion and in granting Appellees’. Accordingly, Appellants request\\njudgment’s being rendered in their favor; alternatively, that this case be\\nremanded to district court.\\n The district court’s “grant[] and denial[] of summary judgment [is\\nreviewed] de novo”. Century Surety Co. v. Seidel, 893 F.3d 328, 332 (5th Cir.\\n2018) (quotations and citation omitted). Summary judgment is proper “if the\\nmovant shows that there is no genuine dispute as to any material fact and the\\nmovant is entitled to judgment as a matter of law”. Fed. R. Civ. P. 56(a). “A\\ngenuine dispute of material fact exists if the evidence is such that a reasonable\\njury could return a verdict for the nonmoving party. However, [a] mere\\nscintilla of evidence will not preclude granting of a motion for summary\\njudgment.” Bitterroot Holdings, L.L.C. v. MTGLQ Inv’rs, L.P., 648 F. App’x\\n 3\\n\\f Case: 18-10248 Document: 00514861432 Page: 4 Date Filed: 03/06/2019\\n\\n\\n\\n No. 18-10248\\n414, 417 (5th Cir. 2016) (alteration in original) (internal quotations and\\ncitations omitted).\\n “When parties file cross-motions for summary judgment, we review each\\nparty’s motion independently, viewing the evidence and inferences in the light\\nmost favorable to the nonmoving party.” Cooley v. Hous. Auth. of Slidell, 747\\nF.3d 295, 298 (5th Cir. 2014) (internal quotations and citation omitted).\\n A.\\n Texas substantive law applies to this diversity-jurisdiction case. Erie\\nR.R. v. Tompkins, 304 U.S. 64, 78–79 (1938). In instances where the State’s\\nhighest court has not spoken on the direct question, federal courts are\\nrequired to make an “Erie guess and determine, in [their] best judgment how\\n[the State’s highest court] would resolve the issue if presented with the same\\ncase”. Temple v. McCall, 720 F.3d 301, 307 (5th Cir. 2013) (first alteration in\\noriginal) (internal quotations and citation omitted). In doing so, our court\\n“defer[s] to intermediate state appellate court decisions, unless convinced by\\nother persuasive data that the highest court of the state would decide\\notherwise”. Mem’l Hermann Healthcare Sys., Inc. v. Eurocopter Deutschland,\\nGMBH, 524 F.3d 676, 678 (5th Cir. 2008) (internal quotations and citation\\nomitted).\\n 1.\\n Under Texas law, “[a] person must bring suit for . . . the foreclosure of a\\nreal property lien not later than four years after the day the cause of action\\naccrues”. Tex. Civ. Prac. & Rem. Code Ann. § 16.035(a). If foreclosure does\\nnot occur within this limitations period, “the real property lien and a power of\\nsale to enforce the . . . lien become void”. Id. § 16.035(d). If the note secured\\nby the property contains an optional acceleration clause, “the action accrues\\nonly when the holder actually exercises its option to accelerate”. Bitterroot,\\n\\n\\n 4\\n\\f Case: 18-10248 Document: 00514861432 Page: 5 Date Filed: 03/06/2019\\n\\n\\n\\n No. 18-10248\\n648 F. App’x at 418 (quoting Holy Cross Church of God in Christ v. Wolf, 44\\nS.W.3d 562, 566 (Tex. 2001)).\\n The acceleration may be abandoned, either by the lender’s unilateral\\nactions or by agreement, thereby suspending the limitations period until the\\nlender exercises its option to re-accelerate the note. Boren v. U.S. Nat’l Bank\\nAss’n, 807 F.3d 99, 106 (5th Cir. 2015); Holy Cross, 44 S.W.3d at 566–67.\\n“[T]he request for payment of less than the full obligation—after initially\\naccelerating the entire obligation—[is] an unequivocal expression of the\\nbank’s intent to abandon or waive its initial acceleration”. Martin v. Fed. Nat’l\\nMortg. Ass’n, 814 F.3d 315, 318 (5th Cir. 2016).\\n Accordingly, the parties do not dispute the November 2012 notice of\\ndefault, which requested less than the full debt, could have constituted an\\nabandonment of the 2010 acceleration. Instead, Appellants assert the Bank\\nwas estopped from abandoning the 2010 acceleration due to Moore’s\\ndetrimental reliance on it.\\n 2.\\n First, the parties dispute whether, under Texas law, a detrimental-\\nreliance exception exists to a lender’s right to unilaterally withdraw its\\nexercise of an option to accelerate. No Texas court has ever held detrimental\\nreliance is an exception.\\n Discussion about a detrimental-reliance exception first appeared in\\n1998 in Swoboda v. Wilshire Credit Corp., in which a Texas intermediate\\nappellate court stated in dicta: “Even if a creditor exercises the option to\\naccelerate and makes a declaration to that effect, the election to accelerate can\\nbe revoked or withdrawn at any time, so long as the debtor has not\\ndetrimentally relied on the acceleration”. 975 S.W.2d 770, 776–77 (Tex. App.\\n1998), disapproved of on other grounds by Holy Cross, 44 S.W.3d 562. For this\\ndetrimental-reliance proposition, the Texas appellate court cited two non-\\n 5\\n\\f Case: 18-10248 Document: 00514861432 Page: 6 Date Filed: 03/06/2019\\n\\n\\n\\n No. 18-10248\\nTexas cases: In re Adu-Kofi, 94 B.R. 14, 15 (Bankr. D. R.I. 1988); and Golden\\nv. Ramapo Improvement Corp., 78 A.D.2d 648 (N.Y. App. Div. 1980).\\n Since Swoboda, numerous courts have cited this language, also in dicta.\\nSee, e.g., Boren, 807 F.3d at 105; Nunnery v. Ocwen Loan Servicing, L.L.C.,\\n641 F. App’x 430, 433 (5th Cir. 2016); Justice v. Wells Fargo Bank Nat’l Ass’n,\\n674 F. App’x 330, 333 (5th Cir. 2016); Nationstar Mortgage, LLC v. Landers,\\nNo. 12-17-00047-CV, 2018 WL 1737013, at *6 (Tex. App. 11 Apr. 2018);\\nGraham v. LNV Corp., No. 03-16-00235-CV, 2016 WL 6407306, at *3 (Tex.\\nApp. 26 Oct. 2016).\\n Recently, however, federal and Texas state courts have expressed\\ndoubts about whether the exception exists. See, e.g., Graham, 2016 WL\\n6407306, at *4 & n.3 (“Texas courts have not resolved the question of whether\\na note holder can unilaterally rescind acceleration . . . despite the debtor’s\\ndetrimental reliance on the acceleration”.); Bitterroot, No. 5:14-CV-862-DAE,\\n2015 WL 6442622, at *7 (W.D. Tex. 23 Oct. 2015) (“Given that Swoboda’s\\ndetrimental reliance rule was derived from authority outside of Texas,\\nhowever, the Court agrees that it is less than clear that the Texas Supreme\\nCourt would adopt the same rule.”), aff’d 648 F. App’x 414 (5th Cir. 2016).\\n Along that line, a very recent unpublished opinion by our court noted:\\n“According to Texas intermediate appellate courts, the holder of a note may\\nnot unilaterally abandon acceleration if the borrower objects to abandonment\\nor has detrimentally relied on the acceleration”. Sims v. RoundPoint Mortg.\\nServicing Corp., --- F. App’x ---, 2019 WL 360069, at *3 (5th Cir. 28 Jan. 2019)\\n(per curiam) (citing Boren, 807 F.3d at 105); see also 5th Cir. R. 47.5.4\\n(unpublished opinions on or after 1 January 1996 are not precedential except\\nin certain instances not applicable in Sims).\\n This opinion did not discuss the uncertainty surrounding the\\ndetrimental-reliance exception, nor did it hold a detrimental-reliance\\n 6\\n\\f Case: 18-10248 Document: 00514861432 Page: 7 Date Filed: 03/06/2019\\n\\n\\n\\n No. 18-10248\\nexception exists under Texas law. Id. Instead, it joins the line of cases that\\nhave cited this purported exception in dicta. Ultimately, our court held the\\nfiling of bankruptcy, in that case, was not proof of detrimental reliance on the\\nacceleration notice. Id. at *4.\\n More to the issue at hand, the Texas legislature in 2015—almost 20\\nyears after Swoboda was decided—enacted Texas Civil Practice and Remedies\\nCode § 16.038; subsection (a) states: “If the maturity date of a series of notes\\nor obligations or a note or obligation payable in installments is accelerated,\\nand the accelerated maturity date is rescinded or waived . . . before the\\nlimitations period expires, the acceleration is deemed rescinded and waived\\nand the note, obligation, or series of notes or obligations shall be governed . . .\\nas if no acceleration had occurred.” This statute provides no exceptions to a\\nlender’s right to unilaterally withdraw the acceleration.\\n “A statute is presumed to have been enacted by the legislature with\\ncomplete knowledge of the existing law and with reference to it.” Acker v. Tex.\\nWater Comm’n, 790 S.W.2d 299, 301 (Tex. 1990) (citation omitted). “Enforcing\\nthe law as written is a court’s safest refuge in matters of statutory\\nconstruction, and we should always refrain from rewriting text that\\nlawmakers chose . . . .” Entergy Gulf States, Inc. v. Summers, 282 S.W.3d 433,\\n443 (Tex. 2009) (citing Simmons v. Arnim, 220 S.W. 66, 70 (1920) (“Courts\\nmust take statutes as they find them.”)).\\n The Texas legislature, presumably with knowledge of the case law,\\nchose not to include in the statute any exception to the lender’s right to\\nunilaterally withdraw an acceleration notice. Therefore, it is unlikely the\\nTexas Supreme Court would be willing to read such language into the statute,\\nespecially considering the language ultimately comes from dicta citing\\nauthority from outside of Texas.\\n\\n\\n 7\\n\\f Case: 18-10248 Document: 00514861432 Page: 8 Date Filed: 03/06/2019\\n\\n\\n\\n No. 18-10248\\n Accordingly, we hold detrimental reliance is not an exception to the\\nlender’s right to unilaterally withdraw an acceleration notice under Texas\\nlaw.\\n B.\\n The other issue on appeal concerned whether, for the claimed exception,\\nthe requisite detrimental reliance existed. The district court concluded:\\nJatera did not suffer such reliance; and Moore no longer retained an interest\\nin the property, and, therefore, lacked standing. Jatera asserts Moore’s\\npurported reliance was assigned to it through the earlier-described special\\nwarranty deed.\\n But, as held above, the claimed detrimental-reliance exception does not\\nexist under Texas law. Therefore, we need not reach whether there was such\\nreliance, including whether Jatera was assigned Moore’s detrimental-reliance\\nclaim, or whether Moore suffered such reliance.\\n III.\\n For the foregoing reasons, the judgment is AFFIRMED.\\n\\n\\n\\n\\n 8\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4374795/\", \"author_raw\": \"RHESA HAWKINS BARKSDALE, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"SMITH"},"judge2":{"kind":"string","value":"BARKSDALE"},"judge3":{"kind":"string","value":"HO"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"SMITH\": \", Circuit\", \"BARKSDALE\": \", Circuit\", \"HO\": \", Circuit\"}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4597542/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: JATERA CORPORATION; Esther Randle Moore, Plaintiffs-Appellants v. US BANK NATIONAL ASSOCIATION, AS TRUSTEE, in Trust FOR the REGISTERED HOLDERS OF CITIGROUP MORTGAGE LOAN TRUST, Asset-Backed Pass-Through Certificates, Series 2005-HE3; Select Portfolio Servicing, Incorporated, Defendants-Appellees\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-06\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 18-10248 Document: 00514861432 Page: 1 Date Filed: 03/06/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\n United States Court of Appeals\n Fifth Circuit\n\n FILED\n No. 18-10248 March 6, 2019\n Lyle W. Cayce\nJATERA CORPORATION; ESTHER RANDLE MOORE, Clerk\n\n\n Plaintiffs - Appellants\n\nv.\n\nUS BANK NATIONAL ASSOCIATION, As Trustee, in Trust for the\nRegistered Holders of Citigroup Mortgage Loan Trust, Asset-Backed Pass-\nThrough Certificates, Series 2005-HE3; SELECT PORTFOLIO SERVICING,\nINCORPORATED,\n\n Defendants - Appellees\n\n\n\n\n Appeal from the United States District Court\n for the Northern District of Texas\n\n\nBefore SMITH, BARKSDALE, and HO, Circuit Judges.\nRHESA HAWKINS BARKSDALE, Circuit Judge:\n At issue in this diversity action is whether Texas law provides a\ndetrimental-reliance exception to a lender’s right to unilaterally withdraw a\nnotice of acceleration; and, if so, whether Jatera Corporation and Esther\nRandle Moore detrimentally relied on the notice of acceleration by U.S. Bank\nNational Association (Bank) and Select Portfolio Servicing, Inc. (SPS).\nAppellants challenge the district court’s, on cross-motions for summary\njudgment, denying Appellants’ motion and granting Appellees’. AFFIRMED.\n\f Case: 18-10248 Document: 00514861432 Page: 2 Date Filed: 03/06/2019\n\n\n\n No. 18-10248\n I.\n In 2005, Moore and her husband purchased a house located in Dallas,\nTexas (the property), by signing a Texas home equity fixed/adjustable rate note\nin the amount of $99,200, secured by a Texas home equity security instrument.\nThrough a series of transfers and assignments, the Bank became the owner\nand holder of the note and security interest.\n After her husband died in April 2008, all interest in the property was\ntransferred to Moore, who soon defaulted on her mortgage payments. In March\n2010, the Bank’s then loan servicer notified Moore of its intent to accelerate\nthe note (acceleration notice), demanding full payment of the debt\n($116,575.80).\n After the Bank filed suit in state court in 2011 to obtain a court order\npermitting foreclosure on the property, Moore signed an agreed final judgment\nin November 2011, consenting to foreclosure. In January 2012, Moore vacated\nthe property and signed a one-year lease for an apartment.\n The Bank’s new loan servicer, SPS, sent a new notice of default to Moore\nin November 2012, informing her: she could cure her default by making a\npayment of $38,343.99; but, if payment was not received by December 2012,\nthe note would be re-accelerated.\n In March 2015, Moore conveyed her interest in the property to Scojo\nSolutions, LLC, through a special warranty deed. One month later, Scojo\ntransferred its interest in the property to Jatera Corporation.\n After SPS re-initiated the foreclosure proceedings originally pursued by\nthe Bank, Jatera filed this action against the Bank and SPS in state court,\nseeking a judgment declaring the lien on the property void because Appellees\nfailed to initiate foreclosure proceedings within the four-year statute of\nlimitations. In response, Appellees removed this action to federal court on the\nbasis of diversity jurisdiction.\n 2\n\f Case: 18-10248 Document: 00514861432 Page: 3 Date Filed: 03/06/2019\n\n\n\n No. 18-10248\n In district court, Jatera amended its complaint, asserting that Moore’s\ndetrimental reliance on the acceleration notice prevented Appellees from\nabandoning the acceleration in November 2012. Moore was joined as a\nplaintiff. She filed a complaint seeking a judgment declaring the lien on the\nproperty void, and/or quieting title in Jatera’s name (also on grounds of her\ndetrimental reliance).\n The parties filed cross-motions for summary judgment on all claims.\nRegarding Moore’s claims, the district court held Moore no longer retained an\ninterest in the property, and, therefore, lacked standing. Concerning Jatera’s\nclaims, the court noted the uncertainty surrounding the detrimental-reliance\nexception under Texas law, but held that, in any event, detrimental reliance\nruns to the benefit of the party asserting it, and Jatera had failed to show it\ndetrimentally relied on the acceleration notice. Accordingly, the court denied\nAppellants’ motion and granted Appellees’.\n II.\n Appellants contend the district court erred in denying their summary-\njudgment motion and in granting Appellees’. Accordingly, Appellants request\njudgment’s being rendered in their favor; alternatively, that this case be\nremanded to district court.\n The district court’s “grant[] and denial[] of summary judgment [is\nreviewed] de novo”. Century Surety Co. v. Seidel, 893 F.3d 328, 332 (5th Cir.\n2018) (quotations and citation omitted). Summary judgment is proper “if the\nmovant shows that there is no genuine dispute as to any material fact and the\nmovant is entitled to judgment as a matter of law”. Fed. R. Civ. P. 56(a). “A\ngenuine dispute of material fact exists if the evidence is such that a reasonable\njury could return a verdict for the nonmoving party. However, [a] mere\nscintilla of evidence will not preclude granting of a motion for summary\njudgment.” Bitterroot Holdings, L.L.C. v. MTGLQ Inv’rs, L.P., 648 F. App’x\n 3\n\f Case: 18-10248 Document: 00514861432 Page: 4 Date Filed: 03/06/2019\n\n\n\n No. 18-10248\n414, 417 (5th Cir. 2016) (alteration in original) (internal quotations and\ncitations omitted).\n “When parties file cross-motions for summary judgment, we review each\nparty’s motion independently, viewing the evidence and inferences in the light\nmost favorable to the nonmoving party.” Cooley v. Hous. Auth. of Slidell, 747\nF.3d 295, 298 (5th Cir. 2014) (internal quotations and citation omitted).\n A.\n Texas substantive law applies to this diversity-jurisdiction case. Erie\nR.R. v. Tompkins, 304 U.S. 64, 78–79 (1938). In instances where the State’s\nhighest court has not spoken on the direct question, federal courts are\nrequired to make an “Erie guess and determine, in [their] best judgment how\n[the State’s highest court] would resolve the issue if presented with the same\ncase”. Temple v. McCall, 720 F.3d 301, 307 (5th Cir. 2013) (first alteration in\noriginal) (internal quotations and citation omitted). In doing so, our court\n“defer[s] to intermediate state appellate court decisions, unless convinced by\nother persuasive data that the highest court of the state would decide\notherwise”. Mem’l Hermann Healthcare Sys., Inc. v. Eurocopter Deutschland,\nGMBH, 524 F.3d 676, 678 (5th Cir. 2008) (internal quotations and citation\nomitted).\n 1.\n Under Texas law, “[a] person must bring suit for . . . the foreclosure of a\nreal property lien not later than four years after the day the cause of action\naccrues”. Tex. Civ. Prac. & Rem. Code Ann. § 16.035(a). If foreclosure does\nnot occur within this limitations period, “the real property lien and a power of\nsale to enforce the . . . lien become void”. Id. § 16.035(d). If the note secured\nby the property contains an optional acceleration clause, “the action accrues\nonly when the holder actually exercises its option to accelerate”. Bitterroot,\n\n\n 4\n\f Case: 18-10248 Document: 00514861432 Page: 5 Date Filed: 03/06/2019\n\n\n\n No. 18-10248\n648 F. App’x at 418 (quoting Holy Cross Church of God in Christ v. Wolf, 44\nS.W.3d 562, 566 (Tex. 2001)).\n The acceleration may be abandoned, either by the lender’s unilateral\nactions or by agreement, thereby suspending the limitations period until the\nlender exercises its option to re-accelerate the note. Boren v. U.S. Nat’l Bank\nAss’n, 807 F.3d 99, 106 (5th Cir. 2015); Holy Cross, 44 S.W.3d at 566–67.\n“[T]he request for payment of less than the full obligation—after initially\naccelerating the entire obligation—[is] an unequivocal expression of the\nbank’s intent to abandon or waive its initial acceleration”. Martin v. Fed. Nat’l\nMortg. Ass’n, 814 F.3d 315, 318 (5th Cir. 2016).\n Accordingly, the parties do not dispute the November 2012 notice of\ndefault, which requested less than the full debt, could have constituted an\nabandonment of the 2010 acceleration. Instead, Appellants assert the Bank\nwas estopped from abandoning the 2010 acceleration due to Moore’s\ndetrimental reliance on it.\n 2.\n First, the parties dispute whether, under Texas law, a detrimental-\nreliance exception exists to a lender’s right to unilaterally withdraw its\nexercise of an option to accelerate. No Texas court has ever held detrimental\nreliance is an exception.\n Discussion about a detrimental-reliance exception first appeared in\n1998 in Swoboda v. Wilshire Credit Corp., in which a Texas intermediate\nappellate court stated in dicta: “Even if a creditor exercises the option to\naccelerate and makes a declaration to that effect, the election to accelerate can\nbe revoked or withdrawn at any time, so long as the debtor has not\ndetrimentally relied on the acceleration”. 975 S.W.2d 770, 776–77 (Tex. App.\n1998), disapproved of on other grounds by Holy Cross, 44 S.W.3d 562. For this\ndetrimental-reliance proposition, the Texas appellate court cited two non-\n 5\n\f Case: 18-10248 Document: 00514861432 Page: 6 Date Filed: 03/06/2019\n\n\n\n No. 18-10248\nTexas cases: In re Adu-Kofi, 94 B.R. 14, 15 (Bankr. D. R.I. 1988); and Golden\nv. Ramapo Improvement Corp., 78 A.D.2d 648 (N.Y. App. Div. 1980).\n Since Swoboda, numerous courts have cited this language, also in dicta.\nSee, e.g., Boren, 807 F.3d at 105; Nunnery v. Ocwen Loan Servicing, L.L.C.,\n641 F. App’x 430, 433 (5th Cir. 2016); Justice v. Wells Fargo Bank Nat’l Ass’n,\n674 F. App’x 330, 333 (5th Cir. 2016); Nationstar Mortgage, LLC v. Landers,\nNo. 12-17-00047-CV, 2018 WL 1737013, at *6 (Tex. App. 11 Apr. 2018);\nGraham v. LNV Corp., No. 03-16-00235-CV, 2016 WL 6407306, at *3 (Tex.\nApp. 26 Oct. 2016).\n Recently, however, federal and Texas state courts have expressed\ndoubts about whether the exception exists. See, e.g., Graham, 2016 WL\n6407306, at *4 & n.3 (“Texas courts have not resolved the question of whether\na note holder can unilaterally rescind acceleration . . . despite the debtor’s\ndetrimental reliance on the acceleration”.); Bitterroot, No. 5:14-CV-862-DAE,\n2015 WL 6442622, at *7 (W.D. Tex. 23 Oct. 2015) (“Given that Swoboda’s\ndetrimental reliance rule was derived from authority outside of Texas,\nhowever, the Court agrees that it is less than clear that the Texas Supreme\nCourt would adopt the same rule.”), aff’d 648 F. App’x 414 (5th Cir. 2016).\n Along that line, a very recent unpublished opinion by our court noted:\n“According to Texas intermediate appellate courts, the holder of a note may\nnot unilaterally abandon acceleration if the borrower objects to abandonment\nor has detrimentally relied on the acceleration”. Sims v. RoundPoint Mortg.\nServicing Corp., --- F. App’x ---, 2019 WL 360069, at *3 (5th Cir. 28 Jan. 2019)\n(per curiam) (citing Boren, 807 F.3d at 105); see also 5th Cir. R. 47.5.4\n(unpublished opinions on or after 1 January 1996 are not precedential except\nin certain instances not applicable in Sims).\n This opinion did not discuss the uncertainty surrounding the\ndetrimental-reliance exception, nor did it hold a detrimental-reliance\n 6\n\f Case: 18-10248 Document: 00514861432 Page: 7 Date Filed: 03/06/2019\n\n\n\n No. 18-10248\nexception exists under Texas law. Id. Instead, it joins the line of cases that\nhave cited this purported exception in dicta. Ultimately, our court held the\nfiling of bankruptcy, in that case, was not proof of detrimental reliance on the\nacceleration notice. Id. at *4.\n More to the issue at hand, the Texas legislature in 2015—almost 20\nyears after Swoboda was decided—enacted Texas Civil Practice and Remedies\nCode § 16.038; subsection (a) states: “If the maturity date of a series of notes\nor obligations or a note or obligation payable in installments is accelerated,\nand the accelerated maturity date is rescinded or waived . . . before the\nlimitations period expires, the acceleration is deemed rescinded and waived\nand the note, obligation, or series of notes or obligations shall be governed . . .\nas if no acceleration had occurred.” This statute provides no exceptions to a\nlender’s right to unilaterally withdraw the acceleration.\n “A statute is presumed to have been enacted by the legislature with\ncomplete knowledge of the existing law and with reference to it.” Acker v. Tex.\nWater Comm’n, 790 S.W.2d 299, 301 (Tex. 1990) (citation omitted). “Enforcing\nthe law as written is a court’s safest refuge in matters of statutory\nconstruction, and we should always refrain from rewriting text that\nlawmakers chose . . . .” Entergy Gulf States, Inc. v. Summers, 282 S.W.3d 433,\n443 (Tex. 2009) (citing Simmons v. Arnim, 220 S.W. 66, 70 (1920) (“Courts\nmust take statutes as they find them.”)).\n The Texas legislature, presumably with knowledge of the case law,\nchose not to include in the statute any exception to the lender’s right to\nunilaterally withdraw an acceleration notice. Therefore, it is unlikely the\nTexas Supreme Court would be willing to read such language into the statute,\nespecially considering the language ultimately comes from dicta citing\nauthority from outside of Texas.\n\n\n 7\n\f Case: 18-10248 Document: 00514861432 Page: 8 Date Filed: 03/06/2019\n\n\n\n No. 18-10248\n Accordingly, we hold detrimental reliance is not an exception to the\nlender’s right to unilaterally withdraw an acceleration notice under Texas\nlaw.\n B.\n The other issue on appeal concerned whether, for the claimed exception,\nthe requisite detrimental reliance existed. The district court concluded:\nJatera did not suffer such reliance; and Moore no longer retained an interest\nin the property, and, therefore, lacked standing. Jatera asserts Moore’s\npurported reliance was assigned to it through the earlier-described special\nwarranty deed.\n But, as held above, the claimed detrimental-reliance exception does not\nexist under Texas law. Therefore, we need not reach whether there was such\nreliance, including whether Jatera was assigned Moore’s detrimental-reliance\nclaim, or whether Moore suffered such reliance.\n III.\n For the foregoing reasons, the judgment is AFFIRMED.\n\n\n\n\n 8\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: JATERA CORPORATION; Esther Randle Moore, Plaintiffs-Appellants v. US BANK NATIONAL ASSOCIATION, AS TRUSTEE, in Trust FOR the REGISTERED HOLDERS OF CITIGROUP MORTGAGE LOAN TRUST, Asset-Backed Pass-Through Certificates, Series 2005-HE3; Select Portfolio Servicing, Incorporated, Defendants-Appellees\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-06\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 18-10248 Document: 00514861432 Page: 1 Date Filed: 03/06/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n No. 18-10248 March 6, 2019\\n Lyle W. Cayce\\nJATERA CORPORATION; ESTHER RANDLE MOORE, Clerk\\n\\n\\n Plaintiffs - Appellants\\n\\nv.\\n\\nUS BANK NATIONAL ASSOCIATION, As Trustee, in Trust for the\\nRegistered Holders of Citigroup Mortgage Loan Trust, Asset-Backed Pass-\\nThrough Certificates, Series 2005-HE3; SELECT PORTFOLIO SERVICING,\\nINCORPORATED,\\n\\n Defendants - Appellees\\n\\n\\n\\n\\n Appeal from the United States District Court\\n for the Northern District of Texas\\n\\n\\nBefore SMITH, BARKSDALE, and HO, Circuit Judges.\\nRHESA HAWKINS BARKSDALE, Circuit Judge:\\n At issue in this diversity action is whether Texas law provides a\\ndetrimental-reliance exception to a lender’s right to unilaterally withdraw a\\nnotice of acceleration; and, if so, whether Jatera Corporation and Esther\\nRandle Moore detrimentally relied on the notice of acceleration by U.S. Bank\\nNational Association (Bank) and Select Portfolio Servicing, Inc. (SPS).\\nAppellants challenge the district court’s, on cross-motions for summary\\njudgment, denying Appellants’ motion and granting Appellees’. AFFIRMED.\\n\\f Case: 18-10248 Document: 00514861432 Page: 2 Date Filed: 03/06/2019\\n\\n\\n\\n No. 18-10248\\n I.\\n In 2005, Moore and her husband purchased a house located in Dallas,\\nTexas (the property), by signing a Texas home equity fixed/adjustable rate note\\nin the amount of $99,200, secured by a Texas home equity security instrument.\\nThrough a series of transfers and assignments, the Bank became the owner\\nand holder of the note and security interest.\\n After her husband died in April 2008, all interest in the property was\\ntransferred to Moore, who soon defaulted on her mortgage payments. In March\\n2010, the Bank’s then loan servicer notified Moore of its intent to accelerate\\nthe note (acceleration notice), demanding full payment of the debt\\n($116,575.80).\\n After the Bank filed suit in state court in 2011 to obtain a court order\\npermitting foreclosure on the property, Moore signed an agreed final judgment\\nin November 2011, consenting to foreclosure. In January 2012, Moore vacated\\nthe property and signed a one-year lease for an apartment.\\n The Bank’s new loan servicer, SPS, sent a new notice of default to Moore\\nin November 2012, informing her: she could cure her default by making a\\npayment of $38,343.99; but, if payment was not received by December 2012,\\nthe note would be re-accelerated.\\n In March 2015, Moore conveyed her interest in the property to Scojo\\nSolutions, LLC, through a special warranty deed. One month later, Scojo\\ntransferred its interest in the property to Jatera Corporation.\\n After SPS re-initiated the foreclosure proceedings originally pursued by\\nthe Bank, Jatera filed this action against the Bank and SPS in state court,\\nseeking a judgment declaring the lien on the property void because Appellees\\nfailed to initiate foreclosure proceedings within the four-year statute of\\nlimitations. In response, Appellees removed this action to federal court on the\\nbasis of diversity jurisdiction.\\n 2\\n\\f Case: 18-10248 Document: 00514861432 Page: 3 Date Filed: 03/06/2019\\n\\n\\n\\n No. 18-10248\\n In district court, Jatera amended its complaint, asserting that Moore’s\\ndetrimental reliance on the acceleration notice prevented Appellees from\\nabandoning the acceleration in November 2012. Moore was joined as a\\nplaintiff. She filed a complaint seeking a judgment declaring the lien on the\\nproperty void, and/or quieting title in Jatera’s name (also on grounds of her\\ndetrimental reliance).\\n The parties filed cross-motions for summary judgment on all claims.\\nRegarding Moore’s claims, the district court held Moore no longer retained an\\ninterest in the property, and, therefore, lacked standing. Concerning Jatera’s\\nclaims, the court noted the uncertainty surrounding the detrimental-reliance\\nexception under Texas law, but held that, in any event, detrimental reliance\\nruns to the benefit of the party asserting it, and Jatera had failed to show it\\ndetrimentally relied on the acceleration notice. Accordingly, the court denied\\nAppellants’ motion and granted Appellees’.\\n II.\\n Appellants contend the district court erred in denying their summary-\\njudgment motion and in granting Appellees’. Accordingly, Appellants request\\njudgment’s being rendered in their favor; alternatively, that this case be\\nremanded to district court.\\n The district court’s “grant[] and denial[] of summary judgment [is\\nreviewed] de novo”. Century Surety Co. v. Seidel, 893 F.3d 328, 332 (5th Cir.\\n2018) (quotations and citation omitted). Summary judgment is proper “if the\\nmovant shows that there is no genuine dispute as to any material fact and the\\nmovant is entitled to judgment as a matter of law”. Fed. R. Civ. P. 56(a). “A\\ngenuine dispute of material fact exists if the evidence is such that a reasonable\\njury could return a verdict for the nonmoving party. However, [a] mere\\nscintilla of evidence will not preclude granting of a motion for summary\\njudgment.” Bitterroot Holdings, L.L.C. v. MTGLQ Inv’rs, L.P., 648 F. App’x\\n 3\\n\\f Case: 18-10248 Document: 00514861432 Page: 4 Date Filed: 03/06/2019\\n\\n\\n\\n No. 18-10248\\n414, 417 (5th Cir. 2016) (alteration in original) (internal quotations and\\ncitations omitted).\\n “When parties file cross-motions for summary judgment, we review each\\nparty’s motion independently, viewing the evidence and inferences in the light\\nmost favorable to the nonmoving party.” Cooley v. Hous. Auth. of Slidell, 747\\nF.3d 295, 298 (5th Cir. 2014) (internal quotations and citation omitted).\\n A.\\n Texas substantive law applies to this diversity-jurisdiction case. Erie\\nR.R. v. Tompkins, 304 U.S. 64, 78–79 (1938). In instances where the State’s\\nhighest court has not spoken on the direct question, federal courts are\\nrequired to make an “Erie guess and determine, in [their] best judgment how\\n[the State’s highest court] would resolve the issue if presented with the same\\ncase”. Temple v. McCall, 720 F.3d 301, 307 (5th Cir. 2013) (first alteration in\\noriginal) (internal quotations and citation omitted). In doing so, our court\\n“defer[s] to intermediate state appellate court decisions, unless convinced by\\nother persuasive data that the highest court of the state would decide\\notherwise”. Mem’l Hermann Healthcare Sys., Inc. v. Eurocopter Deutschland,\\nGMBH, 524 F.3d 676, 678 (5th Cir. 2008) (internal quotations and citation\\nomitted).\\n 1.\\n Under Texas law, “[a] person must bring suit for . . . the foreclosure of a\\nreal property lien not later than four years after the day the cause of action\\naccrues”. Tex. Civ. Prac. & Rem. Code Ann. § 16.035(a). If foreclosure does\\nnot occur within this limitations period, “the real property lien and a power of\\nsale to enforce the . . . lien become void”. Id. § 16.035(d). If the note secured\\nby the property contains an optional acceleration clause, “the action accrues\\nonly when the holder actually exercises its option to accelerate”. Bitterroot,\\n\\n\\n 4\\n\\f Case: 18-10248 Document: 00514861432 Page: 5 Date Filed: 03/06/2019\\n\\n\\n\\n No. 18-10248\\n648 F. App’x at 418 (quoting Holy Cross Church of God in Christ v. Wolf, 44\\nS.W.3d 562, 566 (Tex. 2001)).\\n The acceleration may be abandoned, either by the lender’s unilateral\\nactions or by agreement, thereby suspending the limitations period until the\\nlender exercises its option to re-accelerate the note. Boren v. U.S. Nat’l Bank\\nAss’n, 807 F.3d 99, 106 (5th Cir. 2015); Holy Cross, 44 S.W.3d at 566–67.\\n“[T]he request for payment of less than the full obligation—after initially\\naccelerating the entire obligation—[is] an unequivocal expression of the\\nbank’s intent to abandon or waive its initial acceleration”. Martin v. Fed. Nat’l\\nMortg. Ass’n, 814 F.3d 315, 318 (5th Cir. 2016).\\n Accordingly, the parties do not dispute the November 2012 notice of\\ndefault, which requested less than the full debt, could have constituted an\\nabandonment of the 2010 acceleration. Instead, Appellants assert the Bank\\nwas estopped from abandoning the 2010 acceleration due to Moore’s\\ndetrimental reliance on it.\\n 2.\\n First, the parties dispute whether, under Texas law, a detrimental-\\nreliance exception exists to a lender’s right to unilaterally withdraw its\\nexercise of an option to accelerate. No Texas court has ever held detrimental\\nreliance is an exception.\\n Discussion about a detrimental-reliance exception first appeared in\\n1998 in Swoboda v. Wilshire Credit Corp., in which a Texas intermediate\\nappellate court stated in dicta: “Even if a creditor exercises the option to\\naccelerate and makes a declaration to that effect, the election to accelerate can\\nbe revoked or withdrawn at any time, so long as the debtor has not\\ndetrimentally relied on the acceleration”. 975 S.W.2d 770, 776–77 (Tex. App.\\n1998), disapproved of on other grounds by Holy Cross, 44 S.W.3d 562. For this\\ndetrimental-reliance proposition, the Texas appellate court cited two non-\\n 5\\n\\f Case: 18-10248 Document: 00514861432 Page: 6 Date Filed: 03/06/2019\\n\\n\\n\\n No. 18-10248\\nTexas cases: In re Adu-Kofi, 94 B.R. 14, 15 (Bankr. D. R.I. 1988); and Golden\\nv. Ramapo Improvement Corp., 78 A.D.2d 648 (N.Y. App. Div. 1980).\\n Since Swoboda, numerous courts have cited this language, also in dicta.\\nSee, e.g., Boren, 807 F.3d at 105; Nunnery v. Ocwen Loan Servicing, L.L.C.,\\n641 F. App’x 430, 433 (5th Cir. 2016); Justice v. Wells Fargo Bank Nat’l Ass’n,\\n674 F. App’x 330, 333 (5th Cir. 2016); Nationstar Mortgage, LLC v. Landers,\\nNo. 12-17-00047-CV, 2018 WL 1737013, at *6 (Tex. App. 11 Apr. 2018);\\nGraham v. LNV Corp., No. 03-16-00235-CV, 2016 WL 6407306, at *3 (Tex.\\nApp. 26 Oct. 2016).\\n Recently, however, federal and Texas state courts have expressed\\ndoubts about whether the exception exists. See, e.g., Graham, 2016 WL\\n6407306, at *4 & n.3 (“Texas courts have not resolved the question of whether\\na note holder can unilaterally rescind acceleration . . . despite the debtor’s\\ndetrimental reliance on the acceleration”.); Bitterroot, No. 5:14-CV-862-DAE,\\n2015 WL 6442622, at *7 (W.D. Tex. 23 Oct. 2015) (“Given that Swoboda’s\\ndetrimental reliance rule was derived from authority outside of Texas,\\nhowever, the Court agrees that it is less than clear that the Texas Supreme\\nCourt would adopt the same rule.”), aff’d 648 F. App’x 414 (5th Cir. 2016).\\n Along that line, a very recent unpublished opinion by our court noted:\\n“According to Texas intermediate appellate courts, the holder of a note may\\nnot unilaterally abandon acceleration if the borrower objects to abandonment\\nor has detrimentally relied on the acceleration”. Sims v. RoundPoint Mortg.\\nServicing Corp., --- F. App’x ---, 2019 WL 360069, at *3 (5th Cir. 28 Jan. 2019)\\n(per curiam) (citing Boren, 807 F.3d at 105); see also 5th Cir. R. 47.5.4\\n(unpublished opinions on or after 1 January 1996 are not precedential except\\nin certain instances not applicable in Sims).\\n This opinion did not discuss the uncertainty surrounding the\\ndetrimental-reliance exception, nor did it hold a detrimental-reliance\\n 6\\n\\f Case: 18-10248 Document: 00514861432 Page: 7 Date Filed: 03/06/2019\\n\\n\\n\\n No. 18-10248\\nexception exists under Texas law. Id. Instead, it joins the line of cases that\\nhave cited this purported exception in dicta. Ultimately, our court held the\\nfiling of bankruptcy, in that case, was not proof of detrimental reliance on the\\nacceleration notice. Id. at *4.\\n More to the issue at hand, the Texas legislature in 2015—almost 20\\nyears after Swoboda was decided—enacted Texas Civil Practice and Remedies\\nCode § 16.038; subsection (a) states: “If the maturity date of a series of notes\\nor obligations or a note or obligation payable in installments is accelerated,\\nand the accelerated maturity date is rescinded or waived . . . before the\\nlimitations period expires, the acceleration is deemed rescinded and waived\\nand the note, obligation, or series of notes or obligations shall be governed . . .\\nas if no acceleration had occurred.” This statute provides no exceptions to a\\nlender’s right to unilaterally withdraw the acceleration.\\n “A statute is presumed to have been enacted by the legislature with\\ncomplete knowledge of the existing law and with reference to it.” Acker v. Tex.\\nWater Comm’n, 790 S.W.2d 299, 301 (Tex. 1990) (citation omitted). “Enforcing\\nthe law as written is a court’s safest refuge in matters of statutory\\nconstruction, and we should always refrain from rewriting text that\\nlawmakers chose . . . .” Entergy Gulf States, Inc. v. Summers, 282 S.W.3d 433,\\n443 (Tex. 2009) (citing Simmons v. Arnim, 220 S.W. 66, 70 (1920) (“Courts\\nmust take statutes as they find them.”)).\\n The Texas legislature, presumably with knowledge of the case law,\\nchose not to include in the statute any exception to the lender’s right to\\nunilaterally withdraw an acceleration notice. Therefore, it is unlikely the\\nTexas Supreme Court would be willing to read such language into the statute,\\nespecially considering the language ultimately comes from dicta citing\\nauthority from outside of Texas.\\n\\n\\n 7\\n\\f Case: 18-10248 Document: 00514861432 Page: 8 Date Filed: 03/06/2019\\n\\n\\n\\n No. 18-10248\\n Accordingly, we hold detrimental reliance is not an exception to the\\nlender’s right to unilaterally withdraw an acceleration notice under Texas\\nlaw.\\n B.\\n The other issue on appeal concerned whether, for the claimed exception,\\nthe requisite detrimental reliance existed. The district court concluded:\\nJatera did not suffer such reliance; and Moore no longer retained an interest\\nin the property, and, therefore, lacked standing. Jatera asserts Moore’s\\npurported reliance was assigned to it through the earlier-described special\\nwarranty deed.\\n But, as held above, the claimed detrimental-reliance exception does not\\nexist under Texas law. Therefore, we need not reach whether there was such\\nreliance, including whether Jatera was assigned Moore’s detrimental-reliance\\nclaim, or whether Moore suffered such reliance.\\n III.\\n For the foregoing reasons, the judgment is AFFIRMED.\\n\\n\\n\\n\\n 8\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1077,"cells":{"id":{"kind":"number","value":4597955,"string":"4,597,955"},"name":{"kind":"string","value":"TEXAS TECH PHYSICIANS ASSOCIATES, Plaintiff-Appellant v. UNITED STATES DEPARTMENT OF HEALTH AND HUMAN SERVICES; Alex M. Azar, II, Secretary, U.S. Department of Health and Human Services, Defendants-Appellees"},"name_abbreviation":{"kind":"string","value":"Tex. Tech Physicians Assocs. v. U.S. Dep't of Health & Human Servs."},"decision_date":{"kind":"string","value":"2019-03-07"},"docket_number":{"kind":"string","value":"18-10620"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"King, Higginson, Costa\", \"parties\": \"\", \"opinions\": [{\"author\": \"GREGG COSTA, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 18-10620 Document: 00514863670 Page: 1 Date Filed: 03/07/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n\\n No. 18-10620\\n FILED\\n March 7, 2019\\n Lyle W. Cayce\\nTEXAS TECH PHYSICIANS ASSOCIATES, Clerk\\n\\n Plaintiff - Appellant\\n\\nv.\\n\\nUNITED STATES DEPARTMENT OF HEALTH AND HUMAN SERVICES;\\nALEX M. AZAR, II, SECRETARY, U.S. DEPARTMENT OF HEALTH AND\\nHUMAN SERVICES,\\n\\n Defendants - Appellees\\n\\n\\n\\n\\n Appeal from the United States District Court\\n for the Northern District of Texas\\n\\n\\nBefore KING, HIGGINSON, and COSTA, Circuit Judges.\\nGREGG COSTA, Circuit Judge:\\n Medicare incentivizes services, not results. Its fee-for-service model\\nrisks not only that beneficiaries may receive treatment they do not need, but\\nalso that they may miss out on less expensive treatment that might help. See\\nMEDICARE PAYMENT ADVISORY COMM’N, REPORT TO THE CONGRESS:\\nREFORMING THE DELIVERY SYSTEM 7 (June 2008). To test whether other\\napproaches could be more efficient, Congress authorizes “experiments and\\ndemonstration projects” deviating from the ordinary Medicare reimbursement\\nrules. 42 U.S.C. § 1395b-1. This case arises from one such demonstration\\nproject, with a twist: Texas Tech Physicians Associates could keep the\\n\\f Case: 18-10620 Document: 00514863670 Page: 2 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\nadditional fees it received for implementing the project only if its care\\nmanagement model achieved cost savings. The government says Texas Tech\\nfailed, and so demands return of roughly $8 million in fees. Texas Tech resists\\nthat demand.\\n I.\\n One of the alternative payment models the Department of Health and\\nHuman Services may explore is whether “payments for services other than\\nthose for which payment may” ordinarily be made might reduce costs and\\nimprove “utilization of services.” 42 U.S.C. § 1395b-1(a)(1)(B). Using that\\nauthorization, the Center for Medicare and Medicaid Services (CMS, the\\nagency within HHS that administers Medicare) solicited proposals for a “Care\\nManagement for High-Cost Beneficiaries Demonstration.” CMS was looking\\nfor projects to test whether “intensive management” of patients and\\ncoordination between providers might improve care and reduce costs for\\nMedicare beneficiaries with substantial medical needs. On top of the normal\\nfees for services, participating programs could earn monthly fees contingent on\\nachieving cost savings of 5%. These extra fees would count as costs.\\n Texas Tech Physicians Associates—together with Texas Tech University\\nHealth Sciences Center and Trailblazer Health Enterprises—submitted a\\nproposal. The project would employ a “system of telephone contacts, letters,\\nsite visits and physician contacts” to help manage and coordinate care for high-\\nrisk beneficiaries treated at Texas Tech’s facilities. Interventions would range\\nfrom home safety assessments to support groups, depending on patients’ risk\\nlevels. The application indicated it expected to achieve Medicare cost savings\\nof up to 25%.\\n CMS took Texas Tech up on its proposal, and the parties signed a\\n“demonstration agreement” in January 2006. Texas Tech agreed to implement\\nthe project “as proposed in the demonstration application.” In exchange, it\\n 2\\n\\f Case: 18-10620 Document: 00514863670 Page: 3 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\nwould receive a monthly management fee of $117 per participating beneficiary.\\nAnd as required by the solicitation, it agreed to be responsible for failure to\\nmeet the 5% net cost savings figure, up to the amount it would receive in\\nmanagement fees.\\n The difficulty—then and now—was selecting an adequate control group.\\nThe control group was important because cost savings would be determined by\\ncomparing the costs of patients in the control group with those of Texas Tech’s\\nparticipating patients, referred to as the intervention group. The\\ndemonstration agreement did not itself identify a control group. Instead, CMS\\nwould “contract with an independent evaluator” to “assist CMS in designing\\nfeatures for a suitable comparison group.” After the contractor proposed a\\nmethodology for matching a control group to the intervention group, Texas\\nTech would have “the opportunity to review and agree” before beginning the\\nproject.\\n Agreeing on a control group proved something of a sticking point.\\nFollowing an initial proposal from a contractor hired by CMS, RTI\\nInternational, Texas Tech raised various concerns about the populations from\\nwhich the control group would be drawn. RTI responded with changes to its\\ninitial approach.\\n Following months of back-and-forth, RTI sent an April 2006 memo\\nsummarizing a “physician group practice-based” approach. RTI used a “loyalty\\nalgorithm” to identify patients whose loyalty to a practice was similar to that\\nof Texas Tech’s patients. Those beneficiaries would be eligible for inclusion in\\nthe control group if they were within the 48-county area served by Texas Tech\\nand had high Medicare costs or serious diseases. RTI would then randomly\\nassign eligible beneficiaries to the control group such that, according to\\nhistorical cost data, it was made up of low-cost, medium-cost, and high-cost\\npatients in percentages nearly identical to Texas Tech’s patient population.\\n 3\\n\\f Case: 18-10620 Document: 00514863670 Page: 4 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\nTexas Tech reviewed and accepted the April 2006 methodology and began\\nenrolling participants that month.\\n The trouble began less than a year later. In February 2007, Actuarial\\nResearch Corporation (another CMS contractor) released a report on the first\\nsix months of Texas Tech’s project. After adjusting for baseline cost\\ndifferences, the intervention group’s monthly per-member costs were 7%\\nhigher than the control group’s. Texas Tech chalked the cost differences up to\\ninconsistencies between the groups. It pointed, for instance, to two features of\\nthe intervention group that it believed explained its higher costs: more deaths\\nand more patients residing in nursing homes. In light of those differences,\\nTexas Tech asked that the control group be adjusted. But CMS declined; it\\nsaid doing so was “not feasible” and its investigation of disparities between the\\ngroups did not reveal “any reasonable adjustments that could produce a match\\n. . . that mitigated disparities.”\\n Texas Tech then terminated the program effective July 31, 2007. The\\ndemonstration agreement permitted early termination, in which event it\\nrequired a prompt “final reconciliation.”\\n Actuarial Research Corporation issued a reconciliation report a year\\nlater. It concluded that (1) Texas Tech had received $7.99 million in\\nadministrative fees; (2) Texas Tech’s savings guarantee required just over $10\\nmillion in net savings—$2.05 million in cost reductions 1 plus the $7.99 million\\nin fees; and (3) the intervention group’s Medicare costs were $6.79 million\\nhigher than the control group’s. This meant a “savings shortfall” of $16.79\\nmillion, exceeding the contingent monthly fees Texas Tech had received and\\nrequiring their return in full.\\n\\n\\n\\n Because Texas Tech terminated the project early, after just 16 months, it guaranteed\\n 1\\n\\nonly 2% cost savings, not the 5% it guaranteed after the full three years.\\n 4\\n\\f Case: 18-10620 Document: 00514863670 Page: 5 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\n Unhappy with that result, Texas Tech hired its own consultant to\\ninvestigate disparities between the intervention and control groups. Its report\\nraised concerns about whether the control group’s historical cost trends\\nmatched the intervention group’s, and whether differences in death rates made\\nthe groups a poor match. CMS asked RTI to look into those concerns, but RTI\\nconcluded that the differences between the groups “cannot account for the\\nestimated Texas Tech intervention effect of higher, not lower, cost growth.”\\n CMS sent a letter to Texas Tech in March 2009 requesting return of the\\n$7.99 million. Texas Tech demurred. Four years passed before CMS sent\\nTexas Tech another letter in September 2013, renewing its demand that Texas\\nTech return the money. That letter said it would represent CMS’s “final\\ndecision” unless Texas Tech appealed to HHS’s Departmental Appeals Board.\\n Texas Tech did appeal to the Board, only to promptly ask for dismissal\\nof its appeal. It argued that the demonstration agreement was a procurement\\ncontract and thus governed by the Contract Disputes Act, 41 U.S.C. §§ 7101–\\n09, which would mean the Board was not the proper forum for resolving this\\ndispute. It also argued that the Act’s six-year statute of limitations barred\\nCMS’s delayed attempt to collect the debt. The Board denied Texas Tech’s\\nmotion to dismiss, holding that the demonstration agreement was a grant\\nagreement rather than a procurement contract.\\n In the merits appeal that followed, Texas Tech raised a variety of\\ncontract theories to avoid CMS’s demand for repayment, including three\\nalleged breaches of the agreement as well as common law defenses like mistake\\nand impossibility. In a thorough opinion, the Board rejected those arguments\\nin part because it determined that “[c]ommon law contract theories are\\ninapplicable” to grant agreements. In light of this view, whether CMS\\nbreached the agreement mattered only insofar as the demonstration\\nagreement conditioned Texas Tech’s repayment obligation on CMS’s\\n 5\\n\\f Case: 18-10620 Document: 00514863670 Page: 6 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\nperformance. And in addition to finding that none of Texas Tech’s allegations\\nwould have affected its duty to meet the cost savings target, the Board\\ndetermined that CMS complied with the agreement.\\n Texas Tech sought further review by suing HHS under the\\nAdministrative Procedure Act, asking the district court to set aside the Board’s\\ndecision and enjoin CMS from enforcing its demand. 2 On competing summary\\njudgment motions, the district court ruled that Texas Tech had not met its\\nburden under the APA and granted HHS’s motion. Texas Tech appeals.\\n II.\\n Texas Tech first argues that the HHS Departmental Appeals Board\\nshould not have heard this case. That is because, in its view, the\\ndemonstration agreement was a procurement contract governed by the\\nContract Disputes Act. See 41 U.S.C. § 7102(a)(2). If that statute applies, it\\naffects where and when this dispute should have been resolved. Disputes over\\ngovernment procurement contracts start with presenting a claim to the\\nappropriate contracting officer. Id. § 7103(a). Any such claim—whether by the\\ngovernment or a private party—must be presented within six years. Id.\\n§ 7103(a)(4)(A). If a party to the contract disagrees with the contracting\\nofficer’s decision, it may appeal to the Civilian Board of Contract Appeals or\\nthe Court of Federal Claims, id. §§ 7104, 7105(b), but not to “any [other] forum,\\ntribunal, or Federal Government agency,” id. § 7103(g). So if the\\ndemonstration agreement was a procurement contract, then the government\\n\\n\\n\\n\\n 2 Other circuits have held that contract claims seeking equitable or declaratory relief\\nare “impliedly forbid[den]” under the APA. 5 U.S.C. § 702; see, e.g., Transohio Sav. Bank v.\\nDir., Office of Thrift Supervision, 967 F.2d 598, 609 (D.C. Cir. 1992). But when we asked for\\nsupplemental briefing, both parties agreed that the APA permits review of disputes about\\ngrant agreements. So we will consider this grant dispute under the APA, as we have before.\\nSee Delta Found., Inc. v. United States, 303 F.3d 551, 563 (5th Cir. 2002); Inst. for Tech. Dev.\\nv. Brown, 63 F.3d 445, 449–50 (5th Cir. 1995).\\n 6\\n\\f Case: 18-10620 Document: 00514863670 Page: 7 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\nmay have been late in seeking return of the fees, and the Board lacked\\njurisdiction.\\n But none of the Contract Disputes Act’s requirements matters if the\\nBoard correctly determined that the demonstration agreement was not a\\nprocurement contract but instead a grant agreement. See id. § 7102(a)(2)\\n(specifying the types of government contracts to which the CDA applies,\\nincluding those for the “procurement of services”); Coastal Corp. v. United\\nStates, 713 F.2d 728, 730 (Fed. Cir. 1983) (“[The CDA] does not cover all\\ngovernment contracts.”). The Federal Circuit, well versed in government\\ncontract disputes, looks to the Federal Grant and Cooperative Agreement Act\\nwhen characterizing government agreements. See, e.g., Hymas v. United\\nStates, 810 F.3d 1312, 1325–26 (Fed. Cir. 2016). So do the parties.\\n That statute says executive agencies must use procurement contracts\\nwhen:\\n the principle purpose of the instrument is to acquire (by purchase,\\n lease, or barter) property or services for the direct benefit or use of\\n the United States government.\\n31 U.S.C. § 6303(1). An example is a Navy contract for purchase of a ship. The\\ngovernment gets to use what it purchased.\\n In contrast, agencies must use a grant agreement when:\\n the principle purpose of the relationship is to transfer a thing of\\n value to the State or local government or other recipient to carry\\n out a public purpose of support or stimulation . . . instead of\\n acquiring (by purchase, lease, or barter) property or services for\\n the direct benefit or use of the United States Government.\\nId. § 6304(1). An example is an agreement with a school district to provide free\\nschool lunches. The federal government pays for the lunches, but students\\nreceive the benefit.\\n We agree with the Board that the demonstration agreement was not a\\nprocurement contract. The “direct” benefits of the agreement ran to the\\n 7\\n\\f Case: 18-10620 Document: 00514863670 Page: 8 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\nMedicare beneficiaries participating in Texas Tech’s program, not to CMS. See\\nUnited States v. Univ. Hosp. of State Univ. of N.Y. at Stony Brook, 575 F. Supp.\\n607, 612–13 (E.D.N.Y. 1983) (distinguishing procurement contracts from\\nagreements to reimburse hospitals because “a hospital receiving\\nreimbursements under Medicaid or Medicare provides services directly to the\\npublic”). CMS hoped to gain insight into how best to operate Medicare for high-\\ncost beneficiaries, but advancing an “agency’s overall mission” (something that\\none would hope all grant agreements do) is not a direct benefit. Hymas, 810\\nF.3d at 1328. And CMS would not achieve any cost savings directly. The\\nsavings would have resulted—had the project gone as hoped—from Texas\\nTech’s making participating beneficiaries healthier, thereby decreasing their\\nneed for Medicare services. 3\\n The Board had jurisdiction.\\n III.\\n Under the APA, the Board’s action may be set aside if “arbitrary,\\ncapricious, an abuse of discretion, or otherwise not in accordance with law.” 5\\nU.S.C. § 706(2)(A). An agency’s decision is presumptively valid; the plaintiff\\nbears the burden of showing otherwise. Texas Clinical Labs, Inc. v. Sebelius,\\n612 F.3d 771, 775 (5th Cir. 2010). We defer to the agency’s findings of fact if\\nthey are supported by substantial evidence. Buffalo Marine Servs. Inc. v.\\nUnited States, 663 F.3d 750, 753–54 (5th Cir. 2011). On questions of law, our\\n\\n\\n\\n 3There may be instances when an agency “acquires” services for its own direct benefit,\\neven though the services are conferred on third parties, such as when it outsources services\\nit would otherwise perform. See, e.g., CMS Contract Mgmt. Servs. v. Mass. Housing Fin.\\nAgency, 745 F.3d 1379, 1385–85 (Fed. Cir. 2014) (holding that HUD’s agreements with\\nhousing authorities, under which authorities would administer Section 8 payments, were\\nprocurement contracts). But this is not an outsourcing case. There is a difference between\\nan agency that hires a company to perform administrative tasks the government would\\notherwise have to perform, see id., and CMS’s paying doctors and hospitals to benefit\\nMedicare patients.\\n 8\\n\\f Case: 18-10620 Document: 00514863670 Page: 9 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\ndegree of deference varies according to the source of law. Although we give\\nChevron deference to an agency’s interpretation of an ambiguous statute it\\nadministers, Memorial Hermann Hosp. v. Sebelius, 728 F.3d 400, 405 (5th Cir.\\n2013), when an agency makes other conclusions of law—including interpreting\\n“contractual agreements”—our review is “effectively de novo,” Inst. for Tech\\nDev. v. Brown, 63 F.3d 445, 450 (5th Cir. 1995).\\n A.\\n Underlying all of its merits arguments is Texas Tech’s objection to the\\nBoard’s characterization of the demonstration agreement as something other\\nthan a contract. Although the Board acknowledged that “the terms of a grant\\nagreement are binding on both the grantee and the grantor,” Brown, 63 F.3d\\nat 449, it concluded that “contract law doctrines do not dictate its analysis or\\nresolution of disputes involving federal grants.” Several cases support that\\nproposition. See, e.g., Bennett v. Ky. Dep’t of Educ., 470 U.S. 656, 669 (1985)\\n(“Although we agree with the State that Title I grant agreements had a\\ncontractual aspect, the program cannot be viewed in the same manner as a\\nbilateral contract governing a discrete transaction.” (citation omitted)); United\\nStates v. Melendez, 944 F.2d 216, 219 (5th Cir. 1991) (holding that “contract\\nprinciples do not apply” in dispute over federal scholarship agreement).\\n Texas Tech attempts to distinguish those decisions as limited to federal\\ngrants in which the parties’ obligations are dictated by statute or regulation,\\nas opposed to the terms of a separately negotiated grant agreement. But we\\nultimately need not resolve whether the Board erred in suggesting that the\\ncommon law of contracts never informs grant disputes. Even if it did, the\\n\\n\\n\\n\\n 9\\n\\f Case: 18-10620 Document: 00514863670 Page: 10 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\nBoard made valid findings justifying the rejection of Texas Tech’s various\\ncontract theories. 4\\n B.\\n Texas Tech’s most forceful complaint is that patients in the control group\\nwere too dissimilar from patients in the intervention group—that is, that CMS\\nbreached the demonstration agreement by failing to provide an appropriately\\nmatched control group.\\n This is what the agreement said about selection of the control group:\\n For a matched control cohort, the evaluator will specify the\\n approach to be used in identifying such cohort. For each site that\\n is not randomized, attention will be given to ensuring that the\\n matched control cohort represents an appropriate comparison\\n group that is specific to the intervention mode. [Texas Tech] will\\n have the opportunity to review and agree to the approach that is\\n proposed by the evaluator and CMS. CMS and [Texas Tech] will\\n mutually agree upon the criteria and methodology used to select\\n the relevant comparison group pursuant to a memorandum from\\n the evaluation contractor documenting these methods and written\\n documentation from [Texas Tech] stating its agreement with such\\n memorandum.\\nThe agreement thus required that “attention” be given to “ensuring” the\\ncontrol group was sufficiently matched to the intervention group. It further\\nexplains how that would be done: CMS’s obligation was to select a third-party\\nevaluator, which would propose an “approach” for choosing a control group.\\nTexas Tech had to review and agree to that approach before starting the\\nproject.\\n\\n\\n\\n\\n 4Typically, when an agency reaches a decision based on erroneous reasoning, the\\nChenery doctrine prohibits a reviewing court from upholding that decision for an alternative\\nreason. Motor Vehicle Mfrs. Assoc. v. State Farm Mut. Auto Ins. Co., 463 U.S. 29, 50 (1983);\\nSEC v. Chenery Corp., 332 U.S. 194, 196 (1947). But when an agency gives multiple reasons,\\nwe may uphold its decision based on any one of those reasons. Salt River Project Agr. Imp.\\n& Power Dist. v. United States, 762 F.2d 1053, 1060 n.8 (D.C. Cir. 1985).\\n 10\\n\\f Case: 18-10620 Document: 00514863670 Page: 11 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\n So agreement by the parties on “criteria and methodology” was the\\nmechanism for ensuring adequacy of the control group, not after-the-fact\\nassessment of whether the control group had an unspecified degree of\\nsimilarity with the intervention group. Texas Tech invoked its right to\\ninfluence the selection criteria, engaging in months of back-and-forth to flesh\\nout the details. The agreement did not require more than that for selection of\\nthe control group.\\n C.\\n Texas Tech next argues that CMS breached the agreement by refusing\\nto allow it to access relevant Medicare claims data. In apparent response to\\nTexas Tech’s request to obtain this information from Trailblazer—a partner in\\nthe project—CMS told Texas Tech (1) that it could not obtain Trailblazer data\\nin order to create its own “pseudo” control group; and (2) that it could not obtain\\nTrailblazer data on patients in the intervention group without submitting a\\ndata use agreement and getting it approved by CMS. CMS did eventually\\napprove a data use agreement between Texas Tech and Trailblazer, but not\\nuntil May 2007, two months before Texas Tech terminated the project. Texas\\nTech’s idea is that had it been armed with Trailblazer data sooner, it could\\nhave better monitored its own performance as well as the accuracy of the\\ncontrol group.\\n Attempting to locate its right to Trailblazer data in the demonstration\\nagreement, Texas Tech points to its project proposal. In it, Texas Tech\\nsuggested that claims data would be available to it from the “Fiscal\\nIntermediary Standard System,” one of several sources of data it might use to\\ntarget its care management interventions. Because the agreement required\\nTexas Tech to “implement the care management program as proposed,” Texas\\nTech claims a right to access and use data from fiscal intermediaries, including\\nTrailblazer.\\n 11\\n\\f Case: 18-10620 Document: 00514863670 Page: 12 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\n We agree with the Board that CMS’s declining or delaying Texas Tech’s\\naccess to Trailblazer data did not violate the demonstration agreement. Even\\nif the proposal indicated that Texas Tech intended to use Trailblazer’s claims\\ndata, the agreement incorporated the proposal to specify the details of the\\nproject Texas Tech agreed to implement. The proposal thus became a Texas\\nTech obligation, not a CMS obligation, so CMS could not have violated it. To\\nbe clear, the agreement (as opposed to the proposal) did impose data-related\\nobligations on CMS. CMS had to give Texas Tech demographic information\\nand claims data on the intervention group going back 12 months, but Texas\\nTech does not claim CMS failed to do so. Nothing in the agreement obligated\\nCMS to give Texas Tech access to additional data from fiscal intermediaries.\\nTo the contrary, the only relevant provision in the agreement said that if Texas\\nTech “wishes to receive additional data . . . from an FI,” it must notify CMS,\\nwhich would decide only “if such information can be provided.”\\n Texas Tech’s argument faces another problem. Even if we were to read\\nthe agreement to require CMS to allow Texas Tech access to Trailblazer data,\\nthat requirement would extend only to data on the intervention group—the\\nproposal said nothing about using fiscal intermediary data for purposes other\\nthan honing Texas Tech’s care management interventions. And the Board\\nfound that under HHS privacy regulations, CMS could not have allowed Texas\\nTech to access Trailblazer’s claims data on the intervention group without a\\ndata use agreement. See 45 C.F.R. § 164.514(e)(3)(i), (4)(i) (permitting a\\n“covered entity” to disclose medical data “only if the covered entity obtains\\nsatisfactory assurance, in the form of a data use agreement” that the recipient\\nwill use the data “for limited purposes”). Texas Tech does not dispute that. It\\nhas not met its burden of showing that the Board’s ruling on this issue should\\nbe set aside.\\n\\n\\n 12\\n\\f Case: 18-10620 Document: 00514863670 Page: 13 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\n D.\\n Texas Tech also contends that CMS breached the demonstration\\nagreement by engaging RTI to evaluate whether differences between the\\nintervention and control groups may have accounted for the apparent lack of\\ncost savings. Because RTI designed the parameters for the control group,\\nTexas Tech contends it had a conflict of interest in checking its work.\\n But the only time RTI analyzed the alleged disparities in the groups was\\nafter Texas Tech had terminated the project, Actuarial Research Corporation\\nhad conducted the final reconciliation, and Texas Tech had alleged that the\\nstudy was flawed. The demonstration agreement imposes no post-\\nreconciliation obligations on CMS, so CMS cannot have breached the\\nagreement by asking RTI to look into Texas Tech’s concerns. 5\\n E.\\n In addition to its breach arguments, Texas Tech asserted a variety of\\ncommon law contract doctrines before the Board. The Board did not expressly\\naddress two of them—mistake and impracticability 6—because of its view that\\nthose common law principles do not apply to grant agreements.\\n But the Board did make findings that doom those two defenses. It found,\\nbased on the months of negotiation over criteria for the control group, that\\nTexas Tech “proceeded despite its concerns” and “could not reasonably have\\nfailed to understand . . . that it had assumed the financial risks associated with\\n\\n\\n\\n 5 Before the Board, Texas Tech framed its conflict-of-interest theory as a breach of the\\nimplied covenant of good faith and fair dealing, not a breach of the demonstration\\nagreement’s explicit terms. But even if the implied covenant can apply to grant agreements,\\nit cannot “expand another party’s contractual duties beyond those in the express contract.”\\nAgility Pub. Warehousing Co. KSCP v. Mattis, 852 F.3d 1370, 1384 (Fed. Cir. 2017) (cleaned\\nup). The same goes for Texas Tech’s argument to the Board that CMS breached the implied\\ncovenant by failing to create a more accurate control group.\\n 6 The Board did alternatively reject the merits of two others: failure to disclose and\\n\\nestoppel. Texas Tech does not challenge those conclusions.\\n 13\\n\\f Case: 18-10620 Document: 00514863670 Page: 14 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\nshortcomings in study design and implementation.” That undermines Texas\\nTech’s mistake theory; Texas Tech assumed the risk by agreeing to perform\\nthe demonstration, knowing that the control group might have problems.\\nRESTATEMENT (SECOND) OF CONTRACTS § 154(b). It also undermines Texas\\nTech’s impracticability theory because it shows that the accuracy of the control\\ngroup was not a “basic assumption” of the parties’ agreement. Id. § 261.\\n Although the Board did not make these findings in the context of\\ndiscussing mistake and impracticability, they would defeat those defenses had\\nthe Board directly addressed them. As a result, and because substantial\\nevidence supports these findings, any error was harmless. See Shinseki v.\\nSanders, 556 U.S. 396, 411 (2009) (clarifying that administrative harmless\\nerror analysis turns on, among other things, the “likelihood that the result\\nwould have been different” but for the error). The administrative harmless\\nerror rule can sit uneasily alongside the Chenery doctrine, which typically\\nconfines judicial review to the agency’s reasoning. See Nicholas Bagley,\\nRemedial Restraint in Administrative Law, 117 COLUM. L. REV. 253, 302–07\\n(2017). But that tension arises when a reviewing court makes findings the\\nagency should have made in the first instance. See id. at 305 (observing\\n“controversial[]” cases upholding agency decisions when “the evidence in the\\nrecord so strongly supports the result that the court is confident the agency\\nwould reach the same decision on remand”). Chenery cautions against\\nintruding onto an agency’s turf, not against giving an agency’s own findings\\ntheir obvious effect. See Henry J. Friendly, Chenery Revisited: Reflections on\\nReversal and Remand of Administrative Orders, 1969 DUKE L.J. 199, 211\\n(explaining that remand to an agency is “necessary only when the reviewing\\ncourt concludes that there is a significant chance that but for the error the\\nagency might have reached a different result” because “in the absence of such\\na possibility, affirmance entails neither an improper judicial invasion of the\\n 14\\n\\f Case: 18-10620 Document: 00514863670 Page: 15 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\nadministrative province nor a dispensation of the agency from its normal\\nresponsibility”).\\n * * *\\n The district court’s judgment is AFFIRMED.\\n\\n\\n\\n\\n 15\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4375208/\", \"author_raw\": \"GREGG COSTA, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"KING"},"judge2":{"kind":"string","value":"HIGGINSON"},"judge3":{"kind":"string","value":"COSTA"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4597955/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: TEXAS TECH PHYSICIANS ASSOCIATES, Plaintiff-Appellant v. UNITED STATES DEPARTMENT OF HEALTH AND HUMAN SERVICES; Alex M. Azar, II, Secretary, U.S. Department of Health and Human Services, Defendants-Appellees\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-07\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 18-10620 Document: 00514863670 Page: 1 Date Filed: 03/07/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\n United States Court of Appeals\n Fifth Circuit\n\n\n No. 18-10620\n FILED\n March 7, 2019\n Lyle W. Cayce\nTEXAS TECH PHYSICIANS ASSOCIATES, Clerk\n\n Plaintiff - Appellant\n\nv.\n\nUNITED STATES DEPARTMENT OF HEALTH AND HUMAN SERVICES;\nALEX M. AZAR, II, SECRETARY, U.S. DEPARTMENT OF HEALTH AND\nHUMAN SERVICES,\n\n Defendants - Appellees\n\n\n\n\n Appeal from the United States District Court\n for the Northern District of Texas\n\n\nBefore KING, HIGGINSON, and COSTA, Circuit Judges.\nGREGG COSTA, Circuit Judge:\n Medicare incentivizes services, not results. Its fee-for-service model\nrisks not only that beneficiaries may receive treatment they do not need, but\nalso that they may miss out on less expensive treatment that might help. See\nMEDICARE PAYMENT ADVISORY COMM’N, REPORT TO THE CONGRESS:\nREFORMING THE DELIVERY SYSTEM 7 (June 2008). To test whether other\napproaches could be more efficient, Congress authorizes “experiments and\ndemonstration projects” deviating from the ordinary Medicare reimbursement\nrules. 42 U.S.C. § 1395b-1. This case arises from one such demonstration\nproject, with a twist: Texas Tech Physicians Associates could keep the\n\f Case: 18-10620 Document: 00514863670 Page: 2 Date Filed: 03/07/2019\n\n\n\n No. 18-10620\nadditional fees it received for implementing the project only if its care\nmanagement model achieved cost savings. The government says Texas Tech\nfailed, and so demands return of roughly $8 million in fees. Texas Tech resists\nthat demand.\n I.\n One of the alternative payment models the Department of Health and\nHuman Services may explore is whether “payments for services other than\nthose for which payment may” ordinarily be made might reduce costs and\nimprove “utilization of services.” 42 U.S.C. § 1395b-1(a)(1)(B). Using that\nauthorization, the Center for Medicare and Medicaid Services (CMS, the\nagency within HHS that administers Medicare) solicited proposals for a “Care\nManagement for High-Cost Beneficiaries Demonstration.” CMS was looking\nfor projects to test whether “intensive management” of patients and\ncoordination between providers might improve care and reduce costs for\nMedicare beneficiaries with substantial medical needs. On top of the normal\nfees for services, participating programs could earn monthly fees contingent on\nachieving cost savings of 5%. These extra fees would count as costs.\n Texas Tech Physicians Associates—together with Texas Tech University\nHealth Sciences Center and Trailblazer Health Enterprises—submitted a\nproposal. The project would employ a “system of telephone contacts, letters,\nsite visits and physician contacts” to help manage and coordinate care for high-\nrisk beneficiaries treated at Texas Tech’s facilities. Interventions would range\nfrom home safety assessments to support groups, depending on patients’ risk\nlevels. The application indicated it expected to achieve Medicare cost savings\nof up to 25%.\n CMS took Texas Tech up on its proposal, and the parties signed a\n“demonstration agreement” in January 2006. Texas Tech agreed to implement\nthe project “as proposed in the demonstration application.” In exchange, it\n 2\n\f Case: 18-10620 Document: 00514863670 Page: 3 Date Filed: 03/07/2019\n\n\n\n No. 18-10620\nwould receive a monthly management fee of $117 per participating beneficiary.\nAnd as required by the solicitation, it agreed to be responsible for failure to\nmeet the 5% net cost savings figure, up to the amount it would receive in\nmanagement fees.\n The difficulty—then and now—was selecting an adequate control group.\nThe control group was important because cost savings would be determined by\ncomparing the costs of patients in the control group with those of Texas Tech’s\nparticipating patients, referred to as the intervention group. The\ndemonstration agreement did not itself identify a control group. Instead, CMS\nwould “contract with an independent evaluator” to “assist CMS in designing\nfeatures for a suitable comparison group.” After the contractor proposed a\nmethodology for matching a control group to the intervention group, Texas\nTech would have “the opportunity to review and agree” before beginning the\nproject.\n Agreeing on a control group proved something of a sticking point.\nFollowing an initial proposal from a contractor hired by CMS, RTI\nInternational, Texas Tech raised various concerns about the populations from\nwhich the control group would be drawn. RTI responded with changes to its\ninitial approach.\n Following months of back-and-forth, RTI sent an April 2006 memo\nsummarizing a “physician group practice-based” approach. RTI used a “loyalty\nalgorithm” to identify patients whose loyalty to a practice was similar to that\nof Texas Tech’s patients. Those beneficiaries would be eligible for inclusion in\nthe control group if they were within the 48-county area served by Texas Tech\nand had high Medicare costs or serious diseases. RTI would then randomly\nassign eligible beneficiaries to the control group such that, according to\nhistorical cost data, it was made up of low-cost, medium-cost, and high-cost\npatients in percentages nearly identical to Texas Tech’s patient population.\n 3\n\f Case: 18-10620 Document: 00514863670 Page: 4 Date Filed: 03/07/2019\n\n\n\n No. 18-10620\nTexas Tech reviewed and accepted the April 2006 methodology and began\nenrolling participants that month.\n The trouble began less than a year later. In February 2007, Actuarial\nResearch Corporation (another CMS contractor) released a report on the first\nsix months of Texas Tech’s project. After adjusting for baseline cost\ndifferences, the intervention group’s monthly per-member costs were 7%\nhigher than the control group’s. Texas Tech chalked the cost differences up to\ninconsistencies between the groups. It pointed, for instance, to two features of\nthe intervention group that it believed explained its higher costs: more deaths\nand more patients residing in nursing homes. In light of those differences,\nTexas Tech asked that the control group be adjusted. But CMS declined; it\nsaid doing so was “not feasible” and its investigation of disparities between the\ngroups did not reveal “any reasonable adjustments that could produce a match\n. . . that mitigated disparities.”\n Texas Tech then terminated the program effective July 31, 2007. The\ndemonstration agreement permitted early termination, in which event it\nrequired a prompt “final reconciliation.”\n Actuarial Research Corporation issued a reconciliation report a year\nlater. It concluded that (1) Texas Tech had received $7.99 million in\nadministrative fees; (2) Texas Tech’s savings guarantee required just over $10\nmillion in net savings—$2.05 million in cost reductions 1 plus the $7.99 million\nin fees; and (3) the intervention group’s Medicare costs were $6.79 million\nhigher than the control group’s. This meant a “savings shortfall” of $16.79\nmillion, exceeding the contingent monthly fees Texas Tech had received and\nrequiring their return in full.\n\n\n\n Because Texas Tech terminated the project early, after just 16 months, it guaranteed\n 1\n\nonly 2% cost savings, not the 5% it guaranteed after the full three years.\n 4\n\f Case: 18-10620 Document: 00514863670 Page: 5 Date Filed: 03/07/2019\n\n\n\n No. 18-10620\n Unhappy with that result, Texas Tech hired its own consultant to\ninvestigate disparities between the intervention and control groups. Its report\nraised concerns about whether the control group’s historical cost trends\nmatched the intervention group’s, and whether differences in death rates made\nthe groups a poor match. CMS asked RTI to look into those concerns, but RTI\nconcluded that the differences between the groups “cannot account for the\nestimated Texas Tech intervention effect of higher, not lower, cost growth.”\n CMS sent a letter to Texas Tech in March 2009 requesting return of the\n$7.99 million. Texas Tech demurred. Four years passed before CMS sent\nTexas Tech another letter in September 2013, renewing its demand that Texas\nTech return the money. That letter said it would represent CMS’s “final\ndecision” unless Texas Tech appealed to HHS’s Departmental Appeals Board.\n Texas Tech did appeal to the Board, only to promptly ask for dismissal\nof its appeal. It argued that the demonstration agreement was a procurement\ncontract and thus governed by the Contract Disputes Act, 41 U.S.C. §§ 7101–\n09, which would mean the Board was not the proper forum for resolving this\ndispute. It also argued that the Act’s six-year statute of limitations barred\nCMS’s delayed attempt to collect the debt. The Board denied Texas Tech’s\nmotion to dismiss, holding that the demonstration agreement was a grant\nagreement rather than a procurement contract.\n In the merits appeal that followed, Texas Tech raised a variety of\ncontract theories to avoid CMS’s demand for repayment, including three\nalleged breaches of the agreement as well as common law defenses like mistake\nand impossibility. In a thorough opinion, the Board rejected those arguments\nin part because it determined that “[c]ommon law contract theories are\ninapplicable” to grant agreements. In light of this view, whether CMS\nbreached the agreement mattered only insofar as the demonstration\nagreement conditioned Texas Tech’s repayment obligation on CMS’s\n 5\n\f Case: 18-10620 Document: 00514863670 Page: 6 Date Filed: 03/07/2019\n\n\n\n No. 18-10620\nperformance. And in addition to finding that none of Texas Tech’s allegations\nwould have affected its duty to meet the cost savings target, the Board\ndetermined that CMS complied with the agreement.\n Texas Tech sought further review by suing HHS under the\nAdministrative Procedure Act, asking the district court to set aside the Board’s\ndecision and enjoin CMS from enforcing its demand. 2 On competing summary\njudgment motions, the district court ruled that Texas Tech had not met its\nburden under the APA and granted HHS’s motion. Texas Tech appeals.\n II.\n Texas Tech first argues that the HHS Departmental Appeals Board\nshould not have heard this case. That is because, in its view, the\ndemonstration agreement was a procurement contract governed by the\nContract Disputes Act. See 41 U.S.C. § 7102(a)(2). If that statute applies, it\naffects where and when this dispute should have been resolved. Disputes over\ngovernment procurement contracts start with presenting a claim to the\nappropriate contracting officer. Id. § 7103(a). Any such claim—whether by the\ngovernment or a private party—must be presented within six years. Id.\n§ 7103(a)(4)(A). If a party to the contract disagrees with the contracting\nofficer’s decision, it may appeal to the Civilian Board of Contract Appeals or\nthe Court of Federal Claims, id. §§ 7104, 7105(b), but not to “any [other] forum,\ntribunal, or Federal Government agency,” id. § 7103(g). So if the\ndemonstration agreement was a procurement contract, then the government\n\n\n\n\n 2 Other circuits have held that contract claims seeking equitable or declaratory relief\nare “impliedly forbid[den]” under the APA. 5 U.S.C. § 702; see, e.g., Transohio Sav. Bank v.\nDir., Office of Thrift Supervision, 967 F.2d 598, 609 (D.C. Cir. 1992). But when we asked for\nsupplemental briefing, both parties agreed that the APA permits review of disputes about\ngrant agreements. So we will consider this grant dispute under the APA, as we have before.\nSee Delta Found., Inc. v. United States, 303 F.3d 551, 563 (5th Cir. 2002); Inst. for Tech. Dev.\nv. Brown, 63 F.3d 445, 449–50 (5th Cir. 1995).\n 6\n\f Case: 18-10620 Document: 00514863670 Page: 7 Date Filed: 03/07/2019\n\n\n\n No. 18-10620\nmay have been late in seeking return of the fees, and the Board lacked\njurisdiction.\n But none of the Contract Disputes Act’s requirements matters if the\nBoard correctly determined that the demonstration agreement was not a\nprocurement contract but instead a grant agreement. See id. § 7102(a)(2)\n(specifying the types of government contracts to which the CDA applies,\nincluding those for the “procurement of services”); Coastal Corp. v. United\nStates, 713 F.2d 728, 730 (Fed. Cir. 1983) (“[The CDA] does not cover all\ngovernment contracts.”). The Federal Circuit, well versed in government\ncontract disputes, looks to the Federal Grant and Cooperative Agreement Act\nwhen characterizing government agreements. See, e.g., Hymas v. United\nStates, 810 F.3d 1312, 1325–26 (Fed. Cir. 2016). So do the parties.\n That statute says executive agencies must use procurement contracts\nwhen:\n the principle purpose of the instrument is to acquire (by purchase,\n lease, or barter) property or services for the direct benefit or use of\n the United States government.\n31 U.S.C. § 6303(1). An example is a Navy contract for purchase of a ship. The\ngovernment gets to use what it purchased.\n In contrast, agencies must use a grant agreement when:\n the principle purpose of the relationship is to transfer a thing of\n value to the State or local government or other recipient to carry\n out a public purpose of support or stimulation . . . instead of\n acquiring (by purchase, lease, or barter) property or services for\n the direct benefit or use of the United States Government.\nId. § 6304(1). An example is an agreement with a school district to provide free\nschool lunches. The federal government pays for the lunches, but students\nreceive the benefit.\n We agree with the Board that the demonstration agreement was not a\nprocurement contract. The “direct” benefits of the agreement ran to the\n 7\n\f Case: 18-10620 Document: 00514863670 Page: 8 Date Filed: 03/07/2019\n\n\n\n No. 18-10620\nMedicare beneficiaries participating in Texas Tech’s program, not to CMS. See\nUnited States v. Univ. Hosp. of State Univ. of N.Y. at Stony Brook, 575 F. Supp.\n607, 612–13 (E.D.N.Y. 1983) (distinguishing procurement contracts from\nagreements to reimburse hospitals because “a hospital receiving\nreimbursements under Medicaid or Medicare provides services directly to the\npublic”). CMS hoped to gain insight into how best to operate Medicare for high-\ncost beneficiaries, but advancing an “agency’s overall mission” (something that\none would hope all grant agreements do) is not a direct benefit. Hymas, 810\nF.3d at 1328. And CMS would not achieve any cost savings directly. The\nsavings would have resulted—had the project gone as hoped—from Texas\nTech’s making participating beneficiaries healthier, thereby decreasing their\nneed for Medicare services. 3\n The Board had jurisdiction.\n III.\n Under the APA, the Board’s action may be set aside if “arbitrary,\ncapricious, an abuse of discretion, or otherwise not in accordance with law.” 5\nU.S.C. § 706(2)(A). An agency’s decision is presumptively valid; the plaintiff\nbears the burden of showing otherwise. Texas Clinical Labs, Inc. v. Sebelius,\n612 F.3d 771, 775 (5th Cir. 2010). We defer to the agency’s findings of fact if\nthey are supported by substantial evidence. Buffalo Marine Servs. Inc. v.\nUnited States, 663 F.3d 750, 753–54 (5th Cir. 2011). On questions of law, our\n\n\n\n 3There may be instances when an agency “acquires” services for its own direct benefit,\neven though the services are conferred on third parties, such as when it outsources services\nit would otherwise perform. See, e.g., CMS Contract Mgmt. Servs. v. Mass. Housing Fin.\nAgency, 745 F.3d 1379, 1385–85 (Fed. Cir. 2014) (holding that HUD’s agreements with\nhousing authorities, under which authorities would administer Section 8 payments, were\nprocurement contracts). But this is not an outsourcing case. There is a difference between\nan agency that hires a company to perform administrative tasks the government would\notherwise have to perform, see id., and CMS’s paying doctors and hospitals to benefit\nMedicare patients.\n 8\n\f Case: 18-10620 Document: 00514863670 Page: 9 Date Filed: 03/07/2019\n\n\n\n No. 18-10620\ndegree of deference varies according to the source of law. Although we give\nChevron deference to an agency’s interpretation of an ambiguous statute it\nadministers, Memorial Hermann Hosp. v. Sebelius, 728 F.3d 400, 405 (5th Cir.\n2013), when an agency makes other conclusions of law—including interpreting\n“contractual agreements”—our review is “effectively de novo,” Inst. for Tech\nDev. v. Brown, 63 F.3d 445, 450 (5th Cir. 1995).\n A.\n Underlying all of its merits arguments is Texas Tech’s objection to the\nBoard’s characterization of the demonstration agreement as something other\nthan a contract. Although the Board acknowledged that “the terms of a grant\nagreement are binding on both the grantee and the grantor,” Brown, 63 F.3d\nat 449, it concluded that “contract law doctrines do not dictate its analysis or\nresolution of disputes involving federal grants.” Several cases support that\nproposition. See, e.g., Bennett v. Ky. Dep’t of Educ., 470 U.S. 656, 669 (1985)\n(“Although we agree with the State that Title I grant agreements had a\ncontractual aspect, the program cannot be viewed in the same manner as a\nbilateral contract governing a discrete transaction.” (citation omitted)); United\nStates v. Melendez, 944 F.2d 216, 219 (5th Cir. 1991) (holding that “contract\nprinciples do not apply” in dispute over federal scholarship agreement).\n Texas Tech attempts to distinguish those decisions as limited to federal\ngrants in which the parties’ obligations are dictated by statute or regulation,\nas opposed to the terms of a separately negotiated grant agreement. But we\nultimately need not resolve whether the Board erred in suggesting that the\ncommon law of contracts never informs grant disputes. Even if it did, the\n\n\n\n\n 9\n\f Case: 18-10620 Document: 00514863670 Page: 10 Date Filed: 03/07/2019\n\n\n\n No. 18-10620\nBoard made valid findings justifying the rejection of Texas Tech’s various\ncontract theories. 4\n B.\n Texas Tech’s most forceful complaint is that patients in the control group\nwere too dissimilar from patients in the intervention group—that is, that CMS\nbreached the demonstration agreement by failing to provide an appropriately\nmatched control group.\n This is what the agreement said about selection of the control group:\n For a matched control cohort, the evaluator will specify the\n approach to be used in identifying such cohort. For each site that\n is not randomized, attention will be given to ensuring that the\n matched control cohort represents an appropriate comparison\n group that is specific to the intervention mode. [Texas Tech] will\n have the opportunity to review and agree to the approach that is\n proposed by the evaluator and CMS. CMS and [Texas Tech] will\n mutually agree upon the criteria and methodology used to select\n the relevant comparison group pursuant to a memorandum from\n the evaluation contractor documenting these methods and written\n documentation from [Texas Tech] stating its agreement with such\n memorandum.\nThe agreement thus required that “attention” be given to “ensuring” the\ncontrol group was sufficiently matched to the intervention group. It further\nexplains how that would be done: CMS’s obligation was to select a third-party\nevaluator, which would propose an “approach” for choosing a control group.\nTexas Tech had to review and agree to that approach before starting the\nproject.\n\n\n\n\n 4Typically, when an agency reaches a decision based on erroneous reasoning, the\nChenery doctrine prohibits a reviewing court from upholding that decision for an alternative\nreason. Motor Vehicle Mfrs. Assoc. v. State Farm Mut. Auto Ins. Co., 463 U.S. 29, 50 (1983);\nSEC v. Chenery Corp., 332 U.S. 194, 196 (1947). But when an agency gives multiple reasons,\nwe may uphold its decision based on any one of those reasons. Salt River Project Agr. Imp.\n& Power Dist. v. United States, 762 F.2d 1053, 1060 n.8 (D.C. Cir. 1985).\n 10\n\f Case: 18-10620 Document: 00514863670 Page: 11 Date Filed: 03/07/2019\n\n\n\n No. 18-10620\n So agreement by the parties on “criteria and methodology” was the\nmechanism for ensuring adequacy of the control group, not after-the-fact\nassessment of whether the control group had an unspecified degree of\nsimilarity with the intervention group. Texas Tech invoked its right to\ninfluence the selection criteria, engaging in months of back-and-forth to flesh\nout the details. The agreement did not require more than that for selection of\nthe control group.\n C.\n Texas Tech next argues that CMS breached the agreement by refusing\nto allow it to access relevant Medicare claims data. In apparent response to\nTexas Tech’s request to obtain this information from Trailblazer—a partner in\nthe project—CMS told Texas Tech (1) that it could not obtain Trailblazer data\nin order to create its own “pseudo” control group; and (2) that it could not obtain\nTrailblazer data on patients in the intervention group without submitting a\ndata use agreement and getting it approved by CMS. CMS did eventually\napprove a data use agreement between Texas Tech and Trailblazer, but not\nuntil May 2007, two months before Texas Tech terminated the project. Texas\nTech’s idea is that had it been armed with Trailblazer data sooner, it could\nhave better monitored its own performance as well as the accuracy of the\ncontrol group.\n Attempting to locate its right to Trailblazer data in the demonstration\nagreement, Texas Tech points to its project proposal. In it, Texas Tech\nsuggested that claims data would be available to it from the “Fiscal\nIntermediary Standard System,” one of several sources of data it might use to\ntarget its care management interventions. Because the agreement required\nTexas Tech to “implement the care management program as proposed,” Texas\nTech claims a right to access and use data from fiscal intermediaries, including\nTrailblazer.\n 11\n\f Case: 18-10620 Document: 00514863670 Page: 12 Date Filed: 03/07/2019\n\n\n\n No. 18-10620\n We agree with the Board that CMS’s declining or delaying Texas Tech’s\naccess to Trailblazer data did not violate the demonstration agreement. Even\nif the proposal indicated that Texas Tech intended to use Trailblazer’s claims\ndata, the agreement incorporated the proposal to specify the details of the\nproject Texas Tech agreed to implement. The proposal thus became a Texas\nTech obligation, not a CMS obligation, so CMS could not have violated it. To\nbe clear, the agreement (as opposed to the proposal) did impose data-related\nobligations on CMS. CMS had to give Texas Tech demographic information\nand claims data on the intervention group going back 12 months, but Texas\nTech does not claim CMS failed to do so. Nothing in the agreement obligated\nCMS to give Texas Tech access to additional data from fiscal intermediaries.\nTo the contrary, the only relevant provision in the agreement said that if Texas\nTech “wishes to receive additional data . . . from an FI,” it must notify CMS,\nwhich would decide only “if such information can be provided.”\n Texas Tech’s argument faces another problem. Even if we were to read\nthe agreement to require CMS to allow Texas Tech access to Trailblazer data,\nthat requirement would extend only to data on the intervention group—the\nproposal said nothing about using fiscal intermediary data for purposes other\nthan honing Texas Tech’s care management interventions. And the Board\nfound that under HHS privacy regulations, CMS could not have allowed Texas\nTech to access Trailblazer’s claims data on the intervention group without a\ndata use agreement. See 45 C.F.R. § 164.514(e)(3)(i), (4)(i) (permitting a\n“covered entity” to disclose medical data “only if the covered entity obtains\nsatisfactory assurance, in the form of a data use agreement” that the recipient\nwill use the data “for limited purposes”). Texas Tech does not dispute that. It\nhas not met its burden of showing that the Board’s ruling on this issue should\nbe set aside.\n\n\n 12\n\f Case: 18-10620 Document: 00514863670 Page: 13 Date Filed: 03/07/2019\n\n\n\n No. 18-10620\n D.\n Texas Tech also contends that CMS breached the demonstration\nagreement by engaging RTI to evaluate whether differences between the\nintervention and control groups may have accounted for the apparent lack of\ncost savings. Because RTI designed the parameters for the control group,\nTexas Tech contends it had a conflict of interest in checking its work.\n But the only time RTI analyzed the alleged disparities in the groups was\nafter Texas Tech had terminated the project, Actuarial Research Corporation\nhad conducted the final reconciliation, and Texas Tech had alleged that the\nstudy was flawed. The demonstration agreement imposes no post-\nreconciliation obligations on CMS, so CMS cannot have breached the\nagreement by asking RTI to look into Texas Tech’s concerns. 5\n E.\n In addition to its breach arguments, Texas Tech asserted a variety of\ncommon law contract doctrines before the Board. The Board did not expressly\naddress two of them—mistake and impracticability 6—because of its view that\nthose common law principles do not apply to grant agreements.\n But the Board did make findings that doom those two defenses. It found,\nbased on the months of negotiation over criteria for the control group, that\nTexas Tech “proceeded despite its concerns” and “could not reasonably have\nfailed to understand . . . that it had assumed the financial risks associated with\n\n\n\n 5 Before the Board, Texas Tech framed its conflict-of-interest theory as a breach of the\nimplied covenant of good faith and fair dealing, not a breach of the demonstration\nagreement’s explicit terms. But even if the implied covenant can apply to grant agreements,\nit cannot “expand another party’s contractual duties beyond those in the express contract.”\nAgility Pub. Warehousing Co. KSCP v. Mattis, 852 F.3d 1370, 1384 (Fed. Cir. 2017) (cleaned\nup). The same goes for Texas Tech’s argument to the Board that CMS breached the implied\ncovenant by failing to create a more accurate control group.\n 6 The Board did alternatively reject the merits of two others: failure to disclose and\n\nestoppel. Texas Tech does not challenge those conclusions.\n 13\n\f Case: 18-10620 Document: 00514863670 Page: 14 Date Filed: 03/07/2019\n\n\n\n No. 18-10620\nshortcomings in study design and implementation.” That undermines Texas\nTech’s mistake theory; Texas Tech assumed the risk by agreeing to perform\nthe demonstration, knowing that the control group might have problems.\nRESTATEMENT (SECOND) OF CONTRACTS § 154(b). It also undermines Texas\nTech’s impracticability theory because it shows that the accuracy of the control\ngroup was not a “basic assumption” of the parties’ agreement. Id. § 261.\n Although the Board did not make these findings in the context of\ndiscussing mistake and impracticability, they would defeat those defenses had\nthe Board directly addressed them. As a result, and because substantial\nevidence supports these findings, any error was harmless. See Shinseki v.\nSanders, 556 U.S. 396, 411 (2009) (clarifying that administrative harmless\nerror analysis turns on, among other things, the “likelihood that the result\nwould have been different” but for the error). The administrative harmless\nerror rule can sit uneasily alongside the Chenery doctrine, which typically\nconfines judicial review to the agency’s reasoning. See Nicholas Bagley,\nRemedial Restraint in Administrative Law, 117 COLUM. L. REV. 253, 302–07\n(2017). But that tension arises when a reviewing court makes findings the\nagency should have made in the first instance. See id. at 305 (observing\n“controversial[]” cases upholding agency decisions when “the evidence in the\nrecord so strongly supports the result that the court is confident the agency\nwould reach the same decision on remand”). Chenery cautions against\nintruding onto an agency’s turf, not against giving an agency’s own findings\ntheir obvious effect. See Henry J. Friendly, Chenery Revisited: Reflections on\nReversal and Remand of Administrative Orders, 1969 DUKE L.J. 199, 211\n(explaining that remand to an agency is “necessary only when the reviewing\ncourt concludes that there is a significant chance that but for the error the\nagency might have reached a different result” because “in the absence of such\na possibility, affirmance entails neither an improper judicial invasion of the\n 14\n\f Case: 18-10620 Document: 00514863670 Page: 15 Date Filed: 03/07/2019\n\n\n\n No. 18-10620\nadministrative province nor a dispensation of the agency from its normal\nresponsibility”).\n * * *\n The district court’s judgment is AFFIRMED.\n\n\n\n\n 15\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: TEXAS TECH PHYSICIANS ASSOCIATES, Plaintiff-Appellant v. UNITED STATES DEPARTMENT OF HEALTH AND HUMAN SERVICES; Alex M. Azar, II, Secretary, U.S. Department of Health and Human Services, Defendants-Appellees\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-07\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 18-10620 Document: 00514863670 Page: 1 Date Filed: 03/07/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n\\n No. 18-10620\\n FILED\\n March 7, 2019\\n Lyle W. Cayce\\nTEXAS TECH PHYSICIANS ASSOCIATES, Clerk\\n\\n Plaintiff - Appellant\\n\\nv.\\n\\nUNITED STATES DEPARTMENT OF HEALTH AND HUMAN SERVICES;\\nALEX M. AZAR, II, SECRETARY, U.S. DEPARTMENT OF HEALTH AND\\nHUMAN SERVICES,\\n\\n Defendants - Appellees\\n\\n\\n\\n\\n Appeal from the United States District Court\\n for the Northern District of Texas\\n\\n\\nBefore KING, HIGGINSON, and COSTA, Circuit Judges.\\nGREGG COSTA, Circuit Judge:\\n Medicare incentivizes services, not results. Its fee-for-service model\\nrisks not only that beneficiaries may receive treatment they do not need, but\\nalso that they may miss out on less expensive treatment that might help. See\\nMEDICARE PAYMENT ADVISORY COMM’N, REPORT TO THE CONGRESS:\\nREFORMING THE DELIVERY SYSTEM 7 (June 2008). To test whether other\\napproaches could be more efficient, Congress authorizes “experiments and\\ndemonstration projects” deviating from the ordinary Medicare reimbursement\\nrules. 42 U.S.C. § 1395b-1. This case arises from one such demonstration\\nproject, with a twist: Texas Tech Physicians Associates could keep the\\n\\f Case: 18-10620 Document: 00514863670 Page: 2 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\nadditional fees it received for implementing the project only if its care\\nmanagement model achieved cost savings. The government says Texas Tech\\nfailed, and so demands return of roughly $8 million in fees. Texas Tech resists\\nthat demand.\\n I.\\n One of the alternative payment models the Department of Health and\\nHuman Services may explore is whether “payments for services other than\\nthose for which payment may” ordinarily be made might reduce costs and\\nimprove “utilization of services.” 42 U.S.C. § 1395b-1(a)(1)(B). Using that\\nauthorization, the Center for Medicare and Medicaid Services (CMS, the\\nagency within HHS that administers Medicare) solicited proposals for a “Care\\nManagement for High-Cost Beneficiaries Demonstration.” CMS was looking\\nfor projects to test whether “intensive management” of patients and\\ncoordination between providers might improve care and reduce costs for\\nMedicare beneficiaries with substantial medical needs. On top of the normal\\nfees for services, participating programs could earn monthly fees contingent on\\nachieving cost savings of 5%. These extra fees would count as costs.\\n Texas Tech Physicians Associates—together with Texas Tech University\\nHealth Sciences Center and Trailblazer Health Enterprises—submitted a\\nproposal. The project would employ a “system of telephone contacts, letters,\\nsite visits and physician contacts” to help manage and coordinate care for high-\\nrisk beneficiaries treated at Texas Tech’s facilities. Interventions would range\\nfrom home safety assessments to support groups, depending on patients’ risk\\nlevels. The application indicated it expected to achieve Medicare cost savings\\nof up to 25%.\\n CMS took Texas Tech up on its proposal, and the parties signed a\\n“demonstration agreement” in January 2006. Texas Tech agreed to implement\\nthe project “as proposed in the demonstration application.” In exchange, it\\n 2\\n\\f Case: 18-10620 Document: 00514863670 Page: 3 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\nwould receive a monthly management fee of $117 per participating beneficiary.\\nAnd as required by the solicitation, it agreed to be responsible for failure to\\nmeet the 5% net cost savings figure, up to the amount it would receive in\\nmanagement fees.\\n The difficulty—then and now—was selecting an adequate control group.\\nThe control group was important because cost savings would be determined by\\ncomparing the costs of patients in the control group with those of Texas Tech’s\\nparticipating patients, referred to as the intervention group. The\\ndemonstration agreement did not itself identify a control group. Instead, CMS\\nwould “contract with an independent evaluator” to “assist CMS in designing\\nfeatures for a suitable comparison group.” After the contractor proposed a\\nmethodology for matching a control group to the intervention group, Texas\\nTech would have “the opportunity to review and agree” before beginning the\\nproject.\\n Agreeing on a control group proved something of a sticking point.\\nFollowing an initial proposal from a contractor hired by CMS, RTI\\nInternational, Texas Tech raised various concerns about the populations from\\nwhich the control group would be drawn. RTI responded with changes to its\\ninitial approach.\\n Following months of back-and-forth, RTI sent an April 2006 memo\\nsummarizing a “physician group practice-based” approach. RTI used a “loyalty\\nalgorithm” to identify patients whose loyalty to a practice was similar to that\\nof Texas Tech’s patients. Those beneficiaries would be eligible for inclusion in\\nthe control group if they were within the 48-county area served by Texas Tech\\nand had high Medicare costs or serious diseases. RTI would then randomly\\nassign eligible beneficiaries to the control group such that, according to\\nhistorical cost data, it was made up of low-cost, medium-cost, and high-cost\\npatients in percentages nearly identical to Texas Tech’s patient population.\\n 3\\n\\f Case: 18-10620 Document: 00514863670 Page: 4 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\nTexas Tech reviewed and accepted the April 2006 methodology and began\\nenrolling participants that month.\\n The trouble began less than a year later. In February 2007, Actuarial\\nResearch Corporation (another CMS contractor) released a report on the first\\nsix months of Texas Tech’s project. After adjusting for baseline cost\\ndifferences, the intervention group’s monthly per-member costs were 7%\\nhigher than the control group’s. Texas Tech chalked the cost differences up to\\ninconsistencies between the groups. It pointed, for instance, to two features of\\nthe intervention group that it believed explained its higher costs: more deaths\\nand more patients residing in nursing homes. In light of those differences,\\nTexas Tech asked that the control group be adjusted. But CMS declined; it\\nsaid doing so was “not feasible” and its investigation of disparities between the\\ngroups did not reveal “any reasonable adjustments that could produce a match\\n. . . that mitigated disparities.”\\n Texas Tech then terminated the program effective July 31, 2007. The\\ndemonstration agreement permitted early termination, in which event it\\nrequired a prompt “final reconciliation.”\\n Actuarial Research Corporation issued a reconciliation report a year\\nlater. It concluded that (1) Texas Tech had received $7.99 million in\\nadministrative fees; (2) Texas Tech’s savings guarantee required just over $10\\nmillion in net savings—$2.05 million in cost reductions 1 plus the $7.99 million\\nin fees; and (3) the intervention group’s Medicare costs were $6.79 million\\nhigher than the control group’s. This meant a “savings shortfall” of $16.79\\nmillion, exceeding the contingent monthly fees Texas Tech had received and\\nrequiring their return in full.\\n\\n\\n\\n Because Texas Tech terminated the project early, after just 16 months, it guaranteed\\n 1\\n\\nonly 2% cost savings, not the 5% it guaranteed after the full three years.\\n 4\\n\\f Case: 18-10620 Document: 00514863670 Page: 5 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\n Unhappy with that result, Texas Tech hired its own consultant to\\ninvestigate disparities between the intervention and control groups. Its report\\nraised concerns about whether the control group’s historical cost trends\\nmatched the intervention group’s, and whether differences in death rates made\\nthe groups a poor match. CMS asked RTI to look into those concerns, but RTI\\nconcluded that the differences between the groups “cannot account for the\\nestimated Texas Tech intervention effect of higher, not lower, cost growth.”\\n CMS sent a letter to Texas Tech in March 2009 requesting return of the\\n$7.99 million. Texas Tech demurred. Four years passed before CMS sent\\nTexas Tech another letter in September 2013, renewing its demand that Texas\\nTech return the money. That letter said it would represent CMS’s “final\\ndecision” unless Texas Tech appealed to HHS’s Departmental Appeals Board.\\n Texas Tech did appeal to the Board, only to promptly ask for dismissal\\nof its appeal. It argued that the demonstration agreement was a procurement\\ncontract and thus governed by the Contract Disputes Act, 41 U.S.C. §§ 7101–\\n09, which would mean the Board was not the proper forum for resolving this\\ndispute. It also argued that the Act’s six-year statute of limitations barred\\nCMS’s delayed attempt to collect the debt. The Board denied Texas Tech’s\\nmotion to dismiss, holding that the demonstration agreement was a grant\\nagreement rather than a procurement contract.\\n In the merits appeal that followed, Texas Tech raised a variety of\\ncontract theories to avoid CMS’s demand for repayment, including three\\nalleged breaches of the agreement as well as common law defenses like mistake\\nand impossibility. In a thorough opinion, the Board rejected those arguments\\nin part because it determined that “[c]ommon law contract theories are\\ninapplicable” to grant agreements. In light of this view, whether CMS\\nbreached the agreement mattered only insofar as the demonstration\\nagreement conditioned Texas Tech’s repayment obligation on CMS’s\\n 5\\n\\f Case: 18-10620 Document: 00514863670 Page: 6 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\nperformance. And in addition to finding that none of Texas Tech’s allegations\\nwould have affected its duty to meet the cost savings target, the Board\\ndetermined that CMS complied with the agreement.\\n Texas Tech sought further review by suing HHS under the\\nAdministrative Procedure Act, asking the district court to set aside the Board’s\\ndecision and enjoin CMS from enforcing its demand. 2 On competing summary\\njudgment motions, the district court ruled that Texas Tech had not met its\\nburden under the APA and granted HHS’s motion. Texas Tech appeals.\\n II.\\n Texas Tech first argues that the HHS Departmental Appeals Board\\nshould not have heard this case. That is because, in its view, the\\ndemonstration agreement was a procurement contract governed by the\\nContract Disputes Act. See 41 U.S.C. § 7102(a)(2). If that statute applies, it\\naffects where and when this dispute should have been resolved. Disputes over\\ngovernment procurement contracts start with presenting a claim to the\\nappropriate contracting officer. Id. § 7103(a). Any such claim—whether by the\\ngovernment or a private party—must be presented within six years. Id.\\n§ 7103(a)(4)(A). If a party to the contract disagrees with the contracting\\nofficer’s decision, it may appeal to the Civilian Board of Contract Appeals or\\nthe Court of Federal Claims, id. §§ 7104, 7105(b), but not to “any [other] forum,\\ntribunal, or Federal Government agency,” id. § 7103(g). So if the\\ndemonstration agreement was a procurement contract, then the government\\n\\n\\n\\n\\n 2 Other circuits have held that contract claims seeking equitable or declaratory relief\\nare “impliedly forbid[den]” under the APA. 5 U.S.C. § 702; see, e.g., Transohio Sav. Bank v.\\nDir., Office of Thrift Supervision, 967 F.2d 598, 609 (D.C. Cir. 1992). But when we asked for\\nsupplemental briefing, both parties agreed that the APA permits review of disputes about\\ngrant agreements. So we will consider this grant dispute under the APA, as we have before.\\nSee Delta Found., Inc. v. United States, 303 F.3d 551, 563 (5th Cir. 2002); Inst. for Tech. Dev.\\nv. Brown, 63 F.3d 445, 449–50 (5th Cir. 1995).\\n 6\\n\\f Case: 18-10620 Document: 00514863670 Page: 7 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\nmay have been late in seeking return of the fees, and the Board lacked\\njurisdiction.\\n But none of the Contract Disputes Act’s requirements matters if the\\nBoard correctly determined that the demonstration agreement was not a\\nprocurement contract but instead a grant agreement. See id. § 7102(a)(2)\\n(specifying the types of government contracts to which the CDA applies,\\nincluding those for the “procurement of services”); Coastal Corp. v. United\\nStates, 713 F.2d 728, 730 (Fed. Cir. 1983) (“[The CDA] does not cover all\\ngovernment contracts.”). The Federal Circuit, well versed in government\\ncontract disputes, looks to the Federal Grant and Cooperative Agreement Act\\nwhen characterizing government agreements. See, e.g., Hymas v. United\\nStates, 810 F.3d 1312, 1325–26 (Fed. Cir. 2016). So do the parties.\\n That statute says executive agencies must use procurement contracts\\nwhen:\\n the principle purpose of the instrument is to acquire (by purchase,\\n lease, or barter) property or services for the direct benefit or use of\\n the United States government.\\n31 U.S.C. § 6303(1). An example is a Navy contract for purchase of a ship. The\\ngovernment gets to use what it purchased.\\n In contrast, agencies must use a grant agreement when:\\n the principle purpose of the relationship is to transfer a thing of\\n value to the State or local government or other recipient to carry\\n out a public purpose of support or stimulation . . . instead of\\n acquiring (by purchase, lease, or barter) property or services for\\n the direct benefit or use of the United States Government.\\nId. § 6304(1). An example is an agreement with a school district to provide free\\nschool lunches. The federal government pays for the lunches, but students\\nreceive the benefit.\\n We agree with the Board that the demonstration agreement was not a\\nprocurement contract. The “direct” benefits of the agreement ran to the\\n 7\\n\\f Case: 18-10620 Document: 00514863670 Page: 8 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\nMedicare beneficiaries participating in Texas Tech’s program, not to CMS. See\\nUnited States v. Univ. Hosp. of State Univ. of N.Y. at Stony Brook, 575 F. Supp.\\n607, 612–13 (E.D.N.Y. 1983) (distinguishing procurement contracts from\\nagreements to reimburse hospitals because “a hospital receiving\\nreimbursements under Medicaid or Medicare provides services directly to the\\npublic”). CMS hoped to gain insight into how best to operate Medicare for high-\\ncost beneficiaries, but advancing an “agency’s overall mission” (something that\\none would hope all grant agreements do) is not a direct benefit. Hymas, 810\\nF.3d at 1328. And CMS would not achieve any cost savings directly. The\\nsavings would have resulted—had the project gone as hoped—from Texas\\nTech’s making participating beneficiaries healthier, thereby decreasing their\\nneed for Medicare services. 3\\n The Board had jurisdiction.\\n III.\\n Under the APA, the Board’s action may be set aside if “arbitrary,\\ncapricious, an abuse of discretion, or otherwise not in accordance with law.” 5\\nU.S.C. § 706(2)(A). An agency’s decision is presumptively valid; the plaintiff\\nbears the burden of showing otherwise. Texas Clinical Labs, Inc. v. Sebelius,\\n612 F.3d 771, 775 (5th Cir. 2010). We defer to the agency’s findings of fact if\\nthey are supported by substantial evidence. Buffalo Marine Servs. Inc. v.\\nUnited States, 663 F.3d 750, 753–54 (5th Cir. 2011). On questions of law, our\\n\\n\\n\\n 3There may be instances when an agency “acquires” services for its own direct benefit,\\neven though the services are conferred on third parties, such as when it outsources services\\nit would otherwise perform. See, e.g., CMS Contract Mgmt. Servs. v. Mass. Housing Fin.\\nAgency, 745 F.3d 1379, 1385–85 (Fed. Cir. 2014) (holding that HUD’s agreements with\\nhousing authorities, under which authorities would administer Section 8 payments, were\\nprocurement contracts). But this is not an outsourcing case. There is a difference between\\nan agency that hires a company to perform administrative tasks the government would\\notherwise have to perform, see id., and CMS’s paying doctors and hospitals to benefit\\nMedicare patients.\\n 8\\n\\f Case: 18-10620 Document: 00514863670 Page: 9 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\ndegree of deference varies according to the source of law. Although we give\\nChevron deference to an agency’s interpretation of an ambiguous statute it\\nadministers, Memorial Hermann Hosp. v. Sebelius, 728 F.3d 400, 405 (5th Cir.\\n2013), when an agency makes other conclusions of law—including interpreting\\n“contractual agreements”—our review is “effectively de novo,” Inst. for Tech\\nDev. v. Brown, 63 F.3d 445, 450 (5th Cir. 1995).\\n A.\\n Underlying all of its merits arguments is Texas Tech’s objection to the\\nBoard’s characterization of the demonstration agreement as something other\\nthan a contract. Although the Board acknowledged that “the terms of a grant\\nagreement are binding on both the grantee and the grantor,” Brown, 63 F.3d\\nat 449, it concluded that “contract law doctrines do not dictate its analysis or\\nresolution of disputes involving federal grants.” Several cases support that\\nproposition. See, e.g., Bennett v. Ky. Dep’t of Educ., 470 U.S. 656, 669 (1985)\\n(“Although we agree with the State that Title I grant agreements had a\\ncontractual aspect, the program cannot be viewed in the same manner as a\\nbilateral contract governing a discrete transaction.” (citation omitted)); United\\nStates v. Melendez, 944 F.2d 216, 219 (5th Cir. 1991) (holding that “contract\\nprinciples do not apply” in dispute over federal scholarship agreement).\\n Texas Tech attempts to distinguish those decisions as limited to federal\\ngrants in which the parties’ obligations are dictated by statute or regulation,\\nas opposed to the terms of a separately negotiated grant agreement. But we\\nultimately need not resolve whether the Board erred in suggesting that the\\ncommon law of contracts never informs grant disputes. Even if it did, the\\n\\n\\n\\n\\n 9\\n\\f Case: 18-10620 Document: 00514863670 Page: 10 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\nBoard made valid findings justifying the rejection of Texas Tech’s various\\ncontract theories. 4\\n B.\\n Texas Tech’s most forceful complaint is that patients in the control group\\nwere too dissimilar from patients in the intervention group—that is, that CMS\\nbreached the demonstration agreement by failing to provide an appropriately\\nmatched control group.\\n This is what the agreement said about selection of the control group:\\n For a matched control cohort, the evaluator will specify the\\n approach to be used in identifying such cohort. For each site that\\n is not randomized, attention will be given to ensuring that the\\n matched control cohort represents an appropriate comparison\\n group that is specific to the intervention mode. [Texas Tech] will\\n have the opportunity to review and agree to the approach that is\\n proposed by the evaluator and CMS. CMS and [Texas Tech] will\\n mutually agree upon the criteria and methodology used to select\\n the relevant comparison group pursuant to a memorandum from\\n the evaluation contractor documenting these methods and written\\n documentation from [Texas Tech] stating its agreement with such\\n memorandum.\\nThe agreement thus required that “attention” be given to “ensuring” the\\ncontrol group was sufficiently matched to the intervention group. It further\\nexplains how that would be done: CMS’s obligation was to select a third-party\\nevaluator, which would propose an “approach” for choosing a control group.\\nTexas Tech had to review and agree to that approach before starting the\\nproject.\\n\\n\\n\\n\\n 4Typically, when an agency reaches a decision based on erroneous reasoning, the\\nChenery doctrine prohibits a reviewing court from upholding that decision for an alternative\\nreason. Motor Vehicle Mfrs. Assoc. v. State Farm Mut. Auto Ins. Co., 463 U.S. 29, 50 (1983);\\nSEC v. Chenery Corp., 332 U.S. 194, 196 (1947). But when an agency gives multiple reasons,\\nwe may uphold its decision based on any one of those reasons. Salt River Project Agr. Imp.\\n& Power Dist. v. United States, 762 F.2d 1053, 1060 n.8 (D.C. Cir. 1985).\\n 10\\n\\f Case: 18-10620 Document: 00514863670 Page: 11 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\n So agreement by the parties on “criteria and methodology” was the\\nmechanism for ensuring adequacy of the control group, not after-the-fact\\nassessment of whether the control group had an unspecified degree of\\nsimilarity with the intervention group. Texas Tech invoked its right to\\ninfluence the selection criteria, engaging in months of back-and-forth to flesh\\nout the details. The agreement did not require more than that for selection of\\nthe control group.\\n C.\\n Texas Tech next argues that CMS breached the agreement by refusing\\nto allow it to access relevant Medicare claims data. In apparent response to\\nTexas Tech’s request to obtain this information from Trailblazer—a partner in\\nthe project—CMS told Texas Tech (1) that it could not obtain Trailblazer data\\nin order to create its own “pseudo” control group; and (2) that it could not obtain\\nTrailblazer data on patients in the intervention group without submitting a\\ndata use agreement and getting it approved by CMS. CMS did eventually\\napprove a data use agreement between Texas Tech and Trailblazer, but not\\nuntil May 2007, two months before Texas Tech terminated the project. Texas\\nTech’s idea is that had it been armed with Trailblazer data sooner, it could\\nhave better monitored its own performance as well as the accuracy of the\\ncontrol group.\\n Attempting to locate its right to Trailblazer data in the demonstration\\nagreement, Texas Tech points to its project proposal. In it, Texas Tech\\nsuggested that claims data would be available to it from the “Fiscal\\nIntermediary Standard System,” one of several sources of data it might use to\\ntarget its care management interventions. Because the agreement required\\nTexas Tech to “implement the care management program as proposed,” Texas\\nTech claims a right to access and use data from fiscal intermediaries, including\\nTrailblazer.\\n 11\\n\\f Case: 18-10620 Document: 00514863670 Page: 12 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\n We agree with the Board that CMS’s declining or delaying Texas Tech’s\\naccess to Trailblazer data did not violate the demonstration agreement. Even\\nif the proposal indicated that Texas Tech intended to use Trailblazer’s claims\\ndata, the agreement incorporated the proposal to specify the details of the\\nproject Texas Tech agreed to implement. The proposal thus became a Texas\\nTech obligation, not a CMS obligation, so CMS could not have violated it. To\\nbe clear, the agreement (as opposed to the proposal) did impose data-related\\nobligations on CMS. CMS had to give Texas Tech demographic information\\nand claims data on the intervention group going back 12 months, but Texas\\nTech does not claim CMS failed to do so. Nothing in the agreement obligated\\nCMS to give Texas Tech access to additional data from fiscal intermediaries.\\nTo the contrary, the only relevant provision in the agreement said that if Texas\\nTech “wishes to receive additional data . . . from an FI,” it must notify CMS,\\nwhich would decide only “if such information can be provided.”\\n Texas Tech’s argument faces another problem. Even if we were to read\\nthe agreement to require CMS to allow Texas Tech access to Trailblazer data,\\nthat requirement would extend only to data on the intervention group—the\\nproposal said nothing about using fiscal intermediary data for purposes other\\nthan honing Texas Tech’s care management interventions. And the Board\\nfound that under HHS privacy regulations, CMS could not have allowed Texas\\nTech to access Trailblazer’s claims data on the intervention group without a\\ndata use agreement. See 45 C.F.R. § 164.514(e)(3)(i), (4)(i) (permitting a\\n“covered entity” to disclose medical data “only if the covered entity obtains\\nsatisfactory assurance, in the form of a data use agreement” that the recipient\\nwill use the data “for limited purposes”). Texas Tech does not dispute that. It\\nhas not met its burden of showing that the Board’s ruling on this issue should\\nbe set aside.\\n\\n\\n 12\\n\\f Case: 18-10620 Document: 00514863670 Page: 13 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\n D.\\n Texas Tech also contends that CMS breached the demonstration\\nagreement by engaging RTI to evaluate whether differences between the\\nintervention and control groups may have accounted for the apparent lack of\\ncost savings. Because RTI designed the parameters for the control group,\\nTexas Tech contends it had a conflict of interest in checking its work.\\n But the only time RTI analyzed the alleged disparities in the groups was\\nafter Texas Tech had terminated the project, Actuarial Research Corporation\\nhad conducted the final reconciliation, and Texas Tech had alleged that the\\nstudy was flawed. The demonstration agreement imposes no post-\\nreconciliation obligations on CMS, so CMS cannot have breached the\\nagreement by asking RTI to look into Texas Tech’s concerns. 5\\n E.\\n In addition to its breach arguments, Texas Tech asserted a variety of\\ncommon law contract doctrines before the Board. The Board did not expressly\\naddress two of them—mistake and impracticability 6—because of its view that\\nthose common law principles do not apply to grant agreements.\\n But the Board did make findings that doom those two defenses. It found,\\nbased on the months of negotiation over criteria for the control group, that\\nTexas Tech “proceeded despite its concerns” and “could not reasonably have\\nfailed to understand . . . that it had assumed the financial risks associated with\\n\\n\\n\\n 5 Before the Board, Texas Tech framed its conflict-of-interest theory as a breach of the\\nimplied covenant of good faith and fair dealing, not a breach of the demonstration\\nagreement’s explicit terms. But even if the implied covenant can apply to grant agreements,\\nit cannot “expand another party’s contractual duties beyond those in the express contract.”\\nAgility Pub. Warehousing Co. KSCP v. Mattis, 852 F.3d 1370, 1384 (Fed. Cir. 2017) (cleaned\\nup). The same goes for Texas Tech’s argument to the Board that CMS breached the implied\\ncovenant by failing to create a more accurate control group.\\n 6 The Board did alternatively reject the merits of two others: failure to disclose and\\n\\nestoppel. Texas Tech does not challenge those conclusions.\\n 13\\n\\f Case: 18-10620 Document: 00514863670 Page: 14 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\nshortcomings in study design and implementation.” That undermines Texas\\nTech’s mistake theory; Texas Tech assumed the risk by agreeing to perform\\nthe demonstration, knowing that the control group might have problems.\\nRESTATEMENT (SECOND) OF CONTRACTS § 154(b). It also undermines Texas\\nTech’s impracticability theory because it shows that the accuracy of the control\\ngroup was not a “basic assumption” of the parties’ agreement. Id. § 261.\\n Although the Board did not make these findings in the context of\\ndiscussing mistake and impracticability, they would defeat those defenses had\\nthe Board directly addressed them. As a result, and because substantial\\nevidence supports these findings, any error was harmless. See Shinseki v.\\nSanders, 556 U.S. 396, 411 (2009) (clarifying that administrative harmless\\nerror analysis turns on, among other things, the “likelihood that the result\\nwould have been different” but for the error). The administrative harmless\\nerror rule can sit uneasily alongside the Chenery doctrine, which typically\\nconfines judicial review to the agency’s reasoning. See Nicholas Bagley,\\nRemedial Restraint in Administrative Law, 117 COLUM. L. REV. 253, 302–07\\n(2017). But that tension arises when a reviewing court makes findings the\\nagency should have made in the first instance. See id. at 305 (observing\\n“controversial[]” cases upholding agency decisions when “the evidence in the\\nrecord so strongly supports the result that the court is confident the agency\\nwould reach the same decision on remand”). Chenery cautions against\\nintruding onto an agency’s turf, not against giving an agency’s own findings\\ntheir obvious effect. See Henry J. Friendly, Chenery Revisited: Reflections on\\nReversal and Remand of Administrative Orders, 1969 DUKE L.J. 199, 211\\n(explaining that remand to an agency is “necessary only when the reviewing\\ncourt concludes that there is a significant chance that but for the error the\\nagency might have reached a different result” because “in the absence of such\\na possibility, affirmance entails neither an improper judicial invasion of the\\n 14\\n\\f Case: 18-10620 Document: 00514863670 Page: 15 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-10620\\nadministrative province nor a dispensation of the agency from its normal\\nresponsibility”).\\n * * *\\n The district court’s judgment is AFFIRMED.\\n\\n\\n\\n\\n 15\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1078,"cells":{"id":{"kind":"number","value":4597960,"string":"4,597,960"},"name":{"kind":"string","value":"Alejandro JORGE-CHAVELAS; Alfredo Moreno-Abarca, Plaintiffs - Appellees v. LOUISIANA FARM BUREAU CASUALTY INSURANCE COMPANY; Louisiana Farm Bureau Mutual Insurance Company, Defendants - Appellants v. American Interstate Insurance Company, Intervenor Plaintiff - Appellee"},"name_abbreviation":{"kind":"string","value":"Jorge-Chavelas v. La. Farm Bureau Cas. Ins. Co."},"decision_date":{"kind":"string","value":"2019-03-07"},"docket_number":{"kind":"string","value":"18-30388"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"King, Higginson, Costa\", \"parties\": \"\", \"opinions\": [{\"author\": \"GREGG COSTA, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 18-30388 Document: 00514863514 Page: 1 Date Filed: 03/07/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n No. 18-30388 March 7, 2019\\n Lyle W. Cayce\\nALEJANDRO JORGE-CHAVELAS; ALFREDO MORENO-ABARCA, Clerk\\n\\n Plaintiffs - Appellees\\n\\nv.\\n\\nLOUISIANA FARM BUREAU CASUALTY INSURANCE COMPANY;\\nLOUISIANA FARM BUREAU MUTUAL INSURANCE COMPANY,\\n\\n Defendants - Appellants\\n\\nv.\\n\\nAMERICAN INTERSTATE INSURANCE COMPANY,\\n\\n Intervenor Plaintiff - Appellee\\n\\n\\n\\n\\n Appeal from the United States District Court\\n for the Middle District of Louisiana\\n\\n\\nBefore KING, HIGGINSON, and COSTA, Circuit Judges.\\nGREGG COSTA, Circuit Judge:\\n Workers’ compensation laws strike a statutory bargain between labor\\nand management. They all but guarantee that a worker will recover from an\\nemployer for workplace injuries. In exchange for that certainty, the worker\\ngives up the right to pursue a potentially larger recovery in a tort suit—\\nemployers are immune from such claims.\\n\\f Case: 18-30388 Document: 00514863514 Page: 2 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\n These tradeoffs mean that questions about whether the statutory\\nscheme covers an injured worker can cause businesses and workers alike to\\noscillate between seemingly opposed positions. A worker uncertain about the\\nchances of a tort suit will often seek workers’ compensation, prompting the\\nbusiness to argue that the worker does not fall within the statutory protections.\\nIf the worker has a strong tort claim, the roles may flip—the business then has\\nan incentive to argue that workers’ compensation is the worker’s exclusive\\nremedy.\\n This case is of the latter variety. The insurer of a Louisiana sugarcane\\nfarm has raised several arguments that the farm is entitled to statutory\\nimmunity from this lawsuit brought by two injured cane planters. Those\\nworkers—entitled to a $2.5 million recovery if workers’ compensation does not\\napply—hope to show otherwise.\\n I.\\n Alejandro Jorge-Chavelas and Alfredo Moreno-Abarca, Mexican citizens\\nin the United States on work visas, were severely injured while working on a\\nLouisiana sugarcane farm operated by Harang Sugars, L.L.C. Their legs were\\ncrushed when a Harang employee drove into the sugarcane cart they were\\nsitting on.\\n No one disputes that Harang’s employee was at fault. Nor does anyone\\ndispute the damages the plaintiffs suffered. Instead, Harang’s insurers\\n(collectively “Farm Bureau”) contend that Jorge-Chavelas and Moreno-Abarca\\nwere Harang’s employees, whose injuries are excluded from its general liability\\npolicy. Alternatively, Farm Bureau argues that Louisiana workers’\\ncompensation laws grant its insured immunity from this suit. Both positions\\nturn on the nature of the plaintiffs’ employment. And so we turn to the\\narrangement between the four main players: Jorge-Chavelas, Moreno-Abarca,\\ntheir direct employer (Lowry Farms, Inc.), and Harang.\\n 2\\n\\f Case: 18-30388 Document: 00514863514 Page: 3 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\n Lowry plants sugarcane for other farmers. Because the sugarcane\\nplanting season is short but labor intensive, farmers prefer to contract out the\\nwork rather than hire the necessary short-term workers. Once a farm\\ncontracts with it, Lowry sends recruiters to Mexico to find cane planters.\\nJorge-Chavelas and Moreno-Abarca were two such recruits. Lowry obtained\\nthe necessary visas and agreed to pay the workers an hourly rate and provide\\nthem housing, transportation to and from the worksite, and workers’\\ncompensation insurance. It also explained that the workers would “be required\\nto work all hours as directed by [Lowry’s] management personnel.”\\n Harang was one of Lowry’s clients. Their contract required Harang to\\npay Lowry on a per-acre-planted basis, as opposed to per hour worked by a\\nplanter. 1 The agreement treated the planters as Lowry’s employees, stating\\nthat the payments were “for the work performed by Lowry Farms, Inc.\\nworkers.” While Harang requested 21 workers for the season, it had no role in\\nthe selection of those individuals.\\n Once planting season began, Lowry recruiters became “crew leaders.”\\nThey oversaw planters in the fields, settled disputes between the planters,\\ncommunicated with the farmers, reported injuries suffered by the planters to\\nLowry, and arranged the planters’ transportation back to Mexico. They also\\ndecided which planters would work on which farms. Crew leaders selected\\n“straw bosses” to be their on-the-ground supervisors during the planting, and\\nthese Lowry employees trained the planters. At the end of each week, Harang\\nfilled out a time sheet for the planters, but it was the crew leaders’\\nresponsibility to report the planters’ hours to Lowry. Every week, Lowry paid\\nthe planters.\\n\\n\\n\\n Lowry gave Harang the option to pay an hourly rate to use its employees for “General\\n 1\\n\\nFarm Labor” on days when planting was infeasible. It never did so.\\n 3\\n\\f Case: 18-30388 Document: 00514863514 Page: 4 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\n On the farms, the planters worked side-by-side with Harang’s\\nemployees. Harang tractor drivers hauled the sugarcane carts while the Lowry\\nplanters followed behind in groups of three, pulling the cane from the carts and\\nplanting it in the ground. Harang provided the necessary equipment—the\\ntractors, carts, and sugarcane all belonged to Harang. But it typically did not\\nexert direct control over the planters. If its owner had a problem with the\\nplanters’ work, he would contact Lowry’s office manager, who would contact\\nthe crew leader, who would in turn communicate the concern to the planters.\\nAnd only Lowry could fire its planters—Harang could voice concern about a\\nplanter in the hope that Lowry would find a substitute, but it could not\\nterminate his employment.\\n Harang’s management did not believe the planters were its employees.\\nOn the day of the accident, after calling emergency services, Harang’s owner\\nimmediately notified Lowry. When asked why, he replied, “Because that’s\\ntheir employees.” Indeed, Lowry’s workers’ compensation insurer covered\\nplaintiffs’ medical expenses. 2\\n Jorge-Chavelas and Moreno-Abarca sued Harang in federal district\\ncourt, invoking diversity jurisdiction. After the court denied competing\\nmotions for summary judgment, a stipulated bench trial followed. The parties\\nagreed that Harang was at fault and that total damages would be $2.5 million\\n(the limit of the Farm Bureau policy). The court had to decide the employment\\nstatus of the plaintiffs and, relatedly, whether Harang was immune from suit.\\nConcluding that the plaintiffs were not Harang’s employees and that the\\nworkers’ compensation laws did not otherwise provide Harang immunity, the\\n\\n\\n\\n 2 The district court awarded that insurer—intervenor American Interstate Insurance\\nCompany—reimbursement for the payments it made to and on behalf of the appellees.\\nAmerican Interstate has informed the court that it too hopes we affirm the judgment below,\\nstanding on the arguments plaintiffs make.\\n 4\\n\\f Case: 18-30388 Document: 00514863514 Page: 5 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\ndistrict court entered judgment in favor of Jorge-Chavelas for $1,937,500 and\\nMoreno-Abarca for $562,500.\\n II.\\n Louisiana law applies in this diversity case. Erie R.R. Co. v. Tompkins,\\n304 U.S. 64 (1938). Our task is to “determine as best [we] can [how] the\\nLouisiana Supreme Court would decide” it. Gulf & Miss. River Transp. Co. v.\\nBP Oil Pipeline Co., 730 F.3d 484, 488 (5th Cir. 2013) (quotation omitted).\\nWhen the absence of a controlling high court decision requires us to make an\\n“Erie guess” about Louisiana law, we consider many of the same sources we\\nuse when guessing the law of other jurisdictions: decisions and reasoning of\\nthe state’s courts; general rules of the jurisdiction, such as those governing\\nstatutory interpretation; and secondary sources like treatises. Id. at 488–89.\\nBut Louisiana’s “civilian methodology” means the pecking order of those\\nsources is different than it is for a common law state. Boyett v. Redland Ins.\\nCo., 741 F.3d 604, 607 (5th Cir. 2014). Louisiana’s “Constitution, codes, and\\nstatutes” are of paramount importance to its judges. Am. Int’l Specialty Lines\\nIns. Co. v. Canal Indem. Co., 352 F.3d 254, 260 (5th Cir. 2003). The doctrine\\nof stare decisis, a creature of common law, is alien to the civilian system.\\nBoyett, 741 F.3d at 607. Unlike stare decisis, which can flow from one decision,\\nin the civil system numerous court decisions must agree on a legal issue to\\nestablish jurisprudence constante (French for constant jurisprudence). And\\neven when that consensus exists in the caselaw, it remains only persuasive\\nauthority for the Erie guess; “we are not strictly bound” by the decisions of\\nLouisiana’s intermediate courts. Am. Int’l Specialty Lines, 352 F.3d at 261\\n(quoting Transcon. Gas Pipe Line Corp. v. Transp. Ins. Co., 953 F.2d 985, 988\\n(5th Cir. 1992)); see generally Alvin B. Rubin, Hazards of a Civilian Venturer\\nin Federal Court: Travel and Travail on the Erie Railroad, 48 LA. L. REV. 1369\\n(1988).\\n 5\\n\\f Case: 18-30388 Document: 00514863514 Page: 6 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\n A.\\n The primacy of legislation under the civil law tradition guides our\\nanalysis of the question Farm Bureau’s primary argument poses: Does\\nLouisiana’s choice to extend workers’ compensation—usually reserved for\\nemployees—to one class of independent contractors apply to the employees of\\nthose independent contractors and thus immunize Harang from this suit?\\n As noted above, workers’ compensation laws are a statutory compromise\\ngranting employers immunity from negligence suits 3 in exchange for their\\nguaranteeing a lesser recovery for on-the-job injuries. 4 Within that general\\nframework, states have experimented with the scope of both the coverage and\\nthe immunity. It is no different in Louisiana. For instance, although\\nindependent contractors generally are excluded from Louisiana’s workers’\\ncompensation regime, there is an exception. Section 23:1021(7) 5 of Louisiana’s\\nRevised Statutes states:\\n “Independent contractor” means any person who renders service,\\n other than manual labor, for a specified recompense for a specified\\n result either as a unit or as a whole, under the control of his\\n principal as to results of his work only, and not as to the means by\\n which such result is accomplished, and are expressly excluded\\n from the provisions of this Chapter unless a substantial part of the\\n work time of an independent contractor is spent in manual labor\\n by him in carrying out the terms of the contract, in which case the\\n\\n\\n\\n 3 Immunity does not extend to an employer’s intentional torts. La. Rev. Stat. Ann.\\n§ 23:1032(B).\\n 4 Among other limits, two potentially sizable categories of damages—pain and\\n\\nsuffering and punitive damages—are not recoverable in Louisiana as workers’ compensation.\\nThose benefits are limited to three types of loss: a partial compensation for lost wages, see\\nLa. Rev. Stat. Ann. § 23:1221(1)–(3), medical expenses, id. § 23:1203, and so-called “schedule”\\nlosses compensating for particular disfigurements, id. § 23:1221(4)(a)–(r); see also 13 H.\\nALSTON JOHNSON III, LA. CIV. LAW. TREATISE, WORKERS’ COMPENSATION LAW AND\\nPRACTICE § 271 (5th ed. 2018).\\n 5 We note, to avoid confusion, that changes to the Louisiana workers’ compensation\\n\\nlaws moved this provision from its previous position in section 1021(6) to section 1021(7).\\nSome cases discussed in this opinion cite the older section.\\n 6\\n\\f Case: 18-30388 Document: 00514863514 Page: 7 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\n independent contractor is expressly covered by the provisions of\\n this Chapter.\\nIn other words, an independent contractor who is engaged primarily in manual\\nlabor has a claim for workers’ compensation against his principal. More\\nimportantly to Farm Bureau, that principal is immunized from a negligence\\nsuit. La. Rev. Stat. Ann. § 23:1032.\\n Farm Bureau maintains that this statute applies not just to independent\\ncontractors, but also to the employees of independent contractors. In this case,\\nthat would mean that the principal (Harang) is immune from suit by the\\nemployees (Jorge-Chavelas and Moreno-Abarca) of the principal’s independent\\ncontractor (Lowry).\\n The text of the statute says otherwise, and that is where we must begin.\\nSee 84 Lumber Co. v. Cont’l Cas. Co., 914 F.3d 329, 334 (5th Cir. 2019)\\n(explaining that, in Louisiana, “[w]hen a law is clear and unambiguous . . . it\\nshall be applied as written”) (quotation omitted). Section 1021(7) excludes\\nmost independent contractors from the workers’ compensation regime. But it\\ngrants coverage to contractors who spend a “substantial part” of their time\\nproviding “manual labor.” In either situation, the statute addresses only\\nindependent contractors.\\n Farm Bureau’s argument that the provision brings plaintiffs under the\\nworkers’ compensation law fails at this most basic requirement. As the term\\nindicates, an independent contractor is “one that contracts” with the principal.\\nSee Contractor, WEBSTER’S THIRD NEW INTERNATIONAL DICTIONARY (2002)\\n(also defining “contractor” as “a party to a bargain”). Under this widespread\\nunderstanding of the term, Jorge-Chavelas and Moreno-Abarca are not\\nHarang’s contractors; they never entered into an express or implied agreement\\nwith the company. La. Civ. Code Ann. art. 11 (“The words of a law must be\\ngiven their generally prevailing meaning.”). A common example illustrates\\n\\n 7\\n\\f Case: 18-30388 Document: 00514863514 Page: 8 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\nthis. Assume a homeowner hires a pest control company to exterminate bugs.\\nThe company becomes the homeowner’s contractor. But that typically does not\\nresult in an agency relationship between the homeowner and the employee of\\nthe pest control company.\\n Other language in section 1021(7) confirms that the statute is referring\\nto “independent contractor” in this ordinary sense of the term—one who has a\\ncontractual relationship with the principal. The statute excepts only an\\nindependent contractor for whom a substantial part of his work is “spent in\\nmanual labor by him in carrying out the terms of the contract.” (emphases\\nadded). And the relevant contract is one “for a specified recompense for a\\nspecified result either as a unit or as a whole.” But, as in this case, the\\nemployees of an independent contractor are typically not parties to “the\\ncontract,” which would be between the principal and the contractor.\\n What little guidance we have from the Supreme Court of Louisiana is\\nconsistent with this plain meaning of the statute. In Lushute v. Diesi, the court\\nremarked that the exception was meant to extend to a contractor engaged in\\nmanual labor “in carrying out the terms of his contract with the principal.” 354\\nSo. 2d 179, 182 (La. 1977) (emphasis added). This suggests the state high court\\nwould adopt this natural reading—that the statute covers only contractors\\nthemselves—rather than Farm Bureau’s more expansive one. And that\\ncomports with the Louisiana Supreme Court’s general approach to workers’\\ncompensation laws. When interpreting the immunity afforded employers,\\n“every presumption should be on the side of preserving the general tort or\\ndelictual rights of an injured worker against the actual wrongdoer, in the\\nabsence of explicit statutory language limiting or excluding such rights.”\\nChampagne v. Am. Alt. Ins. Corp., 112 So. 3d 179, 184 (La. 2013) (quoting\\nRoberts v. Sewerage & Water Bd. of New Orleans, 634 So. 2d 341, 346 (La.\\n1994)).\\n 8\\n\\f Case: 18-30388 Document: 00514863514 Page: 9 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\n Despite the absence of that necessary statutory command, three\\nLouisiana intermediate court decisions have held or suggested that principals\\nare immune from tort suits brought by their contractors’ employees if those\\nemployees were engaged in manual labor. In Lumar v. Zappe Endeavors,\\nL.L.C., an employee of an independent contractor sued his employer’s principal\\nin tort. 946 So. 2d 188 (La. App. 5 Cir. 2006). Louisiana’s Fifth Circuit Court\\nof Appeal held that, because a contractor “performs its duties through its\\nemployees,” the “limitations applicable to [the contractor] are also applicable\\nto its employees.” Id. at 191. Two other courts relied on Lumar not to\\nimmunize an employer, but to find a contractor’s employee was entitled to\\nrecover workers’ compensation from the contractor’s principal. Courtney v.\\nFletcher Trucking, 111 So. 3d 411, 418 n.6 (La. App. 1 Cir. 2012); Moss v.\\nTommasi Constr., Inc., 37 So. 3d 492, 499 (La. App. 3 Cir. 2010).\\n Three decisions do not jurisprudence constante make. That is especially\\ntrue when the court that first announced the rule Farm Bureau presses us to\\nadopt declined to follow it just three years later. In Daigle v. McGee Backhoe\\n& Dozer Service, the Fifth Circuit Court of Appeal denied a claim for workers’\\ncompensation brought by an independent contractor’s employee against the\\ncontractor’s principal. 16 So. 3d 4 (La. App. 5 Cir. 2009). As a dissent in that\\ncase pointed out, following Lumar would have made the contractor’s employee\\neligible for workers’ compensation under section 1021(7). 6 Id. at 8 (Winsberg,\\nJ., dissenting). The majority instead suggested that an employee of a\\ncontractor is eligible for workers’ compensation against his employer’s\\nprincipal, if at all, through a separate provision, section 23:1061, which defines\\n“statutory employment.” Id. at 7. That statute authorizes, in certain\\n\\n\\n 6 The plaintiff in Daigle made the same point, albeit without citing Lumar. Original\\nBrief of Eddie Daigle, Daigle v. McGee Backhoe & Dozer Serv., 16 So. 3d 4 (La. App. 5 Cir.\\n2009), 2008 WL 5478293, at *7–8.\\n 9\\n\\f Case: 18-30388 Document: 00514863514 Page: 10 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\ncircumstances, a claim for workers’ compensation by a contractor’s employee\\nagainst the contractor’s principal “as if he were [that] principal’s employee.”\\n13 H. ALSTON JOHNSON III, LA. CIV. LAW. TREATISE, WORKERS’ COMPENSATION\\nLAW AND PRACTICE § 121 (5th ed. 2018) (emphasis in original).\\n Other Louisiana courts have likewise analyzed cases like this one\\nthrough the lens of statutory employment, explaining that section 1061\\n“provides guidance as to when a contractor’s employee, rather than the\\ncontractor himself, may recover under the principal’s workers’ compensation\\nliability.” Miller v. Higginbottom, 768 So. 2d 127, 132 (La. App. 2 Cir. 2000);\\nsee also Prejean v. Maint. Enters., Inc., 8 So. 3d 766, 770 (La. App. 4 Cir. 2009);\\nPoirrier v. Cajun Insulation, Inc., 459 So. 2d 737, 738–39 (La. App. 4 Cir. 1984).\\nLouisiana’s leading workers’ compensation treatise agrees that statutory\\nemployment is the proper framework for analyzing whether the employee of\\nan independent contractor can recover workers’ compensation from the\\nprincipal. See JOHNSON III, supra § 82 (noting the contractor’s pursuit of\\ncompensation would be analyzed under section 1021(7) while his employee\\n“must seek compensation under the different test of [section] 1061”).\\n That makes sense as the terms of the statutory employment statute\\ndirectly address the employee-of-an-independent-contractor situation we\\nconfront. When applicable, workers’ compensation is the exclusive remedy for\\na contractor’s employee against the principal. La. Rev. Stat. Ann.\\n§ 23:1061(A)(1). The catch is that the relationship must be formed by contract.\\nId. § 23:1061(A)(3). 7 No such contract exists in this case, which explains why\\nFarm Bureau does not seek section 1061’s help. But the existence of this\\n\\n\\n\\n 7 There is another way to create the statutory employment relationship known as the\\n“two contract” theory, but it is not applicable to this case. La. Rev. Stat. Ann. § 23:1061(A)(2);\\nsee also Allen v. Ernest N. Morial-New Orleans Exhibition Hall Auth., 842 So. 2d 373, 379\\n(La. 2003).\\n 10\\n\\f Case: 18-30388 Document: 00514863514 Page: 11 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\nexpress avenue for employees of contractors to seek workers’ compensation\\nfrom a principal (and in turn for those principals to seek immunity) further\\nsupports limiting section 1021(7) to independent contractors themselves, not\\ntheir employees. La. Civ. Code Ann. art. 13 (“Laws on the same subject matter\\nmust be interpreted in reference to each other.”); Fontenot v. Reddell Vidrine\\nWater Dist., 836 So. 2d 14, 28 (La. 2003) (“It is a fundamental rule of statutory\\nconstruction that when two statutes deal with the same subject matter, the\\nstatute specifically directed to the matter at issue must prevail as an exception\\nto the more general statute.”).\\n Sections 1021(7) and 1061 are both deviations from typical workers’\\ncompensation principles, but they serve different purposes. Section 1021(7)\\nprotects a specific class of independent contractors who would not otherwise be\\nentitled to benefits. It was added because, when it came to manual laborers,\\nthe “distinction between contractor and employee had become so tenuous and\\nso difficult to administer that the cases were in a state of almost hopeless\\nconfusion, and many injustices were apparent.” JOHNSON III, supra § 78. To\\nsettle the seemingly interminable debate, the Louisiana legislature resolved\\nthat those who contracted to do manual labor were entitled to benefits, no\\nmatter what a multifactor test said about their relationship to the principal.\\nId.\\n Section 1061 addresses a different concern—contractors who lack the\\nassets to pay workers’ compensation. To encourage principals to hire solvent\\ncontractors, the statute offers them a choice. If a principal enters into a\\nstatutory employment contract, in exchange for assuming workers’\\ncompensation liability, it obtains two benefits: 1) tort immunity from the\\ncontractor’s employees; and 2) indemnification from the contractor if those\\nemployees recover workers’ compensation from the principal. See La. Rev.\\nStat. Ann. § 23:1061(B). Not a bad option if you hire a solvent contractor (but\\n 11\\n\\f Case: 18-30388 Document: 00514863514 Page: 12 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\nif the contractor is insolvent, indemnification won’t help). Or those principals\\ncan choose to forego immunity if they would rather limit their vulnerability to\\nworkers’ compensation claims. So, although “[o]rdinarily a principal is not and\\nshould not be subjected to the compensation claims of his contractor’s\\nemployees,” statutory employment uses the promise of immunity and\\nindemnification to encourage principals to agree otherwise. JOHNSON III,\\nsupra § 78; see also id. at § 121 (noting that the interposition of a contractor\\nbetween the principal and the contractor’s employees “would not deprive the\\nemployee of protection so long as the intermediary contractor was solvent or\\nprotected by insurance”).\\n This statutory employment law that targets the employment\\nrelationship we confront, together with the ordinary meaning of\\nsection 1021(7), tangential but informative guidance from Louisiana’s highest\\ncourt, and the view of a leading authority on Louisiana workers’ compensation\\nlaw, trumps a handful of decisions from intermediate state courts, one of which\\nhas backtracked from its earlier view. The district court’s Erie guess is a solid\\none. 8 Section 1021(7) does not obligate a principal to provide workers’\\ncompensation to the employees of its independent contractors, so it does not\\nafford Harang immunity from this suit. 9\\n\\n\\n\\n 8Farm Bureau asked us to certify this question about the manual labor exception to\\nthe Supreme Court of Louisiana. Because our analysis leads us to conclude that the issue is\\nnot a close one, we decline that invitation.\\n 9 Farm Bureau contends that our interpretation of the manual labor exception\\n\\nthreatens to “obliterate” its role within Louisiana’s workers’ compensation regime. But we\\ndo nothing to displace that statute where its text says it applies—when an independent\\ncontractor herself is primarily engaged in manual labor. If anything, it is Farm Bureau’s\\nreading of the manual labor exception that threatens to displace the role of another statute.\\nIf employees of independent contractors engaged in manual labor are automatically entitled\\nto workers’ compensation from the principal, that would create a large exception to\\nsection 1061’s usual rule that a principal is liable for such claims only when a statutory\\nemployment relationship is created by contract. La. Rev. Stat. Ann. § 23:1061(A)(3). And\\n\\n 12\\n\\f Case: 18-30388 Document: 00514863514 Page: 13 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\n B.\\n Even if plaintiffs are not covered as Harang’s independent contractors,\\nFarm Bureau argues that the workers’ compensation regime still applies for a\\nmore traditional reason: the plaintiffs were Harang’s employees. It says that\\ntwo different provisions treat the plaintiffs as employees.\\n The parties call the first the “presumed employee” provision. It provides\\nthat a “person rendering service for another in any trade[], business[] or\\noccupation[] . . . is presumed to be an employee.” La. Rev. Stat. Ann. § 23:1044.\\nFarm Bureau does not dispute the general view of Louisiana courts that this\\npresumption is overcome when the worker lacks an express or implied\\nemployment agreement with the business. See, e.g., Dustin v. DHCI Home\\nHealth Servs., Inc., 673 So. 2d 356, 359 (La. App. 1 Cir. 1996). Just as we do\\nnow, the district court rejected the “presumed employee” argument for\\nimmunity on that ground because, as we have already explained, plaintiffs did\\nnot have an express or implied agreement with Harang. They are not\\npresumed employees. 10\\n\\n\\nFarm Bureau’s view leads to other interpretive problems. As plaintiffs’ counsel noted at oral\\nargument, if an independent contractor like Lowry is engaged primarily in the provision of\\nmanual labor, which of its employees are entitled to benefits from the principal? Only those\\nactually engaged in manual labor, or would Harang also be liable to pay workers’\\ncompensation to Lowry’s office manager?\\n Nor does our decision render workers’ compensation unavailable to the employees of\\nan independent contractor. As in this case, the direct employer (Lowry) is responsible for\\nworkers’ compensation.\\n 10 There is a factual and logical flaw with a more nuanced argument Farm Bureau\\n\\nmakes under this statute. It contends: 1) that the presumption of employee status is\\novercome if the worker is an independent contractor, see Hillman v. Comm-Care, Inc., 805\\nSo. 2d 1157, 1161 (La. 2002), but 2) section 1021(7) explicitly includes independent\\ncontractors engaged primarily in manual labor in Louisiana’s workers’ compensation regime,\\nand 3) Jorge-Chavelas and Moreno-Abarca were engaged in manual labor, so 4) they are\\npresumed employees. This syllogism falls apart at step two. Section 1021(7) does not bring\\nmanual laborers back under the presumption. That is because it does not render manual\\nlaborers employees—it just entitles those independent contractors to workers’ compensation\\nfrom their principal. JOHNSON III, supra § 74. In any event, we have already held that\\n\\n 13\\n\\f Case: 18-30388 Document: 00514863514 Page: 14 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\n C.\\n Farm Bureau’s final recourse is to characterize the plaintiffs as Harang’s\\nborrowed employees. Louisiana makes borrowing employers (“special\\nemployers” in civil law lingo) and lending employers (“general employers”)\\nliable “jointly and in solido to pay” workers’ compensation for injuries suffered\\nby a borrowed employee. La. Rev. Stat. Ann. § 23:1031(C). In exchange for\\nthat joint liability to pay workers’ compensation, both the special and general\\nemployer are immune from negligence suits. Id.\\n The borrowed servant doctrine arises in many areas, with some of its\\ndeepest roots in maritime law. See Standard Oil v. Anderson, 212 U.S. 215\\n(1909). When applying the Louisiana workers’ compensation version, courts\\nuse either a nine- or ten-factor test to determine whether a borrowed\\nemployment relationship exists. The two tests are essentially identical.\\nCompare McGinnis v. Waste Mgmt. of La., L.L.C., 914 So. 2d 612, 616 (La. App.\\n2 Cir. 2005) (describing nine-factor test), with Billeaud v. Poledore, 603 So. 2d\\n754, 756 (La. App. 1 Cir. 1992) (describing ten-factor test). The district court\\napplied the ten-factor test, but under either one and under any standard of\\nreview 11 the result is the same: Jorge-Chavelas and Moreno-Abarca were not\\nborrowed employees.\\n First and foremost, Lowry at all times controlled its planters. See Lastie\\nv. Cooper, 167 So. 3d 150, 153 (La. App. 5 Cir. 2014). It chose which planters\\n\\n\\n\\nplaintiffs are not Harang’s independent contractors. They are further removed as the\\nemployees of Harang’s independent contractor.\\n 11 Farm Bureau contends that we should review the district court’s ruling on this\\n\\nquestion de novo, while the plaintiffs instead believe the proper standard is clear error. They\\nare both right. While ultimately the plaintiff’s “borrowed servant status is a legal issue”\\nreviewed de novo, the factors considered in making that determination are “factual” and their\\napplication is reviewed for clear error. Sanchez v. Harbor Const. Co., Inc., 968 So. 2d 783,\\n786 (La. App. 4 Cir. 2007); see also Capps v. N.L. Baroid-NL Indus., Inc., 784 F.2d 615, 617\\n(5th Cir. 1986) (explaining that a “district court decides the borrowed employee issue as a\\nmatter of law,” but characterizing the factors as “factual ingredients”).\\n 14\\n\\f Case: 18-30388 Document: 00514863514 Page: 15 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\nwent to which farms, planters were required “to work all hours as directed by\\n[Lowry] personnel,” and Harang’s owner himself admitted he could not control\\nthe planters. There was no agreement recognizing a borrowed employment\\nrelationship, the planters never acquiesced to being borrowed employees,\\nLowry maintained a close relationship with the planters throughout the\\nseason, only Lowry could fire the planters, and it—not Harang—was obligated\\nto pay them. The only factors weighing in favor of a borrowed employment\\nrelationship—that the planters were doing Harang’s work for which Harang\\nprovided the tools—do not overcome the number and importance of the factors\\nweighing against it. We therefore also reject Farm Bureau’s contention that\\nHarang was a borrowing employer.\\n ***\\n Plaintiffs were neither employees of Harang nor its independent\\ncontractors. Instead, they were employees of Harang’s independent contractor.\\nThat means Harang enjoys no immunity from suit.\\n The judgment is AFFIRMED.\\n\\n\\n\\n\\n 15\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4375213/\", \"author_raw\": \"GREGG COSTA, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"KING"},"judge2":{"kind":"string","value":"HIGGINSON"},"judge3":{"kind":"string","value":"COSTA"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4597960/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Alejandro JORGE-CHAVELAS; Alfredo Moreno-Abarca, Plaintiffs - Appellees v. LOUISIANA FARM BUREAU CASUALTY INSURANCE COMPANY; Louisiana Farm Bureau Mutual Insurance Company, Defendants - Appellants v. American Interstate Insurance Company, Intervenor Plaintiff - Appellee\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-07\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 18-30388 Document: 00514863514 Page: 1 Date Filed: 03/07/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\n United States Court of Appeals\n Fifth Circuit\n\n FILED\n No. 18-30388 March 7, 2019\n Lyle W. Cayce\nALEJANDRO JORGE-CHAVELAS; ALFREDO MORENO-ABARCA, Clerk\n\n Plaintiffs - Appellees\n\nv.\n\nLOUISIANA FARM BUREAU CASUALTY INSURANCE COMPANY;\nLOUISIANA FARM BUREAU MUTUAL INSURANCE COMPANY,\n\n Defendants - Appellants\n\nv.\n\nAMERICAN INTERSTATE INSURANCE COMPANY,\n\n Intervenor Plaintiff - Appellee\n\n\n\n\n Appeal from the United States District Court\n for the Middle District of Louisiana\n\n\nBefore KING, HIGGINSON, and COSTA, Circuit Judges.\nGREGG COSTA, Circuit Judge:\n Workers’ compensation laws strike a statutory bargain between labor\nand management. They all but guarantee that a worker will recover from an\nemployer for workplace injuries. In exchange for that certainty, the worker\ngives up the right to pursue a potentially larger recovery in a tort suit—\nemployers are immune from such claims.\n\f Case: 18-30388 Document: 00514863514 Page: 2 Date Filed: 03/07/2019\n\n\n\n No. 18-30388\n These tradeoffs mean that questions about whether the statutory\nscheme covers an injured worker can cause businesses and workers alike to\noscillate between seemingly opposed positions. A worker uncertain about the\nchances of a tort suit will often seek workers’ compensation, prompting the\nbusiness to argue that the worker does not fall within the statutory protections.\nIf the worker has a strong tort claim, the roles may flip—the business then has\nan incentive to argue that workers’ compensation is the worker’s exclusive\nremedy.\n This case is of the latter variety. The insurer of a Louisiana sugarcane\nfarm has raised several arguments that the farm is entitled to statutory\nimmunity from this lawsuit brought by two injured cane planters. Those\nworkers—entitled to a $2.5 million recovery if workers’ compensation does not\napply—hope to show otherwise.\n I.\n Alejandro Jorge-Chavelas and Alfredo Moreno-Abarca, Mexican citizens\nin the United States on work visas, were severely injured while working on a\nLouisiana sugarcane farm operated by Harang Sugars, L.L.C. Their legs were\ncrushed when a Harang employee drove into the sugarcane cart they were\nsitting on.\n No one disputes that Harang’s employee was at fault. Nor does anyone\ndispute the damages the plaintiffs suffered. Instead, Harang’s insurers\n(collectively “Farm Bureau”) contend that Jorge-Chavelas and Moreno-Abarca\nwere Harang’s employees, whose injuries are excluded from its general liability\npolicy. Alternatively, Farm Bureau argues that Louisiana workers’\ncompensation laws grant its insured immunity from this suit. Both positions\nturn on the nature of the plaintiffs’ employment. And so we turn to the\narrangement between the four main players: Jorge-Chavelas, Moreno-Abarca,\ntheir direct employer (Lowry Farms, Inc.), and Harang.\n 2\n\f Case: 18-30388 Document: 00514863514 Page: 3 Date Filed: 03/07/2019\n\n\n\n No. 18-30388\n Lowry plants sugarcane for other farmers. Because the sugarcane\nplanting season is short but labor intensive, farmers prefer to contract out the\nwork rather than hire the necessary short-term workers. Once a farm\ncontracts with it, Lowry sends recruiters to Mexico to find cane planters.\nJorge-Chavelas and Moreno-Abarca were two such recruits. Lowry obtained\nthe necessary visas and agreed to pay the workers an hourly rate and provide\nthem housing, transportation to and from the worksite, and workers’\ncompensation insurance. It also explained that the workers would “be required\nto work all hours as directed by [Lowry’s] management personnel.”\n Harang was one of Lowry’s clients. Their contract required Harang to\npay Lowry on a per-acre-planted basis, as opposed to per hour worked by a\nplanter. 1 The agreement treated the planters as Lowry’s employees, stating\nthat the payments were “for the work performed by Lowry Farms, Inc.\nworkers.” While Harang requested 21 workers for the season, it had no role in\nthe selection of those individuals.\n Once planting season began, Lowry recruiters became “crew leaders.”\nThey oversaw planters in the fields, settled disputes between the planters,\ncommunicated with the farmers, reported injuries suffered by the planters to\nLowry, and arranged the planters’ transportation back to Mexico. They also\ndecided which planters would work on which farms. Crew leaders selected\n“straw bosses” to be their on-the-ground supervisors during the planting, and\nthese Lowry employees trained the planters. At the end of each week, Harang\nfilled out a time sheet for the planters, but it was the crew leaders’\nresponsibility to report the planters’ hours to Lowry. Every week, Lowry paid\nthe planters.\n\n\n\n Lowry gave Harang the option to pay an hourly rate to use its employees for “General\n 1\n\nFarm Labor” on days when planting was infeasible. It never did so.\n 3\n\f Case: 18-30388 Document: 00514863514 Page: 4 Date Filed: 03/07/2019\n\n\n\n No. 18-30388\n On the farms, the planters worked side-by-side with Harang’s\nemployees. Harang tractor drivers hauled the sugarcane carts while the Lowry\nplanters followed behind in groups of three, pulling the cane from the carts and\nplanting it in the ground. Harang provided the necessary equipment—the\ntractors, carts, and sugarcane all belonged to Harang. But it typically did not\nexert direct control over the planters. If its owner had a problem with the\nplanters’ work, he would contact Lowry’s office manager, who would contact\nthe crew leader, who would in turn communicate the concern to the planters.\nAnd only Lowry could fire its planters—Harang could voice concern about a\nplanter in the hope that Lowry would find a substitute, but it could not\nterminate his employment.\n Harang’s management did not believe the planters were its employees.\nOn the day of the accident, after calling emergency services, Harang’s owner\nimmediately notified Lowry. When asked why, he replied, “Because that’s\ntheir employees.” Indeed, Lowry’s workers’ compensation insurer covered\nplaintiffs’ medical expenses. 2\n Jorge-Chavelas and Moreno-Abarca sued Harang in federal district\ncourt, invoking diversity jurisdiction. After the court denied competing\nmotions for summary judgment, a stipulated bench trial followed. The parties\nagreed that Harang was at fault and that total damages would be $2.5 million\n(the limit of the Farm Bureau policy). The court had to decide the employment\nstatus of the plaintiffs and, relatedly, whether Harang was immune from suit.\nConcluding that the plaintiffs were not Harang’s employees and that the\nworkers’ compensation laws did not otherwise provide Harang immunity, the\n\n\n\n 2 The district court awarded that insurer—intervenor American Interstate Insurance\nCompany—reimbursement for the payments it made to and on behalf of the appellees.\nAmerican Interstate has informed the court that it too hopes we affirm the judgment below,\nstanding on the arguments plaintiffs make.\n 4\n\f Case: 18-30388 Document: 00514863514 Page: 5 Date Filed: 03/07/2019\n\n\n\n No. 18-30388\ndistrict court entered judgment in favor of Jorge-Chavelas for $1,937,500 and\nMoreno-Abarca for $562,500.\n II.\n Louisiana law applies in this diversity case. Erie R.R. Co. v. Tompkins,\n304 U.S. 64 (1938). Our task is to “determine as best [we] can [how] the\nLouisiana Supreme Court would decide” it. Gulf & Miss. River Transp. Co. v.\nBP Oil Pipeline Co., 730 F.3d 484, 488 (5th Cir. 2013) (quotation omitted).\nWhen the absence of a controlling high court decision requires us to make an\n“Erie guess” about Louisiana law, we consider many of the same sources we\nuse when guessing the law of other jurisdictions: decisions and reasoning of\nthe state’s courts; general rules of the jurisdiction, such as those governing\nstatutory interpretation; and secondary sources like treatises. Id. at 488–89.\nBut Louisiana’s “civilian methodology” means the pecking order of those\nsources is different than it is for a common law state. Boyett v. Redland Ins.\nCo., 741 F.3d 604, 607 (5th Cir. 2014). Louisiana’s “Constitution, codes, and\nstatutes” are of paramount importance to its judges. Am. Int’l Specialty Lines\nIns. Co. v. Canal Indem. Co., 352 F.3d 254, 260 (5th Cir. 2003). The doctrine\nof stare decisis, a creature of common law, is alien to the civilian system.\nBoyett, 741 F.3d at 607. Unlike stare decisis, which can flow from one decision,\nin the civil system numerous court decisions must agree on a legal issue to\nestablish jurisprudence constante (French for constant jurisprudence). And\neven when that consensus exists in the caselaw, it remains only persuasive\nauthority for the Erie guess; “we are not strictly bound” by the decisions of\nLouisiana’s intermediate courts. Am. Int’l Specialty Lines, 352 F.3d at 261\n(quoting Transcon. Gas Pipe Line Corp. v. Transp. Ins. Co., 953 F.2d 985, 988\n(5th Cir. 1992)); see generally Alvin B. Rubin, Hazards of a Civilian Venturer\nin Federal Court: Travel and Travail on the Erie Railroad, 48 LA. L. REV. 1369\n(1988).\n 5\n\f Case: 18-30388 Document: 00514863514 Page: 6 Date Filed: 03/07/2019\n\n\n\n No. 18-30388\n A.\n The primacy of legislation under the civil law tradition guides our\nanalysis of the question Farm Bureau’s primary argument poses: Does\nLouisiana’s choice to extend workers’ compensation—usually reserved for\nemployees—to one class of independent contractors apply to the employees of\nthose independent contractors and thus immunize Harang from this suit?\n As noted above, workers’ compensation laws are a statutory compromise\ngranting employers immunity from negligence suits 3 in exchange for their\nguaranteeing a lesser recovery for on-the-job injuries. 4 Within that general\nframework, states have experimented with the scope of both the coverage and\nthe immunity. It is no different in Louisiana. For instance, although\nindependent contractors generally are excluded from Louisiana’s workers’\ncompensation regime, there is an exception. Section 23:1021(7) 5 of Louisiana’s\nRevised Statutes states:\n “Independent contractor” means any person who renders service,\n other than manual labor, for a specified recompense for a specified\n result either as a unit or as a whole, under the control of his\n principal as to results of his work only, and not as to the means by\n which such result is accomplished, and are expressly excluded\n from the provisions of this Chapter unless a substantial part of the\n work time of an independent contractor is spent in manual labor\n by him in carrying out the terms of the contract, in which case the\n\n\n\n 3 Immunity does not extend to an employer’s intentional torts. La. Rev. Stat. Ann.\n§ 23:1032(B).\n 4 Among other limits, two potentially sizable categories of damages—pain and\n\nsuffering and punitive damages—are not recoverable in Louisiana as workers’ compensation.\nThose benefits are limited to three types of loss: a partial compensation for lost wages, see\nLa. Rev. Stat. Ann. § 23:1221(1)–(3), medical expenses, id. § 23:1203, and so-called “schedule”\nlosses compensating for particular disfigurements, id. § 23:1221(4)(a)–(r); see also 13 H.\nALSTON JOHNSON III, LA. CIV. LAW. TREATISE, WORKERS’ COMPENSATION LAW AND\nPRACTICE § 271 (5th ed. 2018).\n 5 We note, to avoid confusion, that changes to the Louisiana workers’ compensation\n\nlaws moved this provision from its previous position in section 1021(6) to section 1021(7).\nSome cases discussed in this opinion cite the older section.\n 6\n\f Case: 18-30388 Document: 00514863514 Page: 7 Date Filed: 03/07/2019\n\n\n\n No. 18-30388\n independent contractor is expressly covered by the provisions of\n this Chapter.\nIn other words, an independent contractor who is engaged primarily in manual\nlabor has a claim for workers’ compensation against his principal. More\nimportantly to Farm Bureau, that principal is immunized from a negligence\nsuit. La. Rev. Stat. Ann. § 23:1032.\n Farm Bureau maintains that this statute applies not just to independent\ncontractors, but also to the employees of independent contractors. In this case,\nthat would mean that the principal (Harang) is immune from suit by the\nemployees (Jorge-Chavelas and Moreno-Abarca) of the principal’s independent\ncontractor (Lowry).\n The text of the statute says otherwise, and that is where we must begin.\nSee 84 Lumber Co. v. Cont’l Cas. Co., 914 F.3d 329, 334 (5th Cir. 2019)\n(explaining that, in Louisiana, “[w]hen a law is clear and unambiguous . . . it\nshall be applied as written”) (quotation omitted). Section 1021(7) excludes\nmost independent contractors from the workers’ compensation regime. But it\ngrants coverage to contractors who spend a “substantial part” of their time\nproviding “manual labor.” In either situation, the statute addresses only\nindependent contractors.\n Farm Bureau’s argument that the provision brings plaintiffs under the\nworkers’ compensation law fails at this most basic requirement. As the term\nindicates, an independent contractor is “one that contracts” with the principal.\nSee Contractor, WEBSTER’S THIRD NEW INTERNATIONAL DICTIONARY (2002)\n(also defining “contractor” as “a party to a bargain”). Under this widespread\nunderstanding of the term, Jorge-Chavelas and Moreno-Abarca are not\nHarang’s contractors; they never entered into an express or implied agreement\nwith the company. La. Civ. Code Ann. art. 11 (“The words of a law must be\ngiven their generally prevailing meaning.”). A common example illustrates\n\n 7\n\f Case: 18-30388 Document: 00514863514 Page: 8 Date Filed: 03/07/2019\n\n\n\n No. 18-30388\nthis. Assume a homeowner hires a pest control company to exterminate bugs.\nThe company becomes the homeowner’s contractor. But that typically does not\nresult in an agency relationship between the homeowner and the employee of\nthe pest control company.\n Other language in section 1021(7) confirms that the statute is referring\nto “independent contractor” in this ordinary sense of the term—one who has a\ncontractual relationship with the principal. The statute excepts only an\nindependent contractor for whom a substantial part of his work is “spent in\nmanual labor by him in carrying out the terms of the contract.” (emphases\nadded). And the relevant contract is one “for a specified recompense for a\nspecified result either as a unit or as a whole.” But, as in this case, the\nemployees of an independent contractor are typically not parties to “the\ncontract,” which would be between the principal and the contractor.\n What little guidance we have from the Supreme Court of Louisiana is\nconsistent with this plain meaning of the statute. In Lushute v. Diesi, the court\nremarked that the exception was meant to extend to a contractor engaged in\nmanual labor “in carrying out the terms of his contract with the principal.” 354\nSo. 2d 179, 182 (La. 1977) (emphasis added). This suggests the state high court\nwould adopt this natural reading—that the statute covers only contractors\nthemselves—rather than Farm Bureau’s more expansive one. And that\ncomports with the Louisiana Supreme Court’s general approach to workers’\ncompensation laws. When interpreting the immunity afforded employers,\n“every presumption should be on the side of preserving the general tort or\ndelictual rights of an injured worker against the actual wrongdoer, in the\nabsence of explicit statutory language limiting or excluding such rights.”\nChampagne v. Am. Alt. Ins. Corp., 112 So. 3d 179, 184 (La. 2013) (quoting\nRoberts v. Sewerage & Water Bd. of New Orleans, 634 So. 2d 341, 346 (La.\n1994)).\n 8\n\f Case: 18-30388 Document: 00514863514 Page: 9 Date Filed: 03/07/2019\n\n\n\n No. 18-30388\n Despite the absence of that necessary statutory command, three\nLouisiana intermediate court decisions have held or suggested that principals\nare immune from tort suits brought by their contractors’ employees if those\nemployees were engaged in manual labor. In Lumar v. Zappe Endeavors,\nL.L.C., an employee of an independent contractor sued his employer’s principal\nin tort. 946 So. 2d 188 (La. App. 5 Cir. 2006). Louisiana’s Fifth Circuit Court\nof Appeal held that, because a contractor “performs its duties through its\nemployees,” the “limitations applicable to [the contractor] are also applicable\nto its employees.” Id. at 191. Two other courts relied on Lumar not to\nimmunize an employer, but to find a contractor’s employee was entitled to\nrecover workers’ compensation from the contractor’s principal. Courtney v.\nFletcher Trucking, 111 So. 3d 411, 418 n.6 (La. App. 1 Cir. 2012); Moss v.\nTommasi Constr., Inc., 37 So. 3d 492, 499 (La. App. 3 Cir. 2010).\n Three decisions do not jurisprudence constante make. That is especially\ntrue when the court that first announced the rule Farm Bureau presses us to\nadopt declined to follow it just three years later. In Daigle v. McGee Backhoe\n& Dozer Service, the Fifth Circuit Court of Appeal denied a claim for workers’\ncompensation brought by an independent contractor’s employee against the\ncontractor’s principal. 16 So. 3d 4 (La. App. 5 Cir. 2009). As a dissent in that\ncase pointed out, following Lumar would have made the contractor’s employee\neligible for workers’ compensation under section 1021(7). 6 Id. at 8 (Winsberg,\nJ., dissenting). The majority instead suggested that an employee of a\ncontractor is eligible for workers’ compensation against his employer’s\nprincipal, if at all, through a separate provision, section 23:1061, which defines\n“statutory employment.” Id. at 7. That statute authorizes, in certain\n\n\n 6 The plaintiff in Daigle made the same point, albeit without citing Lumar. Original\nBrief of Eddie Daigle, Daigle v. McGee Backhoe & Dozer Serv., 16 So. 3d 4 (La. App. 5 Cir.\n2009), 2008 WL 5478293, at *7–8.\n 9\n\f Case: 18-30388 Document: 00514863514 Page: 10 Date Filed: 03/07/2019\n\n\n\n No. 18-30388\ncircumstances, a claim for workers’ compensation by a contractor’s employee\nagainst the contractor’s principal “as if he were [that] principal’s employee.”\n13 H. ALSTON JOHNSON III, LA. CIV. LAW. TREATISE, WORKERS’ COMPENSATION\nLAW AND PRACTICE § 121 (5th ed. 2018) (emphasis in original).\n Other Louisiana courts have likewise analyzed cases like this one\nthrough the lens of statutory employment, explaining that section 1061\n“provides guidance as to when a contractor’s employee, rather than the\ncontractor himself, may recover under the principal’s workers’ compensation\nliability.” Miller v. Higginbottom, 768 So. 2d 127, 132 (La. App. 2 Cir. 2000);\nsee also Prejean v. Maint. Enters., Inc., 8 So. 3d 766, 770 (La. App. 4 Cir. 2009);\nPoirrier v. Cajun Insulation, Inc., 459 So. 2d 737, 738–39 (La. App. 4 Cir. 1984).\nLouisiana’s leading workers’ compensation treatise agrees that statutory\nemployment is the proper framework for analyzing whether the employee of\nan independent contractor can recover workers’ compensation from the\nprincipal. See JOHNSON III, supra § 82 (noting the contractor’s pursuit of\ncompensation would be analyzed under section 1021(7) while his employee\n“must seek compensation under the different test of [section] 1061”).\n That makes sense as the terms of the statutory employment statute\ndirectly address the employee-of-an-independent-contractor situation we\nconfront. When applicable, workers’ compensation is the exclusive remedy for\na contractor’s employee against the principal. La. Rev. Stat. Ann.\n§ 23:1061(A)(1). The catch is that the relationship must be formed by contract.\nId. § 23:1061(A)(3). 7 No such contract exists in this case, which explains why\nFarm Bureau does not seek section 1061’s help. But the existence of this\n\n\n\n 7 There is another way to create the statutory employment relationship known as the\n“two contract” theory, but it is not applicable to this case. La. Rev. Stat. Ann. § 23:1061(A)(2);\nsee also Allen v. Ernest N. Morial-New Orleans Exhibition Hall Auth., 842 So. 2d 373, 379\n(La. 2003).\n 10\n\f Case: 18-30388 Document: 00514863514 Page: 11 Date Filed: 03/07/2019\n\n\n\n No. 18-30388\nexpress avenue for employees of contractors to seek workers’ compensation\nfrom a principal (and in turn for those principals to seek immunity) further\nsupports limiting section 1021(7) to independent contractors themselves, not\ntheir employees. La. Civ. Code Ann. art. 13 (“Laws on the same subject matter\nmust be interpreted in reference to each other.”); Fontenot v. Reddell Vidrine\nWater Dist., 836 So. 2d 14, 28 (La. 2003) (“It is a fundamental rule of statutory\nconstruction that when two statutes deal with the same subject matter, the\nstatute specifically directed to the matter at issue must prevail as an exception\nto the more general statute.”).\n Sections 1021(7) and 1061 are both deviations from typical workers’\ncompensation principles, but they serve different purposes. Section 1021(7)\nprotects a specific class of independent contractors who would not otherwise be\nentitled to benefits. It was added because, when it came to manual laborers,\nthe “distinction between contractor and employee had become so tenuous and\nso difficult to administer that the cases were in a state of almost hopeless\nconfusion, and many injustices were apparent.” JOHNSON III, supra § 78. To\nsettle the seemingly interminable debate, the Louisiana legislature resolved\nthat those who contracted to do manual labor were entitled to benefits, no\nmatter what a multifactor test said about their relationship to the principal.\nId.\n Section 1061 addresses a different concern—contractors who lack the\nassets to pay workers’ compensation. To encourage principals to hire solvent\ncontractors, the statute offers them a choice. If a principal enters into a\nstatutory employment contract, in exchange for assuming workers’\ncompensation liability, it obtains two benefits: 1) tort immunity from the\ncontractor’s employees; and 2) indemnification from the contractor if those\nemployees recover workers’ compensation from the principal. See La. Rev.\nStat. Ann. § 23:1061(B). Not a bad option if you hire a solvent contractor (but\n 11\n\f Case: 18-30388 Document: 00514863514 Page: 12 Date Filed: 03/07/2019\n\n\n\n No. 18-30388\nif the contractor is insolvent, indemnification won’t help). Or those principals\ncan choose to forego immunity if they would rather limit their vulnerability to\nworkers’ compensation claims. So, although “[o]rdinarily a principal is not and\nshould not be subjected to the compensation claims of his contractor’s\nemployees,” statutory employment uses the promise of immunity and\nindemnification to encourage principals to agree otherwise. JOHNSON III,\nsupra § 78; see also id. at § 121 (noting that the interposition of a contractor\nbetween the principal and the contractor’s employees “would not deprive the\nemployee of protection so long as the intermediary contractor was solvent or\nprotected by insurance”).\n This statutory employment law that targets the employment\nrelationship we confront, together with the ordinary meaning of\nsection 1021(7), tangential but informative guidance from Louisiana’s highest\ncourt, and the view of a leading authority on Louisiana workers’ compensation\nlaw, trumps a handful of decisions from intermediate state courts, one of which\nhas backtracked from its earlier view. The district court’s Erie guess is a solid\none. 8 Section 1021(7) does not obligate a principal to provide workers’\ncompensation to the employees of its independent contractors, so it does not\nafford Harang immunity from this suit. 9\n\n\n\n 8Farm Bureau asked us to certify this question about the manual labor exception to\nthe Supreme Court of Louisiana. Because our analysis leads us to conclude that the issue is\nnot a close one, we decline that invitation.\n 9 Farm Bureau contends that our interpretation of the manual labor exception\n\nthreatens to “obliterate” its role within Louisiana’s workers’ compensation regime. But we\ndo nothing to displace that statute where its text says it applies—when an independent\ncontractor herself is primarily engaged in manual labor. If anything, it is Farm Bureau’s\nreading of the manual labor exception that threatens to displace the role of another statute.\nIf employees of independent contractors engaged in manual labor are automatically entitled\nto workers’ compensation from the principal, that would create a large exception to\nsection 1061’s usual rule that a principal is liable for such claims only when a statutory\nemployment relationship is created by contract. La. Rev. Stat. Ann. § 23:1061(A)(3). And\n\n 12\n\f Case: 18-30388 Document: 00514863514 Page: 13 Date Filed: 03/07/2019\n\n\n\n No. 18-30388\n B.\n Even if plaintiffs are not covered as Harang’s independent contractors,\nFarm Bureau argues that the workers’ compensation regime still applies for a\nmore traditional reason: the plaintiffs were Harang’s employees. It says that\ntwo different provisions treat the plaintiffs as employees.\n The parties call the first the “presumed employee” provision. It provides\nthat a “person rendering service for another in any trade[], business[] or\noccupation[] . . . is presumed to be an employee.” La. Rev. Stat. Ann. § 23:1044.\nFarm Bureau does not dispute the general view of Louisiana courts that this\npresumption is overcome when the worker lacks an express or implied\nemployment agreement with the business. See, e.g., Dustin v. DHCI Home\nHealth Servs., Inc., 673 So. 2d 356, 359 (La. App. 1 Cir. 1996). Just as we do\nnow, the district court rejected the “presumed employee” argument for\nimmunity on that ground because, as we have already explained, plaintiffs did\nnot have an express or implied agreement with Harang. They are not\npresumed employees. 10\n\n\nFarm Bureau’s view leads to other interpretive problems. As plaintiffs’ counsel noted at oral\nargument, if an independent contractor like Lowry is engaged primarily in the provision of\nmanual labor, which of its employees are entitled to benefits from the principal? Only those\nactually engaged in manual labor, or would Harang also be liable to pay workers’\ncompensation to Lowry’s office manager?\n Nor does our decision render workers’ compensation unavailable to the employees of\nan independent contractor. As in this case, the direct employer (Lowry) is responsible for\nworkers’ compensation.\n 10 There is a factual and logical flaw with a more nuanced argument Farm Bureau\n\nmakes under this statute. It contends: 1) that the presumption of employee status is\novercome if the worker is an independent contractor, see Hillman v. Comm-Care, Inc., 805\nSo. 2d 1157, 1161 (La. 2002), but 2) section 1021(7) explicitly includes independent\ncontractors engaged primarily in manual labor in Louisiana’s workers’ compensation regime,\nand 3) Jorge-Chavelas and Moreno-Abarca were engaged in manual labor, so 4) they are\npresumed employees. This syllogism falls apart at step two. Section 1021(7) does not bring\nmanual laborers back under the presumption. That is because it does not render manual\nlaborers employees—it just entitles those independent contractors to workers’ compensation\nfrom their principal. JOHNSON III, supra § 74. In any event, we have already held that\n\n 13\n\f Case: 18-30388 Document: 00514863514 Page: 14 Date Filed: 03/07/2019\n\n\n\n No. 18-30388\n C.\n Farm Bureau’s final recourse is to characterize the plaintiffs as Harang’s\nborrowed employees. Louisiana makes borrowing employers (“special\nemployers” in civil law lingo) and lending employers (“general employers”)\nliable “jointly and in solido to pay” workers’ compensation for injuries suffered\nby a borrowed employee. La. Rev. Stat. Ann. § 23:1031(C). In exchange for\nthat joint liability to pay workers’ compensation, both the special and general\nemployer are immune from negligence suits. Id.\n The borrowed servant doctrine arises in many areas, with some of its\ndeepest roots in maritime law. See Standard Oil v. Anderson, 212 U.S. 215\n(1909). When applying the Louisiana workers’ compensation version, courts\nuse either a nine- or ten-factor test to determine whether a borrowed\nemployment relationship exists. The two tests are essentially identical.\nCompare McGinnis v. Waste Mgmt. of La., L.L.C., 914 So. 2d 612, 616 (La. App.\n2 Cir. 2005) (describing nine-factor test), with Billeaud v. Poledore, 603 So. 2d\n754, 756 (La. App. 1 Cir. 1992) (describing ten-factor test). The district court\napplied the ten-factor test, but under either one and under any standard of\nreview 11 the result is the same: Jorge-Chavelas and Moreno-Abarca were not\nborrowed employees.\n First and foremost, Lowry at all times controlled its planters. See Lastie\nv. Cooper, 167 So. 3d 150, 153 (La. App. 5 Cir. 2014). It chose which planters\n\n\n\nplaintiffs are not Harang’s independent contractors. They are further removed as the\nemployees of Harang’s independent contractor.\n 11 Farm Bureau contends that we should review the district court’s ruling on this\n\nquestion de novo, while the plaintiffs instead believe the proper standard is clear error. They\nare both right. While ultimately the plaintiff’s “borrowed servant status is a legal issue”\nreviewed de novo, the factors considered in making that determination are “factual” and their\napplication is reviewed for clear error. Sanchez v. Harbor Const. Co., Inc., 968 So. 2d 783,\n786 (La. App. 4 Cir. 2007); see also Capps v. N.L. Baroid-NL Indus., Inc., 784 F.2d 615, 617\n(5th Cir. 1986) (explaining that a “district court decides the borrowed employee issue as a\nmatter of law,” but characterizing the factors as “factual ingredients”).\n 14\n\f Case: 18-30388 Document: 00514863514 Page: 15 Date Filed: 03/07/2019\n\n\n\n No. 18-30388\nwent to which farms, planters were required “to work all hours as directed by\n[Lowry] personnel,” and Harang’s owner himself admitted he could not control\nthe planters. There was no agreement recognizing a borrowed employment\nrelationship, the planters never acquiesced to being borrowed employees,\nLowry maintained a close relationship with the planters throughout the\nseason, only Lowry could fire the planters, and it—not Harang—was obligated\nto pay them. The only factors weighing in favor of a borrowed employment\nrelationship—that the planters were doing Harang’s work for which Harang\nprovided the tools—do not overcome the number and importance of the factors\nweighing against it. We therefore also reject Farm Bureau’s contention that\nHarang was a borrowing employer.\n ***\n Plaintiffs were neither employees of Harang nor its independent\ncontractors. Instead, they were employees of Harang’s independent contractor.\nThat means Harang enjoys no immunity from suit.\n The judgment is AFFIRMED.\n\n\n\n\n 15\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Alejandro JORGE-CHAVELAS; Alfredo Moreno-Abarca, Plaintiffs - Appellees v. LOUISIANA FARM BUREAU CASUALTY INSURANCE COMPANY; Louisiana Farm Bureau Mutual Insurance Company, Defendants - Appellants v. American Interstate Insurance Company, Intervenor Plaintiff - Appellee\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-07\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 18-30388 Document: 00514863514 Page: 1 Date Filed: 03/07/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n No. 18-30388 March 7, 2019\\n Lyle W. Cayce\\nALEJANDRO JORGE-CHAVELAS; ALFREDO MORENO-ABARCA, Clerk\\n\\n Plaintiffs - Appellees\\n\\nv.\\n\\nLOUISIANA FARM BUREAU CASUALTY INSURANCE COMPANY;\\nLOUISIANA FARM BUREAU MUTUAL INSURANCE COMPANY,\\n\\n Defendants - Appellants\\n\\nv.\\n\\nAMERICAN INTERSTATE INSURANCE COMPANY,\\n\\n Intervenor Plaintiff - Appellee\\n\\n\\n\\n\\n Appeal from the United States District Court\\n for the Middle District of Louisiana\\n\\n\\nBefore KING, HIGGINSON, and COSTA, Circuit Judges.\\nGREGG COSTA, Circuit Judge:\\n Workers’ compensation laws strike a statutory bargain between labor\\nand management. They all but guarantee that a worker will recover from an\\nemployer for workplace injuries. In exchange for that certainty, the worker\\ngives up the right to pursue a potentially larger recovery in a tort suit—\\nemployers are immune from such claims.\\n\\f Case: 18-30388 Document: 00514863514 Page: 2 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\n These tradeoffs mean that questions about whether the statutory\\nscheme covers an injured worker can cause businesses and workers alike to\\noscillate between seemingly opposed positions. A worker uncertain about the\\nchances of a tort suit will often seek workers’ compensation, prompting the\\nbusiness to argue that the worker does not fall within the statutory protections.\\nIf the worker has a strong tort claim, the roles may flip—the business then has\\nan incentive to argue that workers’ compensation is the worker’s exclusive\\nremedy.\\n This case is of the latter variety. The insurer of a Louisiana sugarcane\\nfarm has raised several arguments that the farm is entitled to statutory\\nimmunity from this lawsuit brought by two injured cane planters. Those\\nworkers—entitled to a $2.5 million recovery if workers’ compensation does not\\napply—hope to show otherwise.\\n I.\\n Alejandro Jorge-Chavelas and Alfredo Moreno-Abarca, Mexican citizens\\nin the United States on work visas, were severely injured while working on a\\nLouisiana sugarcane farm operated by Harang Sugars, L.L.C. Their legs were\\ncrushed when a Harang employee drove into the sugarcane cart they were\\nsitting on.\\n No one disputes that Harang’s employee was at fault. Nor does anyone\\ndispute the damages the plaintiffs suffered. Instead, Harang’s insurers\\n(collectively “Farm Bureau”) contend that Jorge-Chavelas and Moreno-Abarca\\nwere Harang’s employees, whose injuries are excluded from its general liability\\npolicy. Alternatively, Farm Bureau argues that Louisiana workers’\\ncompensation laws grant its insured immunity from this suit. Both positions\\nturn on the nature of the plaintiffs’ employment. And so we turn to the\\narrangement between the four main players: Jorge-Chavelas, Moreno-Abarca,\\ntheir direct employer (Lowry Farms, Inc.), and Harang.\\n 2\\n\\f Case: 18-30388 Document: 00514863514 Page: 3 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\n Lowry plants sugarcane for other farmers. Because the sugarcane\\nplanting season is short but labor intensive, farmers prefer to contract out the\\nwork rather than hire the necessary short-term workers. Once a farm\\ncontracts with it, Lowry sends recruiters to Mexico to find cane planters.\\nJorge-Chavelas and Moreno-Abarca were two such recruits. Lowry obtained\\nthe necessary visas and agreed to pay the workers an hourly rate and provide\\nthem housing, transportation to and from the worksite, and workers’\\ncompensation insurance. It also explained that the workers would “be required\\nto work all hours as directed by [Lowry’s] management personnel.”\\n Harang was one of Lowry’s clients. Their contract required Harang to\\npay Lowry on a per-acre-planted basis, as opposed to per hour worked by a\\nplanter. 1 The agreement treated the planters as Lowry’s employees, stating\\nthat the payments were “for the work performed by Lowry Farms, Inc.\\nworkers.” While Harang requested 21 workers for the season, it had no role in\\nthe selection of those individuals.\\n Once planting season began, Lowry recruiters became “crew leaders.”\\nThey oversaw planters in the fields, settled disputes between the planters,\\ncommunicated with the farmers, reported injuries suffered by the planters to\\nLowry, and arranged the planters’ transportation back to Mexico. They also\\ndecided which planters would work on which farms. Crew leaders selected\\n“straw bosses” to be their on-the-ground supervisors during the planting, and\\nthese Lowry employees trained the planters. At the end of each week, Harang\\nfilled out a time sheet for the planters, but it was the crew leaders’\\nresponsibility to report the planters’ hours to Lowry. Every week, Lowry paid\\nthe planters.\\n\\n\\n\\n Lowry gave Harang the option to pay an hourly rate to use its employees for “General\\n 1\\n\\nFarm Labor” on days when planting was infeasible. It never did so.\\n 3\\n\\f Case: 18-30388 Document: 00514863514 Page: 4 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\n On the farms, the planters worked side-by-side with Harang’s\\nemployees. Harang tractor drivers hauled the sugarcane carts while the Lowry\\nplanters followed behind in groups of three, pulling the cane from the carts and\\nplanting it in the ground. Harang provided the necessary equipment—the\\ntractors, carts, and sugarcane all belonged to Harang. But it typically did not\\nexert direct control over the planters. If its owner had a problem with the\\nplanters’ work, he would contact Lowry’s office manager, who would contact\\nthe crew leader, who would in turn communicate the concern to the planters.\\nAnd only Lowry could fire its planters—Harang could voice concern about a\\nplanter in the hope that Lowry would find a substitute, but it could not\\nterminate his employment.\\n Harang’s management did not believe the planters were its employees.\\nOn the day of the accident, after calling emergency services, Harang’s owner\\nimmediately notified Lowry. When asked why, he replied, “Because that’s\\ntheir employees.” Indeed, Lowry’s workers’ compensation insurer covered\\nplaintiffs’ medical expenses. 2\\n Jorge-Chavelas and Moreno-Abarca sued Harang in federal district\\ncourt, invoking diversity jurisdiction. After the court denied competing\\nmotions for summary judgment, a stipulated bench trial followed. The parties\\nagreed that Harang was at fault and that total damages would be $2.5 million\\n(the limit of the Farm Bureau policy). The court had to decide the employment\\nstatus of the plaintiffs and, relatedly, whether Harang was immune from suit.\\nConcluding that the plaintiffs were not Harang’s employees and that the\\nworkers’ compensation laws did not otherwise provide Harang immunity, the\\n\\n\\n\\n 2 The district court awarded that insurer—intervenor American Interstate Insurance\\nCompany—reimbursement for the payments it made to and on behalf of the appellees.\\nAmerican Interstate has informed the court that it too hopes we affirm the judgment below,\\nstanding on the arguments plaintiffs make.\\n 4\\n\\f Case: 18-30388 Document: 00514863514 Page: 5 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\ndistrict court entered judgment in favor of Jorge-Chavelas for $1,937,500 and\\nMoreno-Abarca for $562,500.\\n II.\\n Louisiana law applies in this diversity case. Erie R.R. Co. v. Tompkins,\\n304 U.S. 64 (1938). Our task is to “determine as best [we] can [how] the\\nLouisiana Supreme Court would decide” it. Gulf & Miss. River Transp. Co. v.\\nBP Oil Pipeline Co., 730 F.3d 484, 488 (5th Cir. 2013) (quotation omitted).\\nWhen the absence of a controlling high court decision requires us to make an\\n“Erie guess” about Louisiana law, we consider many of the same sources we\\nuse when guessing the law of other jurisdictions: decisions and reasoning of\\nthe state’s courts; general rules of the jurisdiction, such as those governing\\nstatutory interpretation; and secondary sources like treatises. Id. at 488–89.\\nBut Louisiana’s “civilian methodology” means the pecking order of those\\nsources is different than it is for a common law state. Boyett v. Redland Ins.\\nCo., 741 F.3d 604, 607 (5th Cir. 2014). Louisiana’s “Constitution, codes, and\\nstatutes” are of paramount importance to its judges. Am. Int’l Specialty Lines\\nIns. Co. v. Canal Indem. Co., 352 F.3d 254, 260 (5th Cir. 2003). The doctrine\\nof stare decisis, a creature of common law, is alien to the civilian system.\\nBoyett, 741 F.3d at 607. Unlike stare decisis, which can flow from one decision,\\nin the civil system numerous court decisions must agree on a legal issue to\\nestablish jurisprudence constante (French for constant jurisprudence). And\\neven when that consensus exists in the caselaw, it remains only persuasive\\nauthority for the Erie guess; “we are not strictly bound” by the decisions of\\nLouisiana’s intermediate courts. Am. Int’l Specialty Lines, 352 F.3d at 261\\n(quoting Transcon. Gas Pipe Line Corp. v. Transp. Ins. Co., 953 F.2d 985, 988\\n(5th Cir. 1992)); see generally Alvin B. Rubin, Hazards of a Civilian Venturer\\nin Federal Court: Travel and Travail on the Erie Railroad, 48 LA. L. REV. 1369\\n(1988).\\n 5\\n\\f Case: 18-30388 Document: 00514863514 Page: 6 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\n A.\\n The primacy of legislation under the civil law tradition guides our\\nanalysis of the question Farm Bureau’s primary argument poses: Does\\nLouisiana’s choice to extend workers’ compensation—usually reserved for\\nemployees—to one class of independent contractors apply to the employees of\\nthose independent contractors and thus immunize Harang from this suit?\\n As noted above, workers’ compensation laws are a statutory compromise\\ngranting employers immunity from negligence suits 3 in exchange for their\\nguaranteeing a lesser recovery for on-the-job injuries. 4 Within that general\\nframework, states have experimented with the scope of both the coverage and\\nthe immunity. It is no different in Louisiana. For instance, although\\nindependent contractors generally are excluded from Louisiana’s workers’\\ncompensation regime, there is an exception. Section 23:1021(7) 5 of Louisiana’s\\nRevised Statutes states:\\n “Independent contractor” means any person who renders service,\\n other than manual labor, for a specified recompense for a specified\\n result either as a unit or as a whole, under the control of his\\n principal as to results of his work only, and not as to the means by\\n which such result is accomplished, and are expressly excluded\\n from the provisions of this Chapter unless a substantial part of the\\n work time of an independent contractor is spent in manual labor\\n by him in carrying out the terms of the contract, in which case the\\n\\n\\n\\n 3 Immunity does not extend to an employer’s intentional torts. La. Rev. Stat. Ann.\\n§ 23:1032(B).\\n 4 Among other limits, two potentially sizable categories of damages—pain and\\n\\nsuffering and punitive damages—are not recoverable in Louisiana as workers’ compensation.\\nThose benefits are limited to three types of loss: a partial compensation for lost wages, see\\nLa. Rev. Stat. Ann. § 23:1221(1)–(3), medical expenses, id. § 23:1203, and so-called “schedule”\\nlosses compensating for particular disfigurements, id. § 23:1221(4)(a)–(r); see also 13 H.\\nALSTON JOHNSON III, LA. CIV. LAW. TREATISE, WORKERS’ COMPENSATION LAW AND\\nPRACTICE § 271 (5th ed. 2018).\\n 5 We note, to avoid confusion, that changes to the Louisiana workers’ compensation\\n\\nlaws moved this provision from its previous position in section 1021(6) to section 1021(7).\\nSome cases discussed in this opinion cite the older section.\\n 6\\n\\f Case: 18-30388 Document: 00514863514 Page: 7 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\n independent contractor is expressly covered by the provisions of\\n this Chapter.\\nIn other words, an independent contractor who is engaged primarily in manual\\nlabor has a claim for workers’ compensation against his principal. More\\nimportantly to Farm Bureau, that principal is immunized from a negligence\\nsuit. La. Rev. Stat. Ann. § 23:1032.\\n Farm Bureau maintains that this statute applies not just to independent\\ncontractors, but also to the employees of independent contractors. In this case,\\nthat would mean that the principal (Harang) is immune from suit by the\\nemployees (Jorge-Chavelas and Moreno-Abarca) of the principal’s independent\\ncontractor (Lowry).\\n The text of the statute says otherwise, and that is where we must begin.\\nSee 84 Lumber Co. v. Cont’l Cas. Co., 914 F.3d 329, 334 (5th Cir. 2019)\\n(explaining that, in Louisiana, “[w]hen a law is clear and unambiguous . . . it\\nshall be applied as written”) (quotation omitted). Section 1021(7) excludes\\nmost independent contractors from the workers’ compensation regime. But it\\ngrants coverage to contractors who spend a “substantial part” of their time\\nproviding “manual labor.” In either situation, the statute addresses only\\nindependent contractors.\\n Farm Bureau’s argument that the provision brings plaintiffs under the\\nworkers’ compensation law fails at this most basic requirement. As the term\\nindicates, an independent contractor is “one that contracts” with the principal.\\nSee Contractor, WEBSTER’S THIRD NEW INTERNATIONAL DICTIONARY (2002)\\n(also defining “contractor” as “a party to a bargain”). Under this widespread\\nunderstanding of the term, Jorge-Chavelas and Moreno-Abarca are not\\nHarang’s contractors; they never entered into an express or implied agreement\\nwith the company. La. Civ. Code Ann. art. 11 (“The words of a law must be\\ngiven their generally prevailing meaning.”). A common example illustrates\\n\\n 7\\n\\f Case: 18-30388 Document: 00514863514 Page: 8 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\nthis. Assume a homeowner hires a pest control company to exterminate bugs.\\nThe company becomes the homeowner’s contractor. But that typically does not\\nresult in an agency relationship between the homeowner and the employee of\\nthe pest control company.\\n Other language in section 1021(7) confirms that the statute is referring\\nto “independent contractor” in this ordinary sense of the term—one who has a\\ncontractual relationship with the principal. The statute excepts only an\\nindependent contractor for whom a substantial part of his work is “spent in\\nmanual labor by him in carrying out the terms of the contract.” (emphases\\nadded). And the relevant contract is one “for a specified recompense for a\\nspecified result either as a unit or as a whole.” But, as in this case, the\\nemployees of an independent contractor are typically not parties to “the\\ncontract,” which would be between the principal and the contractor.\\n What little guidance we have from the Supreme Court of Louisiana is\\nconsistent with this plain meaning of the statute. In Lushute v. Diesi, the court\\nremarked that the exception was meant to extend to a contractor engaged in\\nmanual labor “in carrying out the terms of his contract with the principal.” 354\\nSo. 2d 179, 182 (La. 1977) (emphasis added). This suggests the state high court\\nwould adopt this natural reading—that the statute covers only contractors\\nthemselves—rather than Farm Bureau’s more expansive one. And that\\ncomports with the Louisiana Supreme Court’s general approach to workers’\\ncompensation laws. When interpreting the immunity afforded employers,\\n“every presumption should be on the side of preserving the general tort or\\ndelictual rights of an injured worker against the actual wrongdoer, in the\\nabsence of explicit statutory language limiting or excluding such rights.”\\nChampagne v. Am. Alt. Ins. Corp., 112 So. 3d 179, 184 (La. 2013) (quoting\\nRoberts v. Sewerage & Water Bd. of New Orleans, 634 So. 2d 341, 346 (La.\\n1994)).\\n 8\\n\\f Case: 18-30388 Document: 00514863514 Page: 9 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\n Despite the absence of that necessary statutory command, three\\nLouisiana intermediate court decisions have held or suggested that principals\\nare immune from tort suits brought by their contractors’ employees if those\\nemployees were engaged in manual labor. In Lumar v. Zappe Endeavors,\\nL.L.C., an employee of an independent contractor sued his employer’s principal\\nin tort. 946 So. 2d 188 (La. App. 5 Cir. 2006). Louisiana’s Fifth Circuit Court\\nof Appeal held that, because a contractor “performs its duties through its\\nemployees,” the “limitations applicable to [the contractor] are also applicable\\nto its employees.” Id. at 191. Two other courts relied on Lumar not to\\nimmunize an employer, but to find a contractor’s employee was entitled to\\nrecover workers’ compensation from the contractor’s principal. Courtney v.\\nFletcher Trucking, 111 So. 3d 411, 418 n.6 (La. App. 1 Cir. 2012); Moss v.\\nTommasi Constr., Inc., 37 So. 3d 492, 499 (La. App. 3 Cir. 2010).\\n Three decisions do not jurisprudence constante make. That is especially\\ntrue when the court that first announced the rule Farm Bureau presses us to\\nadopt declined to follow it just three years later. In Daigle v. McGee Backhoe\\n& Dozer Service, the Fifth Circuit Court of Appeal denied a claim for workers’\\ncompensation brought by an independent contractor’s employee against the\\ncontractor’s principal. 16 So. 3d 4 (La. App. 5 Cir. 2009). As a dissent in that\\ncase pointed out, following Lumar would have made the contractor’s employee\\neligible for workers’ compensation under section 1021(7). 6 Id. at 8 (Winsberg,\\nJ., dissenting). The majority instead suggested that an employee of a\\ncontractor is eligible for workers’ compensation against his employer’s\\nprincipal, if at all, through a separate provision, section 23:1061, which defines\\n“statutory employment.” Id. at 7. That statute authorizes, in certain\\n\\n\\n 6 The plaintiff in Daigle made the same point, albeit without citing Lumar. Original\\nBrief of Eddie Daigle, Daigle v. McGee Backhoe & Dozer Serv., 16 So. 3d 4 (La. App. 5 Cir.\\n2009), 2008 WL 5478293, at *7–8.\\n 9\\n\\f Case: 18-30388 Document: 00514863514 Page: 10 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\ncircumstances, a claim for workers’ compensation by a contractor’s employee\\nagainst the contractor’s principal “as if he were [that] principal’s employee.”\\n13 H. ALSTON JOHNSON III, LA. CIV. LAW. TREATISE, WORKERS’ COMPENSATION\\nLAW AND PRACTICE § 121 (5th ed. 2018) (emphasis in original).\\n Other Louisiana courts have likewise analyzed cases like this one\\nthrough the lens of statutory employment, explaining that section 1061\\n“provides guidance as to when a contractor’s employee, rather than the\\ncontractor himself, may recover under the principal’s workers’ compensation\\nliability.” Miller v. Higginbottom, 768 So. 2d 127, 132 (La. App. 2 Cir. 2000);\\nsee also Prejean v. Maint. Enters., Inc., 8 So. 3d 766, 770 (La. App. 4 Cir. 2009);\\nPoirrier v. Cajun Insulation, Inc., 459 So. 2d 737, 738–39 (La. App. 4 Cir. 1984).\\nLouisiana’s leading workers’ compensation treatise agrees that statutory\\nemployment is the proper framework for analyzing whether the employee of\\nan independent contractor can recover workers’ compensation from the\\nprincipal. See JOHNSON III, supra § 82 (noting the contractor’s pursuit of\\ncompensation would be analyzed under section 1021(7) while his employee\\n“must seek compensation under the different test of [section] 1061”).\\n That makes sense as the terms of the statutory employment statute\\ndirectly address the employee-of-an-independent-contractor situation we\\nconfront. When applicable, workers’ compensation is the exclusive remedy for\\na contractor’s employee against the principal. La. Rev. Stat. Ann.\\n§ 23:1061(A)(1). The catch is that the relationship must be formed by contract.\\nId. § 23:1061(A)(3). 7 No such contract exists in this case, which explains why\\nFarm Bureau does not seek section 1061’s help. But the existence of this\\n\\n\\n\\n 7 There is another way to create the statutory employment relationship known as the\\n“two contract” theory, but it is not applicable to this case. La. Rev. Stat. Ann. § 23:1061(A)(2);\\nsee also Allen v. Ernest N. Morial-New Orleans Exhibition Hall Auth., 842 So. 2d 373, 379\\n(La. 2003).\\n 10\\n\\f Case: 18-30388 Document: 00514863514 Page: 11 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\nexpress avenue for employees of contractors to seek workers’ compensation\\nfrom a principal (and in turn for those principals to seek immunity) further\\nsupports limiting section 1021(7) to independent contractors themselves, not\\ntheir employees. La. Civ. Code Ann. art. 13 (“Laws on the same subject matter\\nmust be interpreted in reference to each other.”); Fontenot v. Reddell Vidrine\\nWater Dist., 836 So. 2d 14, 28 (La. 2003) (“It is a fundamental rule of statutory\\nconstruction that when two statutes deal with the same subject matter, the\\nstatute specifically directed to the matter at issue must prevail as an exception\\nto the more general statute.”).\\n Sections 1021(7) and 1061 are both deviations from typical workers’\\ncompensation principles, but they serve different purposes. Section 1021(7)\\nprotects a specific class of independent contractors who would not otherwise be\\nentitled to benefits. It was added because, when it came to manual laborers,\\nthe “distinction between contractor and employee had become so tenuous and\\nso difficult to administer that the cases were in a state of almost hopeless\\nconfusion, and many injustices were apparent.” JOHNSON III, supra § 78. To\\nsettle the seemingly interminable debate, the Louisiana legislature resolved\\nthat those who contracted to do manual labor were entitled to benefits, no\\nmatter what a multifactor test said about their relationship to the principal.\\nId.\\n Section 1061 addresses a different concern—contractors who lack the\\nassets to pay workers’ compensation. To encourage principals to hire solvent\\ncontractors, the statute offers them a choice. If a principal enters into a\\nstatutory employment contract, in exchange for assuming workers’\\ncompensation liability, it obtains two benefits: 1) tort immunity from the\\ncontractor’s employees; and 2) indemnification from the contractor if those\\nemployees recover workers’ compensation from the principal. See La. Rev.\\nStat. Ann. § 23:1061(B). Not a bad option if you hire a solvent contractor (but\\n 11\\n\\f Case: 18-30388 Document: 00514863514 Page: 12 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\nif the contractor is insolvent, indemnification won’t help). Or those principals\\ncan choose to forego immunity if they would rather limit their vulnerability to\\nworkers’ compensation claims. So, although “[o]rdinarily a principal is not and\\nshould not be subjected to the compensation claims of his contractor’s\\nemployees,” statutory employment uses the promise of immunity and\\nindemnification to encourage principals to agree otherwise. JOHNSON III,\\nsupra § 78; see also id. at § 121 (noting that the interposition of a contractor\\nbetween the principal and the contractor’s employees “would not deprive the\\nemployee of protection so long as the intermediary contractor was solvent or\\nprotected by insurance”).\\n This statutory employment law that targets the employment\\nrelationship we confront, together with the ordinary meaning of\\nsection 1021(7), tangential but informative guidance from Louisiana’s highest\\ncourt, and the view of a leading authority on Louisiana workers’ compensation\\nlaw, trumps a handful of decisions from intermediate state courts, one of which\\nhas backtracked from its earlier view. The district court’s Erie guess is a solid\\none. 8 Section 1021(7) does not obligate a principal to provide workers’\\ncompensation to the employees of its independent contractors, so it does not\\nafford Harang immunity from this suit. 9\\n\\n\\n\\n 8Farm Bureau asked us to certify this question about the manual labor exception to\\nthe Supreme Court of Louisiana. Because our analysis leads us to conclude that the issue is\\nnot a close one, we decline that invitation.\\n 9 Farm Bureau contends that our interpretation of the manual labor exception\\n\\nthreatens to “obliterate” its role within Louisiana’s workers’ compensation regime. But we\\ndo nothing to displace that statute where its text says it applies—when an independent\\ncontractor herself is primarily engaged in manual labor. If anything, it is Farm Bureau’s\\nreading of the manual labor exception that threatens to displace the role of another statute.\\nIf employees of independent contractors engaged in manual labor are automatically entitled\\nto workers’ compensation from the principal, that would create a large exception to\\nsection 1061’s usual rule that a principal is liable for such claims only when a statutory\\nemployment relationship is created by contract. La. Rev. Stat. Ann. § 23:1061(A)(3). And\\n\\n 12\\n\\f Case: 18-30388 Document: 00514863514 Page: 13 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\n B.\\n Even if plaintiffs are not covered as Harang’s independent contractors,\\nFarm Bureau argues that the workers’ compensation regime still applies for a\\nmore traditional reason: the plaintiffs were Harang’s employees. It says that\\ntwo different provisions treat the plaintiffs as employees.\\n The parties call the first the “presumed employee” provision. It provides\\nthat a “person rendering service for another in any trade[], business[] or\\noccupation[] . . . is presumed to be an employee.” La. Rev. Stat. Ann. § 23:1044.\\nFarm Bureau does not dispute the general view of Louisiana courts that this\\npresumption is overcome when the worker lacks an express or implied\\nemployment agreement with the business. See, e.g., Dustin v. DHCI Home\\nHealth Servs., Inc., 673 So. 2d 356, 359 (La. App. 1 Cir. 1996). Just as we do\\nnow, the district court rejected the “presumed employee” argument for\\nimmunity on that ground because, as we have already explained, plaintiffs did\\nnot have an express or implied agreement with Harang. They are not\\npresumed employees. 10\\n\\n\\nFarm Bureau’s view leads to other interpretive problems. As plaintiffs’ counsel noted at oral\\nargument, if an independent contractor like Lowry is engaged primarily in the provision of\\nmanual labor, which of its employees are entitled to benefits from the principal? Only those\\nactually engaged in manual labor, or would Harang also be liable to pay workers’\\ncompensation to Lowry’s office manager?\\n Nor does our decision render workers’ compensation unavailable to the employees of\\nan independent contractor. As in this case, the direct employer (Lowry) is responsible for\\nworkers’ compensation.\\n 10 There is a factual and logical flaw with a more nuanced argument Farm Bureau\\n\\nmakes under this statute. It contends: 1) that the presumption of employee status is\\novercome if the worker is an independent contractor, see Hillman v. Comm-Care, Inc., 805\\nSo. 2d 1157, 1161 (La. 2002), but 2) section 1021(7) explicitly includes independent\\ncontractors engaged primarily in manual labor in Louisiana’s workers’ compensation regime,\\nand 3) Jorge-Chavelas and Moreno-Abarca were engaged in manual labor, so 4) they are\\npresumed employees. This syllogism falls apart at step two. Section 1021(7) does not bring\\nmanual laborers back under the presumption. That is because it does not render manual\\nlaborers employees—it just entitles those independent contractors to workers’ compensation\\nfrom their principal. JOHNSON III, supra § 74. In any event, we have already held that\\n\\n 13\\n\\f Case: 18-30388 Document: 00514863514 Page: 14 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\n C.\\n Farm Bureau’s final recourse is to characterize the plaintiffs as Harang’s\\nborrowed employees. Louisiana makes borrowing employers (“special\\nemployers” in civil law lingo) and lending employers (“general employers”)\\nliable “jointly and in solido to pay” workers’ compensation for injuries suffered\\nby a borrowed employee. La. Rev. Stat. Ann. § 23:1031(C). In exchange for\\nthat joint liability to pay workers’ compensation, both the special and general\\nemployer are immune from negligence suits. Id.\\n The borrowed servant doctrine arises in many areas, with some of its\\ndeepest roots in maritime law. See Standard Oil v. Anderson, 212 U.S. 215\\n(1909). When applying the Louisiana workers’ compensation version, courts\\nuse either a nine- or ten-factor test to determine whether a borrowed\\nemployment relationship exists. The two tests are essentially identical.\\nCompare McGinnis v. Waste Mgmt. of La., L.L.C., 914 So. 2d 612, 616 (La. App.\\n2 Cir. 2005) (describing nine-factor test), with Billeaud v. Poledore, 603 So. 2d\\n754, 756 (La. App. 1 Cir. 1992) (describing ten-factor test). The district court\\napplied the ten-factor test, but under either one and under any standard of\\nreview 11 the result is the same: Jorge-Chavelas and Moreno-Abarca were not\\nborrowed employees.\\n First and foremost, Lowry at all times controlled its planters. See Lastie\\nv. Cooper, 167 So. 3d 150, 153 (La. App. 5 Cir. 2014). It chose which planters\\n\\n\\n\\nplaintiffs are not Harang’s independent contractors. They are further removed as the\\nemployees of Harang’s independent contractor.\\n 11 Farm Bureau contends that we should review the district court’s ruling on this\\n\\nquestion de novo, while the plaintiffs instead believe the proper standard is clear error. They\\nare both right. While ultimately the plaintiff’s “borrowed servant status is a legal issue”\\nreviewed de novo, the factors considered in making that determination are “factual” and their\\napplication is reviewed for clear error. Sanchez v. Harbor Const. Co., Inc., 968 So. 2d 783,\\n786 (La. App. 4 Cir. 2007); see also Capps v. N.L. Baroid-NL Indus., Inc., 784 F.2d 615, 617\\n(5th Cir. 1986) (explaining that a “district court decides the borrowed employee issue as a\\nmatter of law,” but characterizing the factors as “factual ingredients”).\\n 14\\n\\f Case: 18-30388 Document: 00514863514 Page: 15 Date Filed: 03/07/2019\\n\\n\\n\\n No. 18-30388\\nwent to which farms, planters were required “to work all hours as directed by\\n[Lowry] personnel,” and Harang’s owner himself admitted he could not control\\nthe planters. There was no agreement recognizing a borrowed employment\\nrelationship, the planters never acquiesced to being borrowed employees,\\nLowry maintained a close relationship with the planters throughout the\\nseason, only Lowry could fire the planters, and it—not Harang—was obligated\\nto pay them. The only factors weighing in favor of a borrowed employment\\nrelationship—that the planters were doing Harang’s work for which Harang\\nprovided the tools—do not overcome the number and importance of the factors\\nweighing against it. We therefore also reject Farm Bureau’s contention that\\nHarang was a borrowing employer.\\n ***\\n Plaintiffs were neither employees of Harang nor its independent\\ncontractors. Instead, they were employees of Harang’s independent contractor.\\nThat means Harang enjoys no immunity from suit.\\n The judgment is AFFIRMED.\\n\\n\\n\\n\\n 15\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1079,"cells":{"id":{"kind":"number","value":4598194,"string":"4,598,194"},"name":{"kind":"string","value":"In RE: Julius Omar ROBINSON, Movant. United States of America, Plaintiff-Appellee, v. Julius Omar Robinson, Also Known as Face, Also Known as Scar, Also Known as Scarface, Defendant-Appellant."},"name_abbreviation":{"kind":"string","value":"United States v. Robinson (In Re Robinson)"},"decision_date":{"kind":"string","value":"2019-03-08"},"docket_number":{"kind":"string","value":"18-10732; 18-70022"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Higginbotham, Smith, Engelhardt\", \"parties\": \"\", \"opinions\": [{\"author\": \"JERRY E. SMITH, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 18-70022 Document: 00514865791 Page: 1 Date Filed: 03/08/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n March 8, 2019\\n No. 18-10732\\n Lyle W. Cayce\\n Clerk\\nIN RE: JULIUS OMAR ROBINSON,\\n\\n Movant.\\n\\n * * * * *\\n\\n\\n No. 18-70022\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff–Appellee,\\n\\nversus\\n\\nJULIUS OMAR ROBINSON, Also Known as Face,\\nAlso Known as Scar, Also Known as Scarface,\\n\\n Defendant–Appellant.\\n\\n\\n\\n Appeals from the United States District Court\\n for the Northern District of Texas\\n\\n\\n\\n\\nBefore HIGGINBOTHAM, SMITH, and ENGELHARDT, Circuit Judges.\\nJERRY E. SMITH, Circuit Judge:\\n\\n Julius Robinson was sentenced to death for his role in multiple murders.\\n\\f Case: 18-70022 Document: 00514865791 Page: 2 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\nAfter we affirmed his conviction on direct appeal, Robinson filed a federal\\nhabeas corpus petition asserting six grounds for relief. The district court\\ndenied the petition. Nearly ten years later, Robinson filed a Federal Rule of\\nCivil Procedure 60(b)(6) motion for relief from judgment. The district court\\ndetermined that Robinson’s motion was “in actuality a second or successive\\npetition for habeas relief” and transferred it to this court.\\n\\n Robinson maintains that the district court erred by construing his Rule\\n60(b)(6) motion as a second or successive habeas petition. Finding no error,\\nand that Robinson fails to meet the standard for a second or successive petition,\\nwe deny his motion for authorization and dismiss for want of jurisdiction.\\n\\n I.\\n In 1998, Robinson murdered Johnny Shelton, “a man he mistakenly\\nbelieved responsible for an armed hijacking that cost him $30,000.” United\\nStates v. Robinson, 367 F.3d 278, 282 (5th Cir.), cert. denied, 543 U.S. 1005\\n(2004). Five months later, Robinson killed Juan Reyes in retaliation for “a\\nfraudulent drug transaction in which [Robinson] paid $17,000 for a block of\\nwood covered in sheetrock.” Id. Robinson was also involved “in a broad con-\\nspiracy that led to the murder of Rudolfo Resendez at the hands of Britt and\\nHendrick Tunstall.” Id. at 283.\\n\\n In 2002, a jury convicted Robinson on sixteen counts, including, inter\\nalia, 1 one count of murder while engaging in a continuing criminal enterprise,\\n\\n\\n 1 The jury also convicted Robinson on one count of conspiracy to distribute more than\\n100 kilograms of marihuana, in violation of 21 U.S.C. §§ 846 and 841(b)(1)(B) (Count 1); one\\ncount of conspiracy to distribute more than five kilograms of cocaine, in violation of 21 U.S.C.\\n§§ 846 and 841(b)(1)(A) (Count 2); three counts of possession of a firearm in furtherance of a\\ndrug trafficking crime, in violation of § 924(c)(1)(A)(i), (C)(i) (Counts 4, 8, and 17); three\\ncounts of carrying or using a firearm during a drug trafficking crime, in violation of\\n§ 924(c)(1)(A)(ii) (Counts 5, 9, and 13); and three counts of carrying or using and discharging\\na firearm during a drug trafficking crime, in violation of § 924(c)(1)(C)(iii) (Counts 6, 10,\\n 2\\n\\f Case: 18-70022 Document: 00514865791 Page: 3 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\nin violation of 21 U.S.C. § 848(e) (2012) (Count 3); three counts of murder in\\nthe course of carrying or using a firearm during a drug trafficking crime, in\\nviolation of 18 U.S.C. § 924(j) (Counts 7, 11, and 15); and one count of murder\\nwhile engaged in possession of more than five kilograms of cocaine with intent\\nto distribute, in violation of 21 U.S.C. §§ 841(a)(1), (b)(1)(A), and 848(e)\\n(Count 12). The district court sentenced Robinson to death on Counts 3, 7,\\nand 11. The court imposed a life sentence on Counts 12 and 15, to be served\\nconcurrently, and 300 months on Count 17, to run consecutively to the sen-\\ntences on Counts 12 and 15. 2 We affirmed Robinson’s conviction and sentence\\non direct appeal. Robinson, 367 F.3d at 293.\\n\\n In 2005, Robinson initiated federal habeas proceedings via a motion to\\nvacate conviction and sentence and for a new trial under 28 U.S.C. § 2255 and\\nRule 33 of the Federal Rules of Criminal Procedure. Robinson raised six\\ngrounds: (1) ineffective assistance of counsel (“IAC”) during the penalty phase,\\n(2) an equal protection (Batson) claim related to the prosecuting attorney’s\\nalleged use of preemptory challenges in a racially motived manner, (3) a claim\\nthat the Federal Death Penalty Act, as applied in Texas, violates the Equal\\nProtection Clause, (4) a claim of IAC on appeal, (5) a due process claim related\\nto the prosecuting attorney’s alleged pursuit of fundamentally inconsistent\\ntheories at seriatim capital trials, and (6) a due process claim related to the\\nprosecutor’s alleged use of false and misleading testimony during the penalty\\nphase. Robinson sought to amend his motion by adding a seventh ground for\\n\\n\\nand 14).\\n 2 The court did not impose a sentence on Counts 1 and 2 because these counts are\\nlesser included offenses of Count 3. Similarly, it declined to impose a sentence on Counts 4,\\n5, and 6 because each is a lesser included offense of Count 7. Moreover, the court did not\\nimpose a sentence on Counts 8, 9, and 10 because those three counts are lesser included\\noffenses of Count 11. Lastly, it declined to impose a sentence on Counts 13 and 14 because\\nthey are lesser included offenses of Count 15.\\n 3\\n\\f Case: 18-70022 Document: 00514865791 Page: 4 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\nrelief—a defective-indictment claim based on the prosecuting attorney’s failure\\nto include aggravating factors for the capital charge. The district court granted\\nin part Robinson’s motion to amend, allowing him to “add documentary\\nevidence and corresponding argument relating back to his original petition.”\\nThe court denied Robinson’s request to add the defective-indictment claim,\\nfinding that we had already addressed the issue on direct appeal. 3\\n\\n In 2008, the district court denied Robinson’s motion to vacate his con-\\nviction and sentence under 28 U.S.C. § 2255, finding that each of his claims\\nwas without merit. The court also denied Robinson’s motions for a new trial\\nand an evidentiary hearing. With respect to Robinson’s request that the court\\nhold an evidentiary hearing on his habeas grounds for relief, the court noted\\nthat “the record before [it], including the exhibits submitted by Robinson with\\nhis motion, do[es] not create any contested fact issues that must be resolved in\\norder to decide Robinson’s claims.” 4 Moreover, the court decided Robinson’s\\nhabeas claims “either by assuming that everything Robinson allege[d] [was]\\ntrue or based on legal, not factual, bases.” Consequently, “because the record\\nbefore [the district] [c]ourt show[ed] conclusively that Robinson [was] not\\nentitled to relief, his request for an evidentiary hearing [was] denied.”\\n\\n Robinson filed a Federal Rule of Civil Procedure 59(e) motion for recon-\\n\\n\\n\\n 3 See United States v. Kalish, 780 F.2d 506, 508 (5th Cir. 1986) (“It is settled in this\\nCircuit that issues raised and disposed of in a previous appeal from an original judgment of\\nconviction are not considered in § 2255 [m]otions.”). On direct appeal, we held that “the\\nfailure to charge [the death penalty aggravating] factors in an indictment did not contribute\\nto Robinson’s conviction or death sentence.” Robinson, 367 F.3d at 289. The district court\\nalso determined that the Supreme Court cases cited by Robinson—United States v. Gonzalez–\\nLopez, 548 U.S. 140 (2006), and United States v. Resendiz–Ponce, 549 U.S. 102 (2007)—were\\ninapposite, and, in any event, because these cases considered procedural errors, they were\\nnot retroactively applicable to cases on collateral review.\\n Section 2255 “does not automatically require a hearing to dispose of every motion\\n 4\\n\\nmade under its statutory authority.” Coco v. United States, 569 F.2d 367, 369 (5th Cir. 1978).\\n 4\\n\\f Case: 18-70022 Document: 00514865791 Page: 5 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\nsideration of the order denying the motion to vacate sentencing without an\\nevidentiary hearing. The district court denied that motion 5 and declined to\\nissue a certificate of appealability (“COA”). We affirmed, and the Supreme\\nCourt denied Robinson’s petition for writ of certiorari.\\n\\n In February 2018, Robinson filed a Rule 60(b)(6) motion for relief from\\njudgment. He asserted that “the lack of due process in his post-conviction pro-\\nceedings constituted an extraordinary circumstance that justified re-opening\\nthe judgment in his case pursuant to Rule 60(b).” Relying on Supreme Court\\nprecedent established after the district court denied his § 2255 motion, Robin-\\nson contended that the district court (1) “wrongly denied his ability to appeal”\\nbecause that court (and the Fifth Circuit) “applied an erroneously high stan-\\ndard for obtaining a [COA],” (2) “erroneously barred [him] from conducting a\\nreasonable investigation,” and (3) erroneously denied his “right to amend his\\n[§] 2255 motion to include his [defective-indictment] claim.”\\n\\n The district court determined that the motion was, “in actuality[,] a sec-\\nond or successive petition for habeas relief” and transferred it to this court. On\\nappeal, Robinson asserts that the district court improperly construed his\\nRule 60(b)(6) motion as a second or successive § 2255 motion. In the event,\\nhowever, that we find the district court did not err, Robinson asks that we\\n\\n\\n\\n 5 The court emphasized that “[b]ona fide contested issues of fact raised in a motion to\\nvacate brought under § 2255 must be resolved on the basis of an evidentiary hearing. . . . But\\n§ 2255 does not require a hearing if the motion, files, and record of the case conclusively\\ndemonstrate that no relief is appropriate.” The court also stressed that “the record before\\nthis Court, including the exhibits submitted by Robinson with his motions, do[es] not create\\nany contested fact issues with regard to Robinson’s insufficiency-of-counsel claims that must\\nbe resolved in order to decide his case.” Instead, the court noted, “many of Robinson’s claims\\nare based on the record from the trial.” Moreover, “with regard to the claims for which Robin-\\nson has submitted additional evidence, the Court . . . decided these claims based on uncon-\\ntested allegations of fact and, where facts are contested, by assuming that what Robinson\\nalleges is true, or based on legal, not factual, bases.”\\n 5\\n\\f Case: 18-70022 Document: 00514865791 Page: 6 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\ncertify a second or successive § 2255 motion so that he may raise his impartial-\\njury claim in the district court.\\n\\n II.\\n “We review a district court’s determination as to whether a Rule 60(b)\\nmotion constitutes a second-or-successive habeas petition de novo.” In re\\nEdwards, 865 F.3d 197, 202–03 (5th Cir.), cert. denied, 137 S. Ct. 909 (2017).\\n\\n A.\\n Federal habeas review for a prisoner in federal custody is governed by\\n 28 U.S.C. § 2255, as amended by the Antiterrorism and Effective Death Pen-\\n alty Act of 1996 (“AEDPA”). “AEDPA limits the circumstances under which a\\n [federal] prisoner may file a successive application for federal habeas review.”\\n Edwards, 865 F.3d at 203. Under § 2255(h),\\n [a] second or successive motion must be certified as provided in\\n section 2244 by a panel of the appropriate court of appeals to\\n contain—\\n (1) newly discovered evidence that, if proven and viewed in\\n light of the evidence as a whole, would be sufficient to establish\\n by clear and convincing evidence that no reasonable fact-finder\\n would have found the movant guilty of the offense; or\\n (2) a new rule of constitutional law, made retroactive to cases\\n on collateral review by the Supreme Court, that was previ-\\n ously unavailable.\\n28 U.S.C §2255(h). Section 2244(a) provides,\\n No circuit or district judge shall be required to entertain an\\n application for a writ of habeas corpus to inquire into the deten-\\n tion of a person pursuant to a judgment of a court of the United\\n States if it appears that the legality of such detention has been\\n determined by a judge or court of the United States on a prior\\n application for a writ of habeas corpus, except as provided in sec-\\n tion 2255.\\nA petition is successive when it ‘raises a claim . . . that was or could have been\\n 6\\n\\f Case: 18-70022 Document: 00514865791 Page: 7 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\nraised in an earlier petition . . . .’” Edwards, 865 F.3d at 203 (quoting Harde-\\nmon v. Quarterman, 516 F.3d 272, 275 (5th Cir. 2008)).\\n\\n Federal Rule of Civil Procedure 60(b)(6) authorizes a court to “relieve a\\nparty or its legal representative from a final judgment, order, or proceeding for\\n. . . any other reason that justifies relief.” To prevail on a Rule 60(b)(6) motion\\nin a federal habeas proceeding, a movant must establish that (1) the motion\\nwas “made within a reasonable time” 6 and (2) “‘extraordinary circumstances’\\n[exist to] justify[] the reopening of a final judgment.” Gonzalez v. Crosby,\\n545 U.S. 524, 535 (2005) (quoting Ackermann v. United States, 340 U.S.\\n193, 199 (1950)). 7 Extraordinary circumstances “will rarely occur in the\\nhabeas context.” Id.\\n\\n “Because of the comparative leniency of Rule 60(b) [as compared to\\nAEDPA], petitioners sometimes attempt to file what are in fact second-or-\\nsuccessive habeas petitions under the guise of Rule 60(b) motions.” Edwards,\\n865 F.3d at 203. “[T]o bring a proper Rule 60(b) claim, a movant must show ‘a\\nnon-merits-based defect in the district court’s earlier decision on the federal\\nhabeas petition.’” Id. at 204 (quoting Balentine v. Thaler, 626 F.3d 842, 847\\n(5th Cir. 2010) (emphasis added). Thus, we have cautioned that\\n it is extraordinarily difficult to bring a claim of procedural defect\\n rather than a successive habeas claim, because ‘[p]rocedural defects\\n are narrowly construed. They include fraud on the habeas court, as\\n well as erroneous previous rulings which precluded a merits\\n\\n\\n Rule 60(c) states, “A motion under Rule 60(b) must be made within a reasonable\\n 6\\n\\ntime—and for reasons [in (b)](1), (2), and (3) no more than a year after the entry of the\\njudgment or order or the date of the proceeding.”\\n 7Although Gonzalez addressed the application of a Rule 60(b) motion only in the\\ncontext of a § 2254 habeas proceeding, we have joined “[n]early every circuit [in applying]\\nthe Gonzalez rationale to federal prisoners seeking habeas relief under § 2255.” Williams\\nv. Thaler, 602 F.3d 291, 302 & n.4 (5th Cir. 2010) (collecting cases); see also United States\\nv. Roberts, 360 F. App’x 584, 585 (5th Cir. 2010).\\n 7\\n\\f Case: 18-70022 Document: 00514865791 Page: 8 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\n determination—for example, a denial for such reasons as failure to\\n exhaust, procedural default, or statute-of limitations bar. They\\n generally do not include an attack based on the movant’s own con-\\n duct, or his habeas counsel’s omissions, which do not go to the integ-\\n rity of the proceedings, but in effect ask for a second chance to have\\n the merits determined favorably.’\\nId. at 205 (quoting In re Coleman, 768 F.3d 367, 371 (5th Cir. 2014)).\\n\\n Accordingly, “[a] federal court examining a Rule 60(b) motion should\\ndetermine whether it either: (1) presents a new habeas claim (an ‘asserted\\nfederal basis for relief from a . . . judgment of conviction’), or (2) ‘attacks the\\nfederal court’s previous resolution of a claim on the merits.’” Id. at 203 (quoting\\nGonzales, 545 U.S. at 530, 532). 8 A “Rule 60(b) motion [that] does either . . .\\nshould be treated as a second-or-successive habeas petition and subjected to\\nAEDPA’s limitation on such petitions.” Id. at 204. But a petitioner who “merely\\nasserts that a previous ruling which precluded a merits determination was in\\nerror—for example, a denial for such reasons as failure to exhaust, procedural\\ndefault, or statute-of-limitations bar,” is not asserting one of the aforemen-\\ntioned grounds. Id. 9\\n\\n B.\\n Robinson contends that the district court erred when it construed his\\nclaim concerning the denial of a COA as a second or successive habeas petition.\\nAfter the district court denied relief on each of the six grounds he raised in his\\n\\n\\n\\n 8 A federal court makes a merits determination when it concludes that “there exist or\\ndo not exist grounds entitling a petitioner to habeas corpus relief . . . .” Gonzalez, 545 U.S.\\nat 532 n.4. So, “[w]hen a movant asserts one of those grounds (or asserts that a previous\\nruling regarding one of those grounds was in error) he is making a habeas corpus claim.” Id.\\n 9 If a Rule 60(b) “motion challenges ‘not the substance of the federal court’s resolution\\nof a claim on the merits, but some defect in the integrity of the federal habeas proceedings,’\\nthen a Rule 60(b) motion is proper.” Coleman, 768 F.3d at 371 (quoting Gonzalez, 545 U.S.\\nat 532).\\n 8\\n\\f Case: 18-70022 Document: 00514865791 Page: 9 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\ninitial § 2255 motion, Robinson moved for a COA on his penalty-phase IAC\\nclaim. The court denied the application. Robinson then sought a COA from\\nthis court, but we also declined. The Supreme Court denied Robinson’s petition\\nfor writ of certiorari. Robinson v. United States, 565 U.S. 827 (2011).\\n\\n Robinson cites Buck v. Davis, 137 S. Ct. 759, 774 (2017), in which the\\nCourt reaffirmed that “[a] ‘court of appeals should limit its examination [at the\\nCOA stage] to a threshold inquiry into the underlying merit of [the] claims,’\\nand ask ‘only if the District Court’s decision was debatable.’” Id. (quoting\\nMiller-El v. Cockrell, 537 U.S. 322, 327, 348 (2003)). Robinson maintains that\\nboth the district court and this circuit erred when each declined to issue a COA\\nto him because both courts “effectively required him to prove he would succeed\\non appeal before granting the right to appeal.” Robinson asserts that both\\ncourts should have merely determined whether “it was at least debatable that\\nhe was deprived of the effective assistance of counsel at the penalty phase of\\nhis trial.”\\n\\n Robinson avers that the district court wrongly decided that “[t]he denial\\nof a COA did not preclude a merits determination,” because “merits review by\\nan appellate court is . . . its own independent proceeding that the appellant has\\na right to access.” Because “appellate merits review is a separate entity, . . .\\nan erroneous procedural ruling that precludes appellate merits review is\\nentitled to reconsideration under Rule 60(b).”\\n\\n The government maintains that Robinson’s denial-of-COA claim “is not\\na proper basis for a Rule 60(b)(6) motion because it does not seek to reopen a\\nruling that precluded a merits determination of his [IAC] claim.” Rather, Rob-\\ninson “seeks to reopen a ruling (the denial of a COA) that followed the district\\ncourt’s merits-based ruling on [his] [IAC] claim.” The government emphasizes\\nthat “a Rule 60(b) motion that seeks to revisit the federal court’s denial on the\\n 9\\n\\f Case: 18-70022 Document: 00514865791 Page: 10 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\nmerits of a claim for relief should be treated as a successive habeas petition”\\n(quoting Gonzalez, 545 U.S. at 534). 10 Asserting that Robinson’s Rule 60(b)\\nmotion attempts to do just that, the government contends that the district\\ncourt correctly determined the motion was a second or successive § 2255\\nmotion. 11\\n\\n The district court correctly concluded that Robinson “badly misreads\\nGonzalez.” The denial of a COA on Robinson’s IAC claim did not preclude a\\nmerits determination. Instead, the court reviewed and denied the claim on its\\nmerits as part of Robinson’s initial § 2255 motion. Because his Rule 60(b)\\nmotion attacks the district court’s merits-based resolution of his IAC claim, it\\nis best viewed as a second or successive petition. 12 The court did not err in\\nfinding that it had “no jurisdiction to consider [the motion].”\\n\\n C.\\n Robinson asserts that the district court erred in determining that his\\nrequest to interview the jurors was a second or successive § 2255 motion. He\\ncontends that “he was unreasonably barred from interviewing the trial jurors,\\nthus depriving him of a reasonable post-conviction investigation.” Citing In re\\nSessions, 672 F.2d 564, 566 (5th Cir. 1982), Robinson maintains that “it is well-\\nsettled law that a denial of discovery is not akin to a denial on the merits of a\\n\\n\\n 10The government highlights that “Robinson points to no authority holding that a\\nruling that precludes appellate review is the same as a ruling that precludes a merits\\ndetermination.”\\n 11 The government also avers that Buck does not “stand for the proposition that the\\ndenial of a COA is a proper basis for a Rule 60(b) motion” because “the denial of the COA was\\nnot the basis for Buck’s Rule 60(b) motion.” Instead, the inverse was true: “Buck sought a\\nCOA to appeal the denial of his Rule 60(b) motion . . . .”\\n 12See Gonzalez 545 U.S. at 532; Edwards, 865 F.3d at 203. The district court deter-\\nmined that Robinson’s motion was, “‘if not in substance a habeas corpus application, at least\\nsimilar enough that failing to subject it to the same requirements would be inconsistent with\\nthe statute’ governing successive petitions” (quoting Gonzalez, 545 U.S. at 531).\\n 10\\n\\f Case: 18-70022 Document: 00514865791 Page: 11 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\nclaim for relief.” 13 He cites Mitchell v. Rees, 261 F. App’x 825, 828–29 (6th Cir.\\n2008), for the proposition that “if [reopening] a case for the purposes of holding\\nan evidentiary hearing is a valid use of Rule 60(b), then [reopening] to conduct\\njuror interviews must certainly be valid.”\\n\\n Robinson avers that the district court was not correct that his “request\\n. . . seeks to develop evidence in support of an impartial-jury claim under the\\nSixth Amendment.” He contends that as part of his first habeas petition, he\\nsought to interview jurors and that “the reason that [an impartial-jury] claim\\nwas not raised to the [d]istrict [c]ourt in Robinson’s amended [§] 2255 motion\\nwas because the court prevented Robinson from conducting discovery.” Con-\\nsequently, “Robinson’s inability to raise an [impartial-jury] claim is a prime\\nexample of a defect in the integrity of the habeas proceedings.”\\n\\n In response, the government maintains that Robinson’s Rule 60(b)\\nmotion seeks to “reopen the [§] 2255 proceedings so that he [can] interview\\njurors ‘to determine what role, if any, racial bias played in his convictions and\\nsentences.’” The government notes, correctly, that “[a] habeas petitioner,\\nunlike the usual civil litigant in federal court, is not entitled to discovery as a\\nmatter of ordinary course.” Bracy v. Gramley, 520 U.S. 899, 904 (1997).\\nRather, as we stated in United States v. Fields, 761 F.3d 443, 478 (5th Cir.\\n2014), “[a] petitioner demonstrates ‘good cause’ [for discovery] under Rule 6(a)\\n[of the Rules Governing § 2255 Proceedings] ‘where specific allegations before\\nthe court show reason to believe that a petitioner may, if the facts are fully\\ndeveloped, be able to demonstrate that he is . . . entitled to relief” (quoting\\nBracy, 520 U.S. at 908–09). 14\\n\\n\\n See also Wellons v. Hall, 558 U.S. 220, 223 (2010) (per curiam). Robinson concedes,\\n 13\\n\\nhowever, that “Sessions does not concern Rule 60(b) motions.”\\n 14 Rule 6(a) of the Rules Governing § 2255 Proceedings “does not authorize fishing\\n 11\\n\\f Case: 18-70022 Document: 00514865791 Page: 12 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\n The government emphasizes that Robinson’s previous request to inter-\\nview jurors, filed as part of his first § 2255 petition, did not concern a potential\\nimpartial-jury claim, but instead related to his Batson and IAC claims. The\\ngovernment also highlights that when he made his initial interview request,\\nRobinson expressly acknowledged that he did not have a viable impartial-jury\\nclaim. Accordingly, although Robinson “certainly had the ability to bring the\\nclaim in his original [§] 2255 motion or to seek leave to amend his motion to\\nadd the claim,” he “chose not to because . . . there was no evidence to support\\nsuch a claim.” 15\\n\\n The best view is that Robinson is attempting to advance a new habeas\\nclaim related to jury impartiality (in light of Pena-Rodriguez v. Colorado, 137\\nS. Ct. 855 (2017)) under the guise of a Rule 60(b)(6) motion. His “motion seeks\\nto re-open the proceedings for the purpose of adding new claims” and, as such,\\nis “the definition of a successive claim.” Edwards, 865 F.3d at 204.\\n\\n The denial of Robinson’s discovery request during his initial habeas\\nproceedings—a request that was then related to his Batson and IAC claims—\\ndid not prevent a merits determination on those issues. Moreover, Robinson\\nwas not prevented from litigating his impartial-jury claim because of “a denial\\nfor such reasons as failure to exhaust, procedural default, or statute-of-\\nlimitations bar.” See Gonzalez, 545 U.S. at 532 n.4. Instead, Robinson chose\\n\\n\\n\\nexpeditions.” Ward v. Whitley, 21 F.3d 1355, 1367 (5th Cir. 1994).\\n 15 The government also posits that “[g]iven that federal courts disfavor post-verdict\\ninterviewing of jurors except where there is some showing of an illegal or prejudicial intrusion\\ninto the jury process, United States v. Riley, 544 F.2d 237, 242 (5th Cir. 1976), and that by\\nRobinson’s own admission, he could not make that requisite showing, Robinson’s alleged\\n‘inability’ to bring an impartial-jury claim hardly represents a ‘defect’ in the proceedings.” In\\nRiley, we strongly cautioned that “Courts simply [must] not denigrate jury trials by after-\\nwards ransacking the jurors in search of some ground, not previously supported by evidence,\\nfor a new trial.” Id.\\n 12\\n\\f Case: 18-70022 Document: 00514865791 Page: 13 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\nnot to bring this claim in his initial § 2255 motion because, as he acknowledged,\\nsuch a claim was frivolous. 16\\n\\n To the extent that Robinson now attempts to bring such a claim, the gov-\\nernment rightly posits that “[b]ecause the merits of Robinson’s discovery\\nrequest to interview jurors [are] wrapped up with, and dependent on, his abil-\\nity to bring a new claim for relief from the judgment of his conviction,” his\\nrequest is “a paradigmatic habeas claim.” Rodwell v. Pepe, 324 F.3d 66, 72 (1st\\nCir. 2003). 17 Accordingly, this claim is best viewed as a second or successive\\n§ 2255 motion.\\n\\n Ultimately, “[u]sing Rule 60(b) to present new claims for relief from a\\n. . . court’s judgment of conviction—even claims couched in the language of a\\ntrue Rule 60(b) motion—circumvents AEDPA’s requirement that a new claim\\nbe dismissed unless it relies on either a new rule of constitutional law or newly\\ndiscovered facts.” Gonzalez, 545 U.S. at 531. The district court did not err in\\ndetermining that Robinson’s claim is a second or successive habeas petition. 18\\n\\n\\n\\n 16The district court echoed this conclusion when it stated that “Robinson conceded he\\nhad no evidence of a Sixth Amendment violation.”\\n 17 The cases cited by Robinson are inapposite. The decision in Ruiz v. Quarterman,\\n504 F.3d 523, 526 (5th Cir. 2007), stands for the unremarkable proposition that a denial of\\n“relief based on procedural default and failure to exhaust” may properly be reviewed using a\\nRule 60(b) motion. Likewise, Balentine v. Thaler, 626 F.3d 842, 844–49 (5th Cir. 2010),\\nmerely affirmed that the denial of relief on the ground that a claim is “unexhausted and\\nprocedurally barred” may be challenged using the Rule 60(b) vehicle. Neither situation is\\npresented here. Importantly, the Ruiz court emphasized that “a Rule 60(b) motion is a\\nhabeas claim when it presents a new claim for relief, or when it presents new evidence in\\nsupport of a claim already litigated, or when it asserts a change in the substantive law gov-\\nerning the claim, or when it attacks the federal court’s previous resolution of a claim on the\\nmerits.” Ruiz, 504 F.3d at 526.\\n 18 Even if we were to find that Robinson’s impartial-jury claim did not constitute a\\nsecond or successive habeas petition, we would undoubtedly conclude that he fails to show\\nthat, as a result of the denial of his discovery request, “‘extraordinary circumstances’ [exist\\nto] justify[] the reopening of [the] final judgment” under Rule 60(b)(6). Gonzalez, 545 U.S. at\\n535 (quoting Ackermann, 340 U.S. at 199); see also Mitchell, 261 F. App’x at 828–31.\\n 13\\n\\f Case: 18-70022 Document: 00514865791 Page: 14 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\n D.\\n Robinson raises a third ground for relief in his Rule 60(b) motion. He\\nmaintains that the district court erred in finding that his challenge to the\\ndenial of his motion to amend his original § 2255 petition to include a defective-\\nindictment claim was substantive in nature. Citing a number of intervening\\nSupreme Court precedents, including Weaver v. Massachusetts, 137 S. Ct. 1899\\n(2017), and Williams v. Pennsylvania, 136 S. Ct. 1899 (2016), Robinson essen-\\ntially asserts that our determination in Robinson, 367 F.3d at 289—that the\\ngovernment’s “failure to charge [the death penalty aggravating] factors in an\\nindictment did not contribute to [his] conviction or death sentence” was harm-\\nless error “beyond a reasonable doubt”—was flawed.\\n\\n Robinson maintains that Weaver, in particular, “casts serious doubt on\\n[our] denial of Robinson’s defective indictment claim in two significant ways.”\\nFirst, “the Weaver Court’s description of the three general categories of struc-\\ntural error[ 19] make clear that this Court’s requirement that [Robinson’s]\\ndefective indictment claim affect the ‘fundamental fairness’ of his trial in order\\nto be structural was misguided.” Second, “Weaver left no doubt that this\\nCourt’s application of the harmless error standard to Robinson’s preserved\\ndefective indictment claim—a claim of structural error—was improper.”\\n\\n Robinson contends that Williams “establishes that the indictment error\\nat issue in Robinson is structural because it falls under Weaver’s rubric of an\\nerror whose effects are ‘simply too hard to measure’” (quoting Weaver,\\n\\n\\n\\n 19 The Weaver Court noted that structural error typically occurs in three instances.\\nFirst, “an error has been deemed structural in some instances if the right at issue is not\\ndesigned to protect the defendant from erroneous conviction but instead protects some other\\ninterest.” Weaver, 137 S. Ct. at 1908. Second, “an error has been deemed structural if the\\neffects of the error are simply too hard to measure.” Id. And third, “an error has been deemed\\nstructural if the error always results in fundamental unfairness.” Id.\\n 14\\n\\f Case: 18-70022 Document: 00514865791 Page: 15 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\n137 S. Ct. at 1908). 20 Ultimately, Robinson avers that “these opinions demon-\\nstrate that the earlier denial of Robinson’s motion to amend is clearly erron-\\neous; and the courts’ continued denial of Robinson’s right to litigate the impact\\nof the structural error inherent in his defective-indictment claim would work\\na manifest injustice, especially since this is a death-penalty case.”\\n\\n In response, the government asserts that “Robinson’s Rule 60(b) motion\\nis a second or successive petition because it attacks the district court’s merit-\\nbased ruling on his defective-indictment claim.” The government notes—as\\ndid the district court as part of Robinson’s initial habeas proceedings—that\\n“Robinson had ‘previously claimed, both at his trial on the merits before [the\\ndistrict court] and on direct appeal before . . . the Fifth Circuit, that the govern-\\nment’s failure to submit the death penalty aggravating factors to the grand\\njury violated the Indictment Clause of the Fifth Amendment.’” Consequently,\\nbecause we ruled otherwise on direct appeal, Robinson, 367 F.3d at 286–89,\\nthe government maintains that Robinson “lost his defective-indictment claim\\non the merits in a legal decision that was binding on the district court.” 21\\n\\n Importantly, the government highlights that Robinson did not appeal\\nthe denial of his motion to amend but instead raises the issue now, several\\nyears later, in a Rule 60(b) motion. Nonetheless, the government posits that\\n“[b]ecause Robinson’s Rule 60(b) motion attacks the district court’s merits-\\nbased resolution of his proposed [defective-indictment] claim, it is a second or\\n\\n\\n 20 Robinson claims that McCoy v. Louisiana, 138 S. Ct. 1500, 1509 (2018), “undermines\\n[our] treatment of his [defective-indictment] claim as if it were unpreserved (and therefore\\nsubject to harmless error analysis).”\\n 21 See also United States v. Kalish, 780 F.2d 506, 508 (5th Cir. 1986) (emphasizing\\nthat we do not consider, on collateral review, issues that were previously raised and decided\\non direct appeal); United States v. Jones, 614 F.2d 80, 82 (5th Cir. 1980) (noting that we are\\n“not required on [§] 2255 motions to reconsider claims of error raised and disposed of on direct\\nappeal”).\\n 15\\n\\f Case: 18-70022 Document: 00514865791 Page: 16 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\nsuccessive [§] 2255 motion.”\\n\\n At bottom, Robinson challenges not “some defect in the integrity of the\\nhabeas proceedings,” Gonzalez, 545 U.S. at 532, but rather our previous resolu-\\ntion, on the merits, of his defective-indictment claim, Robinson, 367 F.3d\\nat 286–89. Attempting to disguise this claim, which was definitively resolved\\non direct appeal nearly fifteen years ago, 22 Robinson submits that the district\\ncourt’s refusal to allow, on collateral review, an amendment to his habeas peti-\\ntion to include defective-indictment claim was a procedural defect in the integ-\\nrity of the habeas proceedings.\\n\\n The court’s refusal, however, was nothing of the sort. Looking to binding\\ncircuit precedent, including Kadish and Jones, the district court concluded that\\nthe claim was frivolous because its merits had already been determined on dir-\\nect appeal. Consequently, the court properly denied amendment in the merits-\\nbased decision.\\n\\n In its transfer order, the district court noted that “Robinson’s argument\\nis based solely on a purported change in substantive law regarding the defini-\\ntion of structural error which, he asserts, would alter the outcome of his appel-\\nlate claim.” 23 AEDPA forecloses such a claim here because it potentially cir-\\n\\n\\n\\n 22 Notably, Robinson does not assert that the intervening Supreme Court caselaw,\\nincluding Weaver and Williams, announced “a new rule of constitutional law, made retroac-\\ntive to cases on collateral review by the Supreme Court, that was previously unavailable.”\\n28 U.S.C. § 2255(h)(2). Consequently, because of the strict requirements for second or succes-\\nsive habeas petitions, Robinson attempts to bring this claim before the district court using a\\nRule 60(b)(6) procedural vehicle. In any event, however, Weaver and Williams were only\\nchanges in decisional law and “did not create an extraordinary circumstance and thus [can-\\nnot] create[] a basis for [Robinson] to re-open his proceedings as he now wishes to do.”\\nEdwards, 865 F.3d at 208. Thus, even if Robinson’s second-or-successive claim were some-\\nhow construed as properly before us in a Rule 60(b)(6) motion, it would still fail.\\n 23The court also noted that “[t]his is the type of end-run around the successive petition\\nrules that Gonzalez prohibits.”\\n 16\\n\\f Case: 18-70022 Document: 00514865791 Page: 17 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\ncumvents § 2255’s successive-petition requirements. 28 U.S.C. § 2255(h)(2);\\nsee also id. § 2244. The district court did not err in determining that the motion\\nwas, in actuality, a second or successive habeas petition.\\n\\n III.\\n Because we conclude that Robinson’s Rule 60(b) motion is a second or\\nsuccessive § 2255 motion, we also address his motion for leave to file a succes-\\nsive petition concerning his impartial-jury claim.\\n\\n A.\\n “Before a second or successive [habeas] application . . . is filed in the dis-\\ntrict court, the applicant shall move in the appropriate court of appeals for an\\norder authorizing the district court to consider the application.” 28 U.S.C.\\n§ 2244(b)(3)(A). Relevant here, we may authorize such a finding “only if the\\nmovant makes a prima facie showing that his claims rely upon ‘a new rule of\\nconstitutional law, made retroactive to cases on collateral review by the\\nSupreme Court, that was previously unavailable.’” In re Jackson, 776 F.3d\\n292, 293 (5th Cir. 2015) (per curiam) (quoting 28 U.S.C. § 2255(h)(2)); see also\\n28 U.S.C. § 2244(b)(3)(C).\\n\\n “A ‘prima facie showing’ is ‘simply a sufficient showing of possible merit\\nto warrant a fuller exploration by the district court.’” In re Simpson,\\n555 F. App’x 369, 371 (5th Cir. 2014) (per curiam) (quoting Reyes–Requena v.\\nUnited States, 243 F.3d 893, 899 (5th Cir. 2001)). That standard is satisfied\\nwhere the movant “put[s] forth minimally sufficient evidence to make a prima\\nfacie case” such that “there is sufficient, albeit slight, merit in the [petitioner’s]\\nmotion to warrant further exploration by the district court.” In re Hearn, 418\\nF.3d 444, 447–48 (5th Cir. 2005).\\n\\n\\n\\n 17\\n\\f Case: 18-70022 Document: 00514865791 Page: 18 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\n B.\\n Robinson “seeks leave to file a successive § 2255 motion on the ground\\nthat . . . [Pena-Rodriguez] . . . announced a new rule of constitutional law made\\nretroactively applicable on collateral review.” Simpson, 555 F. App’x at 370–\\n71. In Pena-Rodriguez, 137 S. Ct. at 861, the Court examined “whether there\\nis an exception to the no-impeachment rule when, after the jury is discharged,\\na juror comes forward with compelling evidence that another juror made clear\\nand explicit statements indicating that racial animus was a significant moti-\\nvating factor in his or her vote to convict.” It held,\\n [W]here a juror makes a clear statement that indicates he or she\\n relied on racial stereotypes or animus to convict a criminal defen-\\n dant, the Sixth Amendment requires that the no-impeachment\\n rule give way in order to permit the trial court to consider the evi-\\n dence of the juror’s statement and any resulting denial of the jury\\n trial guarantee.\\nId. at 869.\\n The Pena-Rodriguez Court cautioned that “[n]ot every offhand comment\\nindicating racial bias or hostility will justify setting aside the no-impeachment\\nbar to allow further judicial inquiry.” Id. Consequently, “[f]or the inquiry to\\nproceed, there must be a showing that one or more jurors made statements\\nexhibiting overt racial bias that cast serious doubt on the fairness and impar-\\ntiality of the jury’s deliberations and resulting verdict.” Id. Such a statement\\nmust “tend to show that racial animus was a significant motivating factor in\\nthe juror’s vote to convict.” Id. Ultimately, “[w]hether that threshold showing\\nhas been satisfied is a matter committed to the substantial discretion of the\\ntrial court in light of all the circumstances, including the content and timing of\\nthe alleged statements and the reliability of the proffered evidence.” Id.\\n\\n C.\\n The Supreme Court has not expressly stated whether Pena-Rodriguez\\n 18\\n\\f Case: 18-70022 Document: 00514865791 Page: 19 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\nannounced “a new rule of constitutional law, made retroactive to cases on col-\\nlateral review . . . that was previously unavailable.” 28 U.S.C. § 2255(h)(2).\\nNonetheless, Robinson avers that Tharpe v. Sellers, 138 S. Ct. 545, 545–47\\n(2018) (per curiam), “indicate[s] that Pena-Rodriguez is indeed retroactively\\napplicable.”\\n\\n In response, the government notes that the per curiam opinion in Tharpe\\n“failed to mention Pena-Rodriguez at all.” The government also highlights lan-\\nguage in a dissenting opinion filed by three Justices in Tharpe, 138 S. Ct. at\\n547–53 (Thomas, J., dissenting). “[N]o reasonable jurist could argue that\\nPena–Rodriguez applies retroactively on collateral review.” Id. at 551. Pena-\\nRodriguez “established a new rule: The opinion states that it is answering a\\nquestion ‘left open’ by this Court’s earlier precedents.” Id. (quoting Pena-\\nRodriguez, 137 S. Ct. at 867). Further, “[a] new rule does not apply retroac-\\ntively unless it is substantive or a ‘watershed rul[e] of criminal procedure.’” Id.\\n(quoting Teague v. Lane, 489 U.S. 288, 311 (1989) (plurality opinion)). Conse-\\nquently, “[s]ince Pena-Rodriguez permits a trial court ‘to consider [certain]\\nevidence,’ 137 S. Ct. at 869–70, and does not ‘alte[r] the range of conduct or the\\nclass of persons that the law punishes,’ Schriro v. Summerlin, 542 U.S. 348,\\n353 (2004), it cannot be a substantive rule.” Id.\\n\\n Although Robinson’s contention that Pena-Rodriguez (in conjunction\\nwith Tharpe) announced a new substantive rule that applies retroactively to\\ncases on collateral review is exceedingly doubtful, we need not reach that issue\\nhere. Even if the rule announced in Pena-Rodriguez did apply retroactively to\\ncases on collateral review, Robinson fails to make the requisite prima facie\\nshowing of possible merit necessary, under 28 U.S.C. §§ 2244(b)(3)(C) and\\n2255(h)(2), to warrant the certification of his second or successive habeas\\nmotion. Over the past seventeen years, Robinson has proffered absolutely no\\n 19\\n\\f Case: 18-70022 Document: 00514865791 Page: 20 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\nevidence of juror misconduct or bias. 24 Accordingly, we decline, as did the\\ndistrict court, Robinson’s invitation to join his “improper fishing expedition in\\nsupport of a hypothetical claim.” Because Robinson fails to “put forth mini-\\nmally sufficient evidence to make a prima facie case” and there is not “suffici-\\nent . . . merit in [his] motion to warrant further exploration by the district\\ncourt,” we deny the motion for authorization to file a second or successive\\n§ 2255 petition. See Hearn, 418 F.3d at 447–48.\\n\\n In sum, the district court correctly construed Robinson’s Rule 60(b)(6)\\nmotion as a second-or-successive petition for habeas relief. Because Robinson\\nfails to meet the requisite standard for certification of a second or successive\\n§ 2255 petition, we DENY the motion for authorization and DISMISS the\\nappeal for want of jurisdiction.\\n\\n\\n\\n\\n 24 Here, and unlike in Pena–Rodriguez, 137 S. Ct. at 869, there is no evidence of “a\\njuror mak[ing] a clear statement that indicates he or she relied on racial stereotypes or\\nanimus to convict.” Robinson seemingly concedes as much when he claims that he “should\\nbe permitted to conduct an investigation . . . to determine what role, if any, racial bias played\\nin his convictions and sentences” (emphasis added).\\n 20\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4375447/\", \"author_raw\": \"JERRY E. SMITH, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"HIGGINBOTHAM"},"judge2":{"kind":"string","value":"SMITH"},"judge3":{"kind":"string","value":"ENGELHARDT"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4598194/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: In RE: Julius Omar ROBINSON, Movant. United States of America, Plaintiff-Appellee, v. Julius Omar Robinson, Also Known as Face, Also Known as Scar, Also Known as Scarface, Defendant-Appellant.\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-08\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 18-70022 Document: 00514865791 Page: 1 Date Filed: 03/08/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\n United States Court of Appeals\n Fifth Circuit\n\n FILED\n March 8, 2019\n No. 18-10732\n Lyle W. Cayce\n Clerk\nIN RE: JULIUS OMAR ROBINSON,\n\n Movant.\n\n * * * * *\n\n\n No. 18-70022\n\n\nUNITED STATES OF AMERICA,\n\n Plaintiff–Appellee,\n\nversus\n\nJULIUS OMAR ROBINSON, Also Known as Face,\nAlso Known as Scar, Also Known as Scarface,\n\n Defendant–Appellant.\n\n\n\n Appeals from the United States District Court\n for the Northern District of Texas\n\n\n\n\nBefore HIGGINBOTHAM, SMITH, and ENGELHARDT, Circuit Judges.\nJERRY E. SMITH, Circuit Judge:\n\n Julius Robinson was sentenced to death for his role in multiple murders.\n\f Case: 18-70022 Document: 00514865791 Page: 2 Date Filed: 03/08/2019\n\n\n\n No. 18-10732\n No. 18-70022\nAfter we affirmed his conviction on direct appeal, Robinson filed a federal\nhabeas corpus petition asserting six grounds for relief. The district court\ndenied the petition. Nearly ten years later, Robinson filed a Federal Rule of\nCivil Procedure 60(b)(6) motion for relief from judgment. The district court\ndetermined that Robinson’s motion was “in actuality a second or successive\npetition for habeas relief” and transferred it to this court.\n\n Robinson maintains that the district court erred by construing his Rule\n60(b)(6) motion as a second or successive habeas petition. Finding no error,\nand that Robinson fails to meet the standard for a second or successive petition,\nwe deny his motion for authorization and dismiss for want of jurisdiction.\n\n I.\n In 1998, Robinson murdered Johnny Shelton, “a man he mistakenly\nbelieved responsible for an armed hijacking that cost him $30,000.” United\nStates v. Robinson, 367 F.3d 278, 282 (5th Cir.), cert. denied, 543 U.S. 1005\n(2004). Five months later, Robinson killed Juan Reyes in retaliation for “a\nfraudulent drug transaction in which [Robinson] paid $17,000 for a block of\nwood covered in sheetrock.” Id. Robinson was also involved “in a broad con-\nspiracy that led to the murder of Rudolfo Resendez at the hands of Britt and\nHendrick Tunstall.” Id. at 283.\n\n In 2002, a jury convicted Robinson on sixteen counts, including, inter\nalia, 1 one count of murder while engaging in a continuing criminal enterprise,\n\n\n 1 The jury also convicted Robinson on one count of conspiracy to distribute more than\n100 kilograms of marihuana, in violation of 21 U.S.C. §§ 846 and 841(b)(1)(B) (Count 1); one\ncount of conspiracy to distribute more than five kilograms of cocaine, in violation of 21 U.S.C.\n§§ 846 and 841(b)(1)(A) (Count 2); three counts of possession of a firearm in furtherance of a\ndrug trafficking crime, in violation of § 924(c)(1)(A)(i), (C)(i) (Counts 4, 8, and 17); three\ncounts of carrying or using a firearm during a drug trafficking crime, in violation of\n§ 924(c)(1)(A)(ii) (Counts 5, 9, and 13); and three counts of carrying or using and discharging\na firearm during a drug trafficking crime, in violation of § 924(c)(1)(C)(iii) (Counts 6, 10,\n 2\n\f Case: 18-70022 Document: 00514865791 Page: 3 Date Filed: 03/08/2019\n\n\n\n No. 18-10732\n No. 18-70022\nin violation of 21 U.S.C. § 848(e) (2012) (Count 3); three counts of murder in\nthe course of carrying or using a firearm during a drug trafficking crime, in\nviolation of 18 U.S.C. § 924(j) (Counts 7, 11, and 15); and one count of murder\nwhile engaged in possession of more than five kilograms of cocaine with intent\nto distribute, in violation of 21 U.S.C. §§ 841(a)(1), (b)(1)(A), and 848(e)\n(Count 12). The district court sentenced Robinson to death on Counts 3, 7,\nand 11. The court imposed a life sentence on Counts 12 and 15, to be served\nconcurrently, and 300 months on Count 17, to run consecutively to the sen-\ntences on Counts 12 and 15. 2 We affirmed Robinson’s conviction and sentence\non direct appeal. Robinson, 367 F.3d at 293.\n\n In 2005, Robinson initiated federal habeas proceedings via a motion to\nvacate conviction and sentence and for a new trial under 28 U.S.C. § 2255 and\nRule 33 of the Federal Rules of Criminal Procedure. Robinson raised six\ngrounds: (1) ineffective assistance of counsel (“IAC”) during the penalty phase,\n(2) an equal protection (Batson) claim related to the prosecuting attorney’s\nalleged use of preemptory challenges in a racially motived manner, (3) a claim\nthat the Federal Death Penalty Act, as applied in Texas, violates the Equal\nProtection Clause, (4) a claim of IAC on appeal, (5) a due process claim related\nto the prosecuting attorney’s alleged pursuit of fundamentally inconsistent\ntheories at seriatim capital trials, and (6) a due process claim related to the\nprosecutor’s alleged use of false and misleading testimony during the penalty\nphase. Robinson sought to amend his motion by adding a seventh ground for\n\n\nand 14).\n 2 The court did not impose a sentence on Counts 1 and 2 because these counts are\nlesser included offenses of Count 3. Similarly, it declined to impose a sentence on Counts 4,\n5, and 6 because each is a lesser included offense of Count 7. Moreover, the court did not\nimpose a sentence on Counts 8, 9, and 10 because those three counts are lesser included\noffenses of Count 11. Lastly, it declined to impose a sentence on Counts 13 and 14 because\nthey are lesser included offenses of Count 15.\n 3\n\f Case: 18-70022 Document: 00514865791 Page: 4 Date Filed: 03/08/2019\n\n\n\n No. 18-10732\n No. 18-70022\nrelief—a defective-indictment claim based on the prosecuting attorney’s failure\nto include aggravating factors for the capital charge. The district court granted\nin part Robinson’s motion to amend, allowing him to “add documentary\nevidence and corresponding argument relating back to his original petition.”\nThe court denied Robinson’s request to add the defective-indictment claim,\nfinding that we had already addressed the issue on direct appeal. 3\n\n In 2008, the district court denied Robinson’s motion to vacate his con-\nviction and sentence under 28 U.S.C. § 2255, finding that each of his claims\nwas without merit. The court also denied Robinson’s motions for a new trial\nand an evidentiary hearing. With respect to Robinson’s request that the court\nhold an evidentiary hearing on his habeas grounds for relief, the court noted\nthat “the record before [it], including the exhibits submitted by Robinson with\nhis motion, do[es] not create any contested fact issues that must be resolved in\norder to decide Robinson’s claims.” 4 Moreover, the court decided Robinson’s\nhabeas claims “either by assuming that everything Robinson allege[d] [was]\ntrue or based on legal, not factual, bases.” Consequently, “because the record\nbefore [the district] [c]ourt show[ed] conclusively that Robinson [was] not\nentitled to relief, his request for an evidentiary hearing [was] denied.”\n\n Robinson filed a Federal Rule of Civil Procedure 59(e) motion for recon-\n\n\n\n 3 See United States v. Kalish, 780 F.2d 506, 508 (5th Cir. 1986) (“It is settled in this\nCircuit that issues raised and disposed of in a previous appeal from an original judgment of\nconviction are not considered in § 2255 [m]otions.”). On direct appeal, we held that “the\nfailure to charge [the death penalty aggravating] factors in an indictment did not contribute\nto Robinson’s conviction or death sentence.” Robinson, 367 F.3d at 289. The district court\nalso determined that the Supreme Court cases cited by Robinson—United States v. Gonzalez–\nLopez, 548 U.S. 140 (2006), and United States v. Resendiz–Ponce, 549 U.S. 102 (2007)—were\ninapposite, and, in any event, because these cases considered procedural errors, they were\nnot retroactively applicable to cases on collateral review.\n Section 2255 “does not automatically require a hearing to dispose of every motion\n 4\n\nmade under its statutory authority.” Coco v. United States, 569 F.2d 367, 369 (5th Cir. 1978).\n 4\n\f Case: 18-70022 Document: 00514865791 Page: 5 Date Filed: 03/08/2019\n\n\n\n No. 18-10732\n No. 18-70022\nsideration of the order denying the motion to vacate sentencing without an\nevidentiary hearing. The district court denied that motion 5 and declined to\nissue a certificate of appealability (“COA”). We affirmed, and the Supreme\nCourt denied Robinson’s petition for writ of certiorari.\n\n In February 2018, Robinson filed a Rule 60(b)(6) motion for relief from\njudgment. He asserted that “the lack of due process in his post-conviction pro-\nceedings constituted an extraordinary circumstance that justified re-opening\nthe judgment in his case pursuant to Rule 60(b).” Relying on Supreme Court\nprecedent established after the district court denied his § 2255 motion, Robin-\nson contended that the district court (1) “wrongly denied his ability to appeal”\nbecause that court (and the Fifth Circuit) “applied an erroneously high stan-\ndard for obtaining a [COA],” (2) “erroneously barred [him] from conducting a\nreasonable investigation,” and (3) erroneously denied his “right to amend his\n[§] 2255 motion to include his [defective-indictment] claim.”\n\n The district court determined that the motion was, “in actuality[,] a sec-\nond or successive petition for habeas relief” and transferred it to this court. On\nappeal, Robinson asserts that the district court improperly construed his\nRule 60(b)(6) motion as a second or successive § 2255 motion. In the event,\nhowever, that we find the district court did not err, Robinson asks that we\n\n\n\n 5 The court emphasized that “[b]ona fide contested issues of fact raised in a motion to\nvacate brought under § 2255 must be resolved on the basis of an evidentiary hearing. . . . But\n§ 2255 does not require a hearing if the motion, files, and record of the case conclusively\ndemonstrate that no relief is appropriate.” The court also stressed that “the record before\nthis Court, including the exhibits submitted by Robinson with his motions, do[es] not create\nany contested fact issues with regard to Robinson’s insufficiency-of-counsel claims that must\nbe resolved in order to decide his case.” Instead, the court noted, “many of Robinson’s claims\nare based on the record from the trial.” Moreover, “with regard to the claims for which Robin-\nson has submitted additional evidence, the Court . . . decided these claims based on uncon-\ntested allegations of fact and, where facts are contested, by assuming that what Robinson\nalleges is true, or based on legal, not factual, bases.”\n 5\n\f Case: 18-70022 Document: 00514865791 Page: 6 Date Filed: 03/08/2019\n\n\n\n No. 18-10732\n No. 18-70022\ncertify a second or successive § 2255 motion so that he may raise his impartial-\njury claim in the district court.\n\n II.\n “We review a district court’s determination as to whether a Rule 60(b)\nmotion constitutes a second-or-successive habeas petition de novo.” In re\nEdwards, 865 F.3d 197, 202–03 (5th Cir.), cert. denied, 137 S. Ct. 909 (2017).\n\n A.\n Federal habeas review for a prisoner in federal custody is governed by\n 28 U.S.C. § 2255, as amended by the Antiterrorism and Effective Death Pen-\n alty Act of 1996 (“AEDPA”). “AEDPA limits the circumstances under which a\n [federal] prisoner may file a successive application for federal habeas review.”\n Edwards, 865 F.3d at 203. Under § 2255(h),\n [a] second or successive motion must be certified as provided in\n section 2244 by a panel of the appropriate court of appeals to\n contain—\n (1) newly discovered evidence that, if proven and viewed in\n light of the evidence as a whole, would be sufficient to establish\n by clear and convincing evidence that no reasonable fact-finder\n would have found the movant guilty of the offense; or\n (2) a new rule of constitutional law, made retroactive to cases\n on collateral review by the Supreme Court, that was previ-\n ously unavailable.\n28 U.S.C §2255(h). Section 2244(a) provides,\n No circuit or district judge shall be required to entertain an\n application for a writ of habeas corpus to inquire into the deten-\n tion of a person pursuant to a judgment of a court of the United\n States if it appears that the legality of such detention has been\n determined by a judge or court of the United States on a prior\n application for a writ of habeas corpus, except as provided in sec-\n tion 2255.\nA petition is successive when it ‘raises a claim . . . that was or could have been\n 6\n\f Case: 18-70022 Document: 00514865791 Page: 7 Date Filed: 03/08/2019\n\n\n\n No. 18-10732\n No. 18-70022\nraised in an earlier petition . . . .’” Edwards, 865 F.3d at 203 (quoting Harde-\nmon v. Quarterman, 516 F.3d 272, 275 (5th Cir. 2008)).\n\n Federal Rule of Civil Procedure 60(b)(6) authorizes a court to “relieve a\nparty or its legal representative from a final judgment, order, or proceeding for\n. . . any other reason that justifies relief.” To prevail on a Rule 60(b)(6) motion\nin a federal habeas proceeding, a movant must establish that (1) the motion\nwas “made within a reasonable time” 6 and (2) “‘extraordinary circumstances’\n[exist to] justify[] the reopening of a final judgment.” Gonzalez v. Crosby,\n545 U.S. 524, 535 (2005) (quoting Ackermann v. United States, 340 U.S.\n193, 199 (1950)). 7 Extraordinary circumstances “will rarely occur in the\nhabeas context.” Id.\n\n “Because of the comparative leniency of Rule 60(b) [as compared to\nAEDPA], petitioners sometimes attempt to file what are in fact second-or-\nsuccessive habeas petitions under the guise of Rule 60(b) motions.” Edwards,\n865 F.3d at 203. “[T]o bring a proper Rule 60(b) claim, a movant must show ‘a\nnon-merits-based defect in the district court’s earlier decision on the federal\nhabeas petition.’” Id. at 204 (quoting Balentine v. Thaler, 626 F.3d 842, 847\n(5th Cir. 2010) (emphasis added). Thus, we have cautioned that\n it is extraordinarily difficult to bring a claim of procedural defect\n rather than a successive habeas claim, because ‘[p]rocedural defects\n are narrowly construed. They include fraud on the habeas court, as\n well as erroneous previous rulings which precluded a merits\n\n\n Rule 60(c) states, “A motion under Rule 60(b) must be made within a reasonable\n 6\n\ntime—and for reasons [in (b)](1), (2), and (3) no more than a year after the entry of the\njudgment or order or the date of the proceeding.”\n 7Although Gonzalez addressed the application of a Rule 60(b) motion only in the\ncontext of a § 2254 habeas proceeding, we have joined “[n]early every circuit [in applying]\nthe Gonzalez rationale to federal prisoners seeking habeas relief under § 2255.” Williams\nv. Thaler, 602 F.3d 291, 302 & n.4 (5th Cir. 2010) (collecting cases); see also United States\nv. Roberts, 360 F. App’x 584, 585 (5th Cir. 2010).\n 7\n\f Case: 18-70022 Document: 00514865791 Page: 8 Date Filed: 03/08/2019\n\n\n\n No. 18-10732\n No. 18-70022\n determination—for example, a denial for such reasons as failure to\n exhaust, procedural default, or statute-of limitations bar. They\n generally do not include an attack based on the movant’s own con-\n duct, or his habeas counsel’s omissions, which do not go to the integ-\n rity of the proceedings, but in effect ask for a second chance to have\n the merits determined favorably.’\nId. at 205 (quoting In re Coleman, 768 F.3d 367, 371 (5th Cir. 2014)).\n\n Accordingly, “[a] federal court examining a Rule 60(b) motion should\ndetermine whether it either: (1) presents a new habeas claim (an ‘asserted\nfederal basis for relief from a . . . judgment of conviction’), or (2) ‘attacks the\nfederal court’s previous resolution of a claim on the merits.’” Id. at 203 (quoting\nGonzales, 545 U.S. at 530, 532). 8 A “Rule 60(b) motion [that] does either . . .\nshould be treated as a second-or-successive habeas petition and subjected to\nAEDPA’s limitation on such petitions.” Id. at 204. But a petitioner who “merely\nasserts that a previous ruling which precluded a merits determination was in\nerror—for example, a denial for such reasons as failure to exhaust, procedural\ndefault, or statute-of-limitations bar,” is not asserting one of the aforemen-\ntioned grounds. Id. 9\n\n B.\n Robinson contends that the district court erred when it construed his\nclaim concerning the denial of a COA as a second or successive habeas petition.\nAfter the district court denied relief on each of the six grounds he raised in his\n\n\n\n 8 A federal court makes a merits determination when it concludes that “there exist or\ndo not exist grounds entitling a petitioner to habeas corpus relief . . . .” Gonzalez, 545 U.S.\nat 532 n.4. So, “[w]hen a movant asserts one of those grounds (or asserts that a previous\nruling regarding one of those grounds was in error) he is making a habeas corpus claim.” Id.\n 9 If a Rule 60(b) “motion challenges ‘not the substance of the federal court’s resolution\nof a claim on the merits, but some defect in the integrity of the federal habeas proceedings,’\nthen a Rule 60(b) motion is proper.” Coleman, 768 F.3d at 371 (quoting Gonzalez, 545 U.S.\nat 532).\n 8\n\f Case: 18-70022 Document: 00514865791 Page: 9 Date Filed: 03/08/2019\n\n\n\n No. 18-10732\n No. 18-70022\ninitial § 2255 motion, Robinson moved for a COA on his penalty-phase IAC\nclaim. The court denied the application. Robinson then sought a COA from\nthis court, but we also declined. The Supreme Court denied Robinson’s petition\nfor writ of certiorari. Robinson v. United States, 565 U.S. 827 (2011).\n\n Robinson cites Buck v. Davis, 137 S. Ct. 759, 774 (2017), in which the\nCourt reaffirmed that “[a] ‘court of appeals should limit its examination [at the\nCOA stage] to a threshold inquiry into the underlying merit of [the] claims,’\nand ask ‘only if the District Court’s decision was debatable.’” Id. (quoting\nMiller-El v. Cockrell, 537 U.S. 322, 327, 348 (2003)). Robinson maintains that\nboth the district court and this circuit erred when each declined to issue a COA\nto him because both courts “effectively required him to prove he would succeed\non appeal before granting the right to appeal.” Robinson asserts that both\ncourts should have merely determined whether “it was at least debatable that\nhe was deprived of the effective assistance of counsel at the penalty phase of\nhis trial.”\n\n Robinson avers that the district court wrongly decided that “[t]he denial\nof a COA did not preclude a merits determination,” because “merits review by\nan appellate court is . . . its own independent proceeding that the appellant has\na right to access.” Because “appellate merits review is a separate entity, . . .\nan erroneous procedural ruling that precludes appellate merits review is\nentitled to reconsideration under Rule 60(b).”\n\n The government maintains that Robinson’s denial-of-COA claim “is not\na proper basis for a Rule 60(b)(6) motion because it does not seek to reopen a\nruling that precluded a merits determination of his [IAC] claim.” Rather, Rob-\ninson “seeks to reopen a ruling (the denial of a COA) that followed the district\ncourt’s merits-based ruling on [his] [IAC] claim.” The government emphasizes\nthat “a Rule 60(b) motion that seeks to revisit the federal court’s denial on the\n 9\n\f Case: 18-70022 Document: 00514865791 Page: 10 Date Filed: 03/08/2019\n\n\n\n No. 18-10732\n No. 18-70022\nmerits of a claim for relief should be treated as a successive habeas petition”\n(quoting Gonzalez, 545 U.S. at 534). 10 Asserting that Robinson’s Rule 60(b)\nmotion attempts to do just that, the government contends that the district\ncourt correctly determined the motion was a second or successive § 2255\nmotion. 11\n\n The district court correctly concluded that Robinson “badly misreads\nGonzalez.” The denial of a COA on Robinson’s IAC claim did not preclude a\nmerits determination. Instead, the court reviewed and denied the claim on its\nmerits as part of Robinson’s initial § 2255 motion. Because his Rule 60(b)\nmotion attacks the district court’s merits-based resolution of his IAC claim, it\nis best viewed as a second or successive petition. 12 The court did not err in\nfinding that it had “no jurisdiction to consider [the motion].”\n\n C.\n Robinson asserts that the district court erred in determining that his\nrequest to interview the jurors was a second or successive § 2255 motion. He\ncontends that “he was unreasonably barred from interviewing the trial jurors,\nthus depriving him of a reasonable post-conviction investigation.” Citing In re\nSessions, 672 F.2d 564, 566 (5th Cir. 1982), Robinson maintains that “it is well-\nsettled law that a denial of discovery is not akin to a denial on the merits of a\n\n\n 10The government highlights that “Robinson points to no authority holding that a\nruling that precludes appellate review is the same as a ruling that precludes a merits\ndetermination.”\n 11 The government also avers that Buck does not “stand for the proposition that the\ndenial of a COA is a proper basis for a Rule 60(b) motion” because “the denial of the COA was\nnot the basis for Buck’s Rule 60(b) motion.” Instead, the inverse was true: “Buck sought a\nCOA to appeal the denial of his Rule 60(b) motion . . . .”\n 12See Gonzalez 545 U.S. at 532; Edwards, 865 F.3d at 203. The district court deter-\nmined that Robinson’s motion was, “‘if not in substance a habeas corpus application, at least\nsimilar enough that failing to subject it to the same requirements would be inconsistent with\nthe statute’ governing successive petitions” (quoting Gonzalez, 545 U.S. at 531).\n 10\n\f Case: 18-70022 Document: 00514865791 Page: 11 Date Filed: 03/08/2019\n\n\n\n No. 18-10732\n No. 18-70022\nclaim for relief.” 13 He cites Mitchell v. Rees, 261 F. App’x 825, 828–29 (6th Cir.\n2008), for the proposition that “if [reopening] a case for the purposes of holding\nan evidentiary hearing is a valid use of Rule 60(b), then [reopening] to conduct\njuror interviews must certainly be valid.”\n\n Robinson avers that the district court was not correct that his “request\n. . . seeks to develop evidence in support of an impartial-jury claim under the\nSixth Amendment.” He contends that as part of his first habeas petition, he\nsought to interview jurors and that “the reason that [an impartial-jury] claim\nwas not raised to the [d]istrict [c]ourt in Robinson’s amended [§] 2255 motion\nwas because the court prevented Robinson from conducting discovery.” Con-\nsequently, “Robinson’s inability to raise an [impartial-jury] claim is a prime\nexample of a defect in the integrity of the habeas proceedings.”\n\n In response, the government maintains that Robinson’s Rule 60(b)\nmotion seeks to “reopen the [§] 2255 proceedings so that he [can] interview\njurors ‘to determine what role, if any, racial bias played in his convictions and\nsentences.’” The government notes, correctly, that “[a] habeas petitioner,\nunlike the usual civil litigant in federal court, is not entitled to discovery as a\nmatter of ordinary course.” Bracy v. Gramley, 520 U.S. 899, 904 (1997).\nRather, as we stated in United States v. Fields, 761 F.3d 443, 478 (5th Cir.\n2014), “[a] petitioner demonstrates ‘good cause’ [for discovery] under Rule 6(a)\n[of the Rules Governing § 2255 Proceedings] ‘where specific allegations before\nthe court show reason to believe that a petitioner may, if the facts are fully\ndeveloped, be able to demonstrate that he is . . . entitled to relief” (quoting\nBracy, 520 U.S. at 908–09). 14\n\n\n See also Wellons v. Hall, 558 U.S. 220, 223 (2010) (per curiam). Robinson concedes,\n 13\n\nhowever, that “Sessions does not concern Rule 60(b) motions.”\n 14 Rule 6(a) of the Rules Governing § 2255 Proceedings “does not authorize fishing\n 11\n\f Case: 18-70022 Document: 00514865791 Page: 12 Date Filed: 03/08/2019\n\n\n\n No. 18-10732\n No. 18-70022\n The government emphasizes that Robinson’s previous request to inter-\nview jurors, filed as part of his first § 2255 petition, did not concern a potential\nimpartial-jury claim, but instead related to his Batson and IAC claims. The\ngovernment also highlights that when he made his initial interview request,\nRobinson expressly acknowledged that he did not have a viable impartial-jury\nclaim. Accordingly, although Robinson “certainly had the ability to bring the\nclaim in his original [§] 2255 motion or to seek leave to amend his motion to\nadd the claim,” he “chose not to because . . . there was no evidence to support\nsuch a claim.” 15\n\n The best view is that Robinson is attempting to advance a new habeas\nclaim related to jury impartiality (in light of Pena-Rodriguez v. Colorado, 137\nS. Ct. 855 (2017)) under the guise of a Rule 60(b)(6) motion. His “motion seeks\nto re-open the proceedings for the purpose of adding new claims” and, as such,\nis “the definition of a successive claim.” Edwards, 865 F.3d at 204.\n\n The denial of Robinson’s discovery request during his initial habeas\nproceedings—a request that was then related to his Batson and IAC claims—\ndid not prevent a merits determination on those issues. Moreover, Robinson\nwas not prevented from litigating his impartial-jury claim because of “a denial\nfor such reasons as failure to exhaust, procedural default, or statute-of-\nlimitations bar.” See Gonzalez, 545 U.S. at 532 n.4. Instead, Robinson chose\n\n\n\nexpeditions.” Ward v. Whitley, 21 F.3d 1355, 1367 (5th Cir. 1994).\n 15 The government also posits that “[g]iven that federal courts disfavor post-verdict\ninterviewing of jurors except where there is some showing of an illegal or prejudicial intrusion\ninto the jury process, United States v. Riley, 544 F.2d 237, 242 (5th Cir. 1976), and that by\nRobinson’s own admission, he could not make that requisite showing, Robinson’s alleged\n‘inability’ to bring an impartial-jury claim hardly represents a ‘defect’ in the proceedings.” In\nRiley, we strongly cautioned that “Courts simply [must] not denigrate jury trials by after-\nwards ransacking the jurors in search of some ground, not previously supported by evidence,\nfor a new trial.” Id.\n 12\n\f Case: 18-70022 Document: 00514865791 Page: 13 Date Filed: 03/08/2019\n\n\n\n No. 18-10732\n No. 18-70022\nnot to bring this claim in his initial § 2255 motion because, as he acknowledged,\nsuch a claim was frivolous. 16\n\n To the extent that Robinson now attempts to bring such a claim, the gov-\nernment rightly posits that “[b]ecause the merits of Robinson’s discovery\nrequest to interview jurors [are] wrapped up with, and dependent on, his abil-\nity to bring a new claim for relief from the judgment of his conviction,” his\nrequest is “a paradigmatic habeas claim.” Rodwell v. Pepe, 324 F.3d 66, 72 (1st\nCir. 2003). 17 Accordingly, this claim is best viewed as a second or successive\n§ 2255 motion.\n\n Ultimately, “[u]sing Rule 60(b) to present new claims for relief from a\n. . . court’s judgment of conviction—even claims couched in the language of a\ntrue Rule 60(b) motion—circumvents AEDPA’s requirement that a new claim\nbe dismissed unless it relies on either a new rule of constitutional law or newly\ndiscovered facts.” Gonzalez, 545 U.S. at 531. The district court did not err in\ndetermining that Robinson’s claim is a second or successive habeas petition. 18\n\n\n\n 16The district court echoed this conclusion when it stated that “Robinson conceded he\nhad no evidence of a Sixth Amendment violation.”\n 17 The cases cited by Robinson are inapposite. The decision in Ruiz v. Quarterman,\n504 F.3d 523, 526 (5th Cir. 2007), stands for the unremarkable proposition that a denial of\n“relief based on procedural default and failure to exhaust” may properly be reviewed using a\nRule 60(b) motion. Likewise, Balentine v. Thaler, 626 F.3d 842, 844–49 (5th Cir. 2010),\nmerely affirmed that the denial of relief on the ground that a claim is “unexhausted and\nprocedurally barred” may be challenged using the Rule 60(b) vehicle. Neither situation is\npresented here. Importantly, the Ruiz court emphasized that “a Rule 60(b) motion is a\nhabeas claim when it presents a new claim for relief, or when it presents new evidence in\nsupport of a claim already litigated, or when it asserts a change in the substantive law gov-\nerning the claim, or when it attacks the federal court’s previous resolution of a claim on the\nmerits.” Ruiz, 504 F.3d at 526.\n 18 Even if we were to find that Robinson’s impartial-jury claim did not constitute a\nsecond or successive habeas petition, we would undoubtedly conclude that he fails to show\nthat, as a result of the denial of his discovery request, “‘extraordinary circumstances’ [exist\nto] justify[] the reopening of [the] final judgment” under Rule 60(b)(6). Gonzalez, 545 U.S. at\n535 (quoting Ackermann, 340 U.S. at 199); see also Mitchell, 261 F. App’x at 828–31.\n 13\n\f Case: 18-70022 Document: 00514865791 Page: 14 Date Filed: 03/08/2019\n\n\n\n No. 18-10732\n No. 18-70022\n D.\n Robinson raises a third ground for relief in his Rule 60(b) motion. He\nmaintains that the district court erred in finding that his challenge to the\ndenial of his motion to amend his original § 2255 petition to include a defective-\nindictment claim was substantive in nature. Citing a number of intervening\nSupreme Court precedents, including Weaver v. Massachusetts, 137 S. Ct. 1899\n(2017), and Williams v. Pennsylvania, 136 S. Ct. 1899 (2016), Robinson essen-\ntially asserts that our determination in Robinson, 367 F.3d at 289—that the\ngovernment’s “failure to charge [the death penalty aggravating] factors in an\nindictment did not contribute to [his] conviction or death sentence” was harm-\nless error “beyond a reasonable doubt”—was flawed.\n\n Robinson maintains that Weaver, in particular, “casts serious doubt on\n[our] denial of Robinson’s defective indictment claim in two significant ways.”\nFirst, “the Weaver Court’s description of the three general categories of struc-\ntural error[ 19] make clear that this Court’s requirement that [Robinson’s]\ndefective indictment claim affect the ‘fundamental fairness’ of his trial in order\nto be structural was misguided.” Second, “Weaver left no doubt that this\nCourt’s application of the harmless error standard to Robinson’s preserved\ndefective indictment claim—a claim of structural error—was improper.”\n\n Robinson contends that Williams “establishes that the indictment error\nat issue in Robinson is structural because it falls under Weaver’s rubric of an\nerror whose effects are ‘simply too hard to measure’” (quoting Weaver,\n\n\n\n 19 The Weaver Court noted that structural error typically occurs in three instances.\nFirst, “an error has been deemed structural in some instances if the right at issue is not\ndesigned to protect the defendant from erroneous conviction but instead protects some other\ninterest.” Weaver, 137 S. Ct. at 1908. Second, “an error has been deemed structural if the\neffects of the error are simply too hard to measure.” Id. And third, “an error has been deemed\nstructural if the error always results in fundamental unfairness.” Id.\n 14\n\f Case: 18-70022 Document: 00514865791 Page: 15 Date Filed: 03/08/2019\n\n\n\n No. 18-10732\n No. 18-70022\n137 S. Ct. at 1908). 20 Ultimately, Robinson avers that “these opinions demon-\nstrate that the earlier denial of Robinson’s motion to amend is clearly erron-\neous; and the courts’ continued denial of Robinson’s right to litigate the impact\nof the structural error inherent in his defective-indictment claim would work\na manifest injustice, especially since this is a death-penalty case.”\n\n In response, the government asserts that “Robinson’s Rule 60(b) motion\nis a second or successive petition because it attacks the district court’s merit-\nbased ruling on his defective-indictment claim.” The government notes—as\ndid the district court as part of Robinson’s initial habeas proceedings—that\n“Robinson had ‘previously claimed, both at his trial on the merits before [the\ndistrict court] and on direct appeal before . . . the Fifth Circuit, that the govern-\nment’s failure to submit the death penalty aggravating factors to the grand\njury violated the Indictment Clause of the Fifth Amendment.’” Consequently,\nbecause we ruled otherwise on direct appeal, Robinson, 367 F.3d at 286–89,\nthe government maintains that Robinson “lost his defective-indictment claim\non the merits in a legal decision that was binding on the district court.” 21\n\n Importantly, the government highlights that Robinson did not appeal\nthe denial of his motion to amend but instead raises the issue now, several\nyears later, in a Rule 60(b) motion. Nonetheless, the government posits that\n“[b]ecause Robinson’s Rule 60(b) motion attacks the district court’s merits-\nbased resolution of his proposed [defective-indictment] claim, it is a second or\n\n\n 20 Robinson claims that McCoy v. Louisiana, 138 S. Ct. 1500, 1509 (2018), “undermines\n[our] treatment of his [defective-indictment] claim as if it were unpreserved (and therefore\nsubject to harmless error analysis).”\n 21 See also United States v. Kalish, 780 F.2d 506, 508 (5th Cir. 1986) (emphasizing\nthat we do not consider, on collateral review, issues that were previously raised and decided\non direct appeal); United States v. Jones, 614 F.2d 80, 82 (5th Cir. 1980) (noting that we are\n“not required on [§] 2255 motions to reconsider claims of error raised and disposed of on direct\nappeal”).\n 15\n\f Case: 18-70022 Document: 00514865791 Page: 16 Date Filed: 03/08/2019\n\n\n\n No. 18-10732\n No. 18-70022\nsuccessive [§] 2255 motion.”\n\n At bottom, Robinson challenges not “some defect in the integrity of the\nhabeas proceedings,” Gonzalez, 545 U.S. at 532, but rather our previous resolu-\ntion, on the merits, of his defective-indictment claim, Robinson, 367 F.3d\nat 286–89. Attempting to disguise this claim, which was definitively resolved\non direct appeal nearly fifteen years ago, 22 Robinson submits that the district\ncourt’s refusal to allow, on collateral review, an amendment to his habeas peti-\ntion to include defective-indictment claim was a procedural defect in the integ-\nrity of the habeas proceedings.\n\n The court’s refusal, however, was nothing of the sort. Looking to binding\ncircuit precedent, including Kadish and Jones, the district court concluded that\nthe claim was frivolous because its merits had already been determined on dir-\nect appeal. Consequently, the court properly denied amendment in the merits-\nbased decision.\n\n In its transfer order, the district court noted that “Robinson’s argument\nis based solely on a purported change in substantive law regarding the defini-\ntion of structural error which, he asserts, would alter the outcome of his appel-\nlate claim.” 23 AEDPA forecloses such a claim here because it potentially cir-\n\n\n\n 22 Notably, Robinson does not assert that the intervening Supreme Court caselaw,\nincluding Weaver and Williams, announced “a new rule of constitutional law, made retroac-\ntive to cases on collateral review by the Supreme Court, that was previously unavailable.”\n28 U.S.C. § 2255(h)(2). Consequently, because of the strict requirements for second or succes-\nsive habeas petitions, Robinson attempts to bring this claim before the district court using a\nRule 60(b)(6) procedural vehicle. In any event, however, Weaver and Williams were only\nchanges in decisional law and “did not create an extraordinary circumstance and thus [can-\nnot] create[] a basis for [Robinson] to re-open his proceedings as he now wishes to do.”\nEdwards, 865 F.3d at 208. Thus, even if Robinson’s second-or-successive claim were some-\nhow construed as properly before us in a Rule 60(b)(6) motion, it would still fail.\n 23The court also noted that “[t]his is the type of end-run around the successive petition\nrules that Gonzalez prohibits.”\n 16\n\f Case: 18-70022 Document: 00514865791 Page: 17 Date Filed: 03/08/2019\n\n\n\n No. 18-10732\n No. 18-70022\ncumvents § 2255’s successive-petition requirements. 28 U.S.C. § 2255(h)(2);\nsee also id. § 2244. The district court did not err in determining that the motion\nwas, in actuality, a second or successive habeas petition.\n\n III.\n Because we conclude that Robinson’s Rule 60(b) motion is a second or\nsuccessive § 2255 motion, we also address his motion for leave to file a succes-\nsive petition concerning his impartial-jury claim.\n\n A.\n “Before a second or successive [habeas] application . . . is filed in the dis-\ntrict court, the applicant shall move in the appropriate court of appeals for an\norder authorizing the district court to consider the application.” 28 U.S.C.\n§ 2244(b)(3)(A). Relevant here, we may authorize such a finding “only if the\nmovant makes a prima facie showing that his claims rely upon ‘a new rule of\nconstitutional law, made retroactive to cases on collateral review by the\nSupreme Court, that was previously unavailable.’” In re Jackson, 776 F.3d\n292, 293 (5th Cir. 2015) (per curiam) (quoting 28 U.S.C. § 2255(h)(2)); see also\n28 U.S.C. § 2244(b)(3)(C).\n\n “A ‘prima facie showing’ is ‘simply a sufficient showing of possible merit\nto warrant a fuller exploration by the district court.’” In re Simpson,\n555 F. App’x 369, 371 (5th Cir. 2014) (per curiam) (quoting Reyes–Requena v.\nUnited States, 243 F.3d 893, 899 (5th Cir. 2001)). That standard is satisfied\nwhere the movant “put[s] forth minimally sufficient evidence to make a prima\nfacie case” such that “there is sufficient, albeit slight, merit in the [petitioner’s]\nmotion to warrant further exploration by the district court.” In re Hearn, 418\nF.3d 444, 447–48 (5th Cir. 2005).\n\n\n\n 17\n\f Case: 18-70022 Document: 00514865791 Page: 18 Date Filed: 03/08/2019\n\n\n\n No. 18-10732\n No. 18-70022\n B.\n Robinson “seeks leave to file a successive § 2255 motion on the ground\nthat . . . [Pena-Rodriguez] . . . announced a new rule of constitutional law made\nretroactively applicable on collateral review.” Simpson, 555 F. App’x at 370–\n71. In Pena-Rodriguez, 137 S. Ct. at 861, the Court examined “whether there\nis an exception to the no-impeachment rule when, after the jury is discharged,\na juror comes forward with compelling evidence that another juror made clear\nand explicit statements indicating that racial animus was a significant moti-\nvating factor in his or her vote to convict.” It held,\n [W]here a juror makes a clear statement that indicates he or she\n relied on racial stereotypes or animus to convict a criminal defen-\n dant, the Sixth Amendment requires that the no-impeachment\n rule give way in order to permit the trial court to consider the evi-\n dence of the juror’s statement and any resulting denial of the jury\n trial guarantee.\nId. at 869.\n The Pena-Rodriguez Court cautioned that “[n]ot every offhand comment\nindicating racial bias or hostility will justify setting aside the no-impeachment\nbar to allow further judicial inquiry.” Id. Consequently, “[f]or the inquiry to\nproceed, there must be a showing that one or more jurors made statements\nexhibiting overt racial bias that cast serious doubt on the fairness and impar-\ntiality of the jury’s deliberations and resulting verdict.” Id. Such a statement\nmust “tend to show that racial animus was a significant motivating factor in\nthe juror’s vote to convict.” Id. Ultimately, “[w]hether that threshold showing\nhas been satisfied is a matter committed to the substantial discretion of the\ntrial court in light of all the circumstances, including the content and timing of\nthe alleged statements and the reliability of the proffered evidence.” Id.\n\n C.\n The Supreme Court has not expressly stated whether Pena-Rodriguez\n 18\n\f Case: 18-70022 Document: 00514865791 Page: 19 Date Filed: 03/08/2019\n\n\n\n No. 18-10732\n No. 18-70022\nannounced “a new rule of constitutional law, made retroactive to cases on col-\nlateral review . . . that was previously unavailable.” 28 U.S.C. § 2255(h)(2).\nNonetheless, Robinson avers that Tharpe v. Sellers, 138 S. Ct. 545, 545–47\n(2018) (per curiam), “indicate[s] that Pena-Rodriguez is indeed retroactively\napplicable.”\n\n In response, the government notes that the per curiam opinion in Tharpe\n“failed to mention Pena-Rodriguez at all.” The government also highlights lan-\nguage in a dissenting opinion filed by three Justices in Tharpe, 138 S. Ct. at\n547–53 (Thomas, J., dissenting). “[N]o reasonable jurist could argue that\nPena–Rodriguez applies retroactively on collateral review.” Id. at 551. Pena-\nRodriguez “established a new rule: The opinion states that it is answering a\nquestion ‘left open’ by this Court’s earlier precedents.” Id. (quoting Pena-\nRodriguez, 137 S. Ct. at 867). Further, “[a] new rule does not apply retroac-\ntively unless it is substantive or a ‘watershed rul[e] of criminal procedure.’” Id.\n(quoting Teague v. Lane, 489 U.S. 288, 311 (1989) (plurality opinion)). Conse-\nquently, “[s]ince Pena-Rodriguez permits a trial court ‘to consider [certain]\nevidence,’ 137 S. Ct. at 869–70, and does not ‘alte[r] the range of conduct or the\nclass of persons that the law punishes,’ Schriro v. Summerlin, 542 U.S. 348,\n353 (2004), it cannot be a substantive rule.” Id.\n\n Although Robinson’s contention that Pena-Rodriguez (in conjunction\nwith Tharpe) announced a new substantive rule that applies retroactively to\ncases on collateral review is exceedingly doubtful, we need not reach that issue\nhere. Even if the rule announced in Pena-Rodriguez did apply retroactively to\ncases on collateral review, Robinson fails to make the requisite prima facie\nshowing of possible merit necessary, under 28 U.S.C. §§ 2244(b)(3)(C) and\n2255(h)(2), to warrant the certification of his second or successive habeas\nmotion. Over the past seventeen years, Robinson has proffered absolutely no\n 19\n\f Case: 18-70022 Document: 00514865791 Page: 20 Date Filed: 03/08/2019\n\n\n\n No. 18-10732\n No. 18-70022\nevidence of juror misconduct or bias. 24 Accordingly, we decline, as did the\ndistrict court, Robinson’s invitation to join his “improper fishing expedition in\nsupport of a hypothetical claim.” Because Robinson fails to “put forth mini-\nmally sufficient evidence to make a prima facie case” and there is not “suffici-\nent . . . merit in [his] motion to warrant further exploration by the district\ncourt,” we deny the motion for authorization to file a second or successive\n§ 2255 petition. See Hearn, 418 F.3d at 447–48.\n\n In sum, the district court correctly construed Robinson’s Rule 60(b)(6)\nmotion as a second-or-successive petition for habeas relief. Because Robinson\nfails to meet the requisite standard for certification of a second or successive\n§ 2255 petition, we DENY the motion for authorization and DISMISS the\nappeal for want of jurisdiction.\n\n\n\n\n 24 Here, and unlike in Pena–Rodriguez, 137 S. Ct. at 869, there is no evidence of “a\njuror mak[ing] a clear statement that indicates he or she relied on racial stereotypes or\nanimus to convict.” Robinson seemingly concedes as much when he claims that he “should\nbe permitted to conduct an investigation . . . to determine what role, if any, racial bias played\nin his convictions and sentences” (emphasis added).\n 20\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: In RE: Julius Omar ROBINSON, Movant. United States of America, Plaintiff-Appellee, v. Julius Omar Robinson, Also Known as Face, Also Known as Scar, Also Known as Scarface, Defendant-Appellant.\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-08\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 18-70022 Document: 00514865791 Page: 1 Date Filed: 03/08/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n March 8, 2019\\n No. 18-10732\\n Lyle W. Cayce\\n Clerk\\nIN RE: JULIUS OMAR ROBINSON,\\n\\n Movant.\\n\\n * * * * *\\n\\n\\n No. 18-70022\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff–Appellee,\\n\\nversus\\n\\nJULIUS OMAR ROBINSON, Also Known as Face,\\nAlso Known as Scar, Also Known as Scarface,\\n\\n Defendant–Appellant.\\n\\n\\n\\n Appeals from the United States District Court\\n for the Northern District of Texas\\n\\n\\n\\n\\nBefore HIGGINBOTHAM, SMITH, and ENGELHARDT, Circuit Judges.\\nJERRY E. SMITH, Circuit Judge:\\n\\n Julius Robinson was sentenced to death for his role in multiple murders.\\n\\f Case: 18-70022 Document: 00514865791 Page: 2 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\nAfter we affirmed his conviction on direct appeal, Robinson filed a federal\\nhabeas corpus petition asserting six grounds for relief. The district court\\ndenied the petition. Nearly ten years later, Robinson filed a Federal Rule of\\nCivil Procedure 60(b)(6) motion for relief from judgment. The district court\\ndetermined that Robinson’s motion was “in actuality a second or successive\\npetition for habeas relief” and transferred it to this court.\\n\\n Robinson maintains that the district court erred by construing his Rule\\n60(b)(6) motion as a second or successive habeas petition. Finding no error,\\nand that Robinson fails to meet the standard for a second or successive petition,\\nwe deny his motion for authorization and dismiss for want of jurisdiction.\\n\\n I.\\n In 1998, Robinson murdered Johnny Shelton, “a man he mistakenly\\nbelieved responsible for an armed hijacking that cost him $30,000.” United\\nStates v. Robinson, 367 F.3d 278, 282 (5th Cir.), cert. denied, 543 U.S. 1005\\n(2004). Five months later, Robinson killed Juan Reyes in retaliation for “a\\nfraudulent drug transaction in which [Robinson] paid $17,000 for a block of\\nwood covered in sheetrock.” Id. Robinson was also involved “in a broad con-\\nspiracy that led to the murder of Rudolfo Resendez at the hands of Britt and\\nHendrick Tunstall.” Id. at 283.\\n\\n In 2002, a jury convicted Robinson on sixteen counts, including, inter\\nalia, 1 one count of murder while engaging in a continuing criminal enterprise,\\n\\n\\n 1 The jury also convicted Robinson on one count of conspiracy to distribute more than\\n100 kilograms of marihuana, in violation of 21 U.S.C. §§ 846 and 841(b)(1)(B) (Count 1); one\\ncount of conspiracy to distribute more than five kilograms of cocaine, in violation of 21 U.S.C.\\n§§ 846 and 841(b)(1)(A) (Count 2); three counts of possession of a firearm in furtherance of a\\ndrug trafficking crime, in violation of § 924(c)(1)(A)(i), (C)(i) (Counts 4, 8, and 17); three\\ncounts of carrying or using a firearm during a drug trafficking crime, in violation of\\n§ 924(c)(1)(A)(ii) (Counts 5, 9, and 13); and three counts of carrying or using and discharging\\na firearm during a drug trafficking crime, in violation of § 924(c)(1)(C)(iii) (Counts 6, 10,\\n 2\\n\\f Case: 18-70022 Document: 00514865791 Page: 3 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\nin violation of 21 U.S.C. § 848(e) (2012) (Count 3); three counts of murder in\\nthe course of carrying or using a firearm during a drug trafficking crime, in\\nviolation of 18 U.S.C. § 924(j) (Counts 7, 11, and 15); and one count of murder\\nwhile engaged in possession of more than five kilograms of cocaine with intent\\nto distribute, in violation of 21 U.S.C. §§ 841(a)(1), (b)(1)(A), and 848(e)\\n(Count 12). The district court sentenced Robinson to death on Counts 3, 7,\\nand 11. The court imposed a life sentence on Counts 12 and 15, to be served\\nconcurrently, and 300 months on Count 17, to run consecutively to the sen-\\ntences on Counts 12 and 15. 2 We affirmed Robinson’s conviction and sentence\\non direct appeal. Robinson, 367 F.3d at 293.\\n\\n In 2005, Robinson initiated federal habeas proceedings via a motion to\\nvacate conviction and sentence and for a new trial under 28 U.S.C. § 2255 and\\nRule 33 of the Federal Rules of Criminal Procedure. Robinson raised six\\ngrounds: (1) ineffective assistance of counsel (“IAC”) during the penalty phase,\\n(2) an equal protection (Batson) claim related to the prosecuting attorney’s\\nalleged use of preemptory challenges in a racially motived manner, (3) a claim\\nthat the Federal Death Penalty Act, as applied in Texas, violates the Equal\\nProtection Clause, (4) a claim of IAC on appeal, (5) a due process claim related\\nto the prosecuting attorney’s alleged pursuit of fundamentally inconsistent\\ntheories at seriatim capital trials, and (6) a due process claim related to the\\nprosecutor’s alleged use of false and misleading testimony during the penalty\\nphase. Robinson sought to amend his motion by adding a seventh ground for\\n\\n\\nand 14).\\n 2 The court did not impose a sentence on Counts 1 and 2 because these counts are\\nlesser included offenses of Count 3. Similarly, it declined to impose a sentence on Counts 4,\\n5, and 6 because each is a lesser included offense of Count 7. Moreover, the court did not\\nimpose a sentence on Counts 8, 9, and 10 because those three counts are lesser included\\noffenses of Count 11. Lastly, it declined to impose a sentence on Counts 13 and 14 because\\nthey are lesser included offenses of Count 15.\\n 3\\n\\f Case: 18-70022 Document: 00514865791 Page: 4 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\nrelief—a defective-indictment claim based on the prosecuting attorney’s failure\\nto include aggravating factors for the capital charge. The district court granted\\nin part Robinson’s motion to amend, allowing him to “add documentary\\nevidence and corresponding argument relating back to his original petition.”\\nThe court denied Robinson’s request to add the defective-indictment claim,\\nfinding that we had already addressed the issue on direct appeal. 3\\n\\n In 2008, the district court denied Robinson’s motion to vacate his con-\\nviction and sentence under 28 U.S.C. § 2255, finding that each of his claims\\nwas without merit. The court also denied Robinson’s motions for a new trial\\nand an evidentiary hearing. With respect to Robinson’s request that the court\\nhold an evidentiary hearing on his habeas grounds for relief, the court noted\\nthat “the record before [it], including the exhibits submitted by Robinson with\\nhis motion, do[es] not create any contested fact issues that must be resolved in\\norder to decide Robinson’s claims.” 4 Moreover, the court decided Robinson’s\\nhabeas claims “either by assuming that everything Robinson allege[d] [was]\\ntrue or based on legal, not factual, bases.” Consequently, “because the record\\nbefore [the district] [c]ourt show[ed] conclusively that Robinson [was] not\\nentitled to relief, his request for an evidentiary hearing [was] denied.”\\n\\n Robinson filed a Federal Rule of Civil Procedure 59(e) motion for recon-\\n\\n\\n\\n 3 See United States v. Kalish, 780 F.2d 506, 508 (5th Cir. 1986) (“It is settled in this\\nCircuit that issues raised and disposed of in a previous appeal from an original judgment of\\nconviction are not considered in § 2255 [m]otions.”). On direct appeal, we held that “the\\nfailure to charge [the death penalty aggravating] factors in an indictment did not contribute\\nto Robinson’s conviction or death sentence.” Robinson, 367 F.3d at 289. The district court\\nalso determined that the Supreme Court cases cited by Robinson—United States v. Gonzalez–\\nLopez, 548 U.S. 140 (2006), and United States v. Resendiz–Ponce, 549 U.S. 102 (2007)—were\\ninapposite, and, in any event, because these cases considered procedural errors, they were\\nnot retroactively applicable to cases on collateral review.\\n Section 2255 “does not automatically require a hearing to dispose of every motion\\n 4\\n\\nmade under its statutory authority.” Coco v. United States, 569 F.2d 367, 369 (5th Cir. 1978).\\n 4\\n\\f Case: 18-70022 Document: 00514865791 Page: 5 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\nsideration of the order denying the motion to vacate sentencing without an\\nevidentiary hearing. The district court denied that motion 5 and declined to\\nissue a certificate of appealability (“COA”). We affirmed, and the Supreme\\nCourt denied Robinson’s petition for writ of certiorari.\\n\\n In February 2018, Robinson filed a Rule 60(b)(6) motion for relief from\\njudgment. He asserted that “the lack of due process in his post-conviction pro-\\nceedings constituted an extraordinary circumstance that justified re-opening\\nthe judgment in his case pursuant to Rule 60(b).” Relying on Supreme Court\\nprecedent established after the district court denied his § 2255 motion, Robin-\\nson contended that the district court (1) “wrongly denied his ability to appeal”\\nbecause that court (and the Fifth Circuit) “applied an erroneously high stan-\\ndard for obtaining a [COA],” (2) “erroneously barred [him] from conducting a\\nreasonable investigation,” and (3) erroneously denied his “right to amend his\\n[§] 2255 motion to include his [defective-indictment] claim.”\\n\\n The district court determined that the motion was, “in actuality[,] a sec-\\nond or successive petition for habeas relief” and transferred it to this court. On\\nappeal, Robinson asserts that the district court improperly construed his\\nRule 60(b)(6) motion as a second or successive § 2255 motion. In the event,\\nhowever, that we find the district court did not err, Robinson asks that we\\n\\n\\n\\n 5 The court emphasized that “[b]ona fide contested issues of fact raised in a motion to\\nvacate brought under § 2255 must be resolved on the basis of an evidentiary hearing. . . . But\\n§ 2255 does not require a hearing if the motion, files, and record of the case conclusively\\ndemonstrate that no relief is appropriate.” The court also stressed that “the record before\\nthis Court, including the exhibits submitted by Robinson with his motions, do[es] not create\\nany contested fact issues with regard to Robinson’s insufficiency-of-counsel claims that must\\nbe resolved in order to decide his case.” Instead, the court noted, “many of Robinson’s claims\\nare based on the record from the trial.” Moreover, “with regard to the claims for which Robin-\\nson has submitted additional evidence, the Court . . . decided these claims based on uncon-\\ntested allegations of fact and, where facts are contested, by assuming that what Robinson\\nalleges is true, or based on legal, not factual, bases.”\\n 5\\n\\f Case: 18-70022 Document: 00514865791 Page: 6 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\ncertify a second or successive § 2255 motion so that he may raise his impartial-\\njury claim in the district court.\\n\\n II.\\n “We review a district court’s determination as to whether a Rule 60(b)\\nmotion constitutes a second-or-successive habeas petition de novo.” In re\\nEdwards, 865 F.3d 197, 202–03 (5th Cir.), cert. denied, 137 S. Ct. 909 (2017).\\n\\n A.\\n Federal habeas review for a prisoner in federal custody is governed by\\n 28 U.S.C. § 2255, as amended by the Antiterrorism and Effective Death Pen-\\n alty Act of 1996 (“AEDPA”). “AEDPA limits the circumstances under which a\\n [federal] prisoner may file a successive application for federal habeas review.”\\n Edwards, 865 F.3d at 203. Under § 2255(h),\\n [a] second or successive motion must be certified as provided in\\n section 2244 by a panel of the appropriate court of appeals to\\n contain—\\n (1) newly discovered evidence that, if proven and viewed in\\n light of the evidence as a whole, would be sufficient to establish\\n by clear and convincing evidence that no reasonable fact-finder\\n would have found the movant guilty of the offense; or\\n (2) a new rule of constitutional law, made retroactive to cases\\n on collateral review by the Supreme Court, that was previ-\\n ously unavailable.\\n28 U.S.C §2255(h). Section 2244(a) provides,\\n No circuit or district judge shall be required to entertain an\\n application for a writ of habeas corpus to inquire into the deten-\\n tion of a person pursuant to a judgment of a court of the United\\n States if it appears that the legality of such detention has been\\n determined by a judge or court of the United States on a prior\\n application for a writ of habeas corpus, except as provided in sec-\\n tion 2255.\\nA petition is successive when it ‘raises a claim . . . that was or could have been\\n 6\\n\\f Case: 18-70022 Document: 00514865791 Page: 7 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\nraised in an earlier petition . . . .’” Edwards, 865 F.3d at 203 (quoting Harde-\\nmon v. Quarterman, 516 F.3d 272, 275 (5th Cir. 2008)).\\n\\n Federal Rule of Civil Procedure 60(b)(6) authorizes a court to “relieve a\\nparty or its legal representative from a final judgment, order, or proceeding for\\n. . . any other reason that justifies relief.” To prevail on a Rule 60(b)(6) motion\\nin a federal habeas proceeding, a movant must establish that (1) the motion\\nwas “made within a reasonable time” 6 and (2) “‘extraordinary circumstances’\\n[exist to] justify[] the reopening of a final judgment.” Gonzalez v. Crosby,\\n545 U.S. 524, 535 (2005) (quoting Ackermann v. United States, 340 U.S.\\n193, 199 (1950)). 7 Extraordinary circumstances “will rarely occur in the\\nhabeas context.” Id.\\n\\n “Because of the comparative leniency of Rule 60(b) [as compared to\\nAEDPA], petitioners sometimes attempt to file what are in fact second-or-\\nsuccessive habeas petitions under the guise of Rule 60(b) motions.” Edwards,\\n865 F.3d at 203. “[T]o bring a proper Rule 60(b) claim, a movant must show ‘a\\nnon-merits-based defect in the district court’s earlier decision on the federal\\nhabeas petition.’” Id. at 204 (quoting Balentine v. Thaler, 626 F.3d 842, 847\\n(5th Cir. 2010) (emphasis added). Thus, we have cautioned that\\n it is extraordinarily difficult to bring a claim of procedural defect\\n rather than a successive habeas claim, because ‘[p]rocedural defects\\n are narrowly construed. They include fraud on the habeas court, as\\n well as erroneous previous rulings which precluded a merits\\n\\n\\n Rule 60(c) states, “A motion under Rule 60(b) must be made within a reasonable\\n 6\\n\\ntime—and for reasons [in (b)](1), (2), and (3) no more than a year after the entry of the\\njudgment or order or the date of the proceeding.”\\n 7Although Gonzalez addressed the application of a Rule 60(b) motion only in the\\ncontext of a § 2254 habeas proceeding, we have joined “[n]early every circuit [in applying]\\nthe Gonzalez rationale to federal prisoners seeking habeas relief under § 2255.” Williams\\nv. Thaler, 602 F.3d 291, 302 & n.4 (5th Cir. 2010) (collecting cases); see also United States\\nv. Roberts, 360 F. App’x 584, 585 (5th Cir. 2010).\\n 7\\n\\f Case: 18-70022 Document: 00514865791 Page: 8 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\n determination—for example, a denial for such reasons as failure to\\n exhaust, procedural default, or statute-of limitations bar. They\\n generally do not include an attack based on the movant’s own con-\\n duct, or his habeas counsel’s omissions, which do not go to the integ-\\n rity of the proceedings, but in effect ask for a second chance to have\\n the merits determined favorably.’\\nId. at 205 (quoting In re Coleman, 768 F.3d 367, 371 (5th Cir. 2014)).\\n\\n Accordingly, “[a] federal court examining a Rule 60(b) motion should\\ndetermine whether it either: (1) presents a new habeas claim (an ‘asserted\\nfederal basis for relief from a . . . judgment of conviction’), or (2) ‘attacks the\\nfederal court’s previous resolution of a claim on the merits.’” Id. at 203 (quoting\\nGonzales, 545 U.S. at 530, 532). 8 A “Rule 60(b) motion [that] does either . . .\\nshould be treated as a second-or-successive habeas petition and subjected to\\nAEDPA’s limitation on such petitions.” Id. at 204. But a petitioner who “merely\\nasserts that a previous ruling which precluded a merits determination was in\\nerror—for example, a denial for such reasons as failure to exhaust, procedural\\ndefault, or statute-of-limitations bar,” is not asserting one of the aforemen-\\ntioned grounds. Id. 9\\n\\n B.\\n Robinson contends that the district court erred when it construed his\\nclaim concerning the denial of a COA as a second or successive habeas petition.\\nAfter the district court denied relief on each of the six grounds he raised in his\\n\\n\\n\\n 8 A federal court makes a merits determination when it concludes that “there exist or\\ndo not exist grounds entitling a petitioner to habeas corpus relief . . . .” Gonzalez, 545 U.S.\\nat 532 n.4. So, “[w]hen a movant asserts one of those grounds (or asserts that a previous\\nruling regarding one of those grounds was in error) he is making a habeas corpus claim.” Id.\\n 9 If a Rule 60(b) “motion challenges ‘not the substance of the federal court’s resolution\\nof a claim on the merits, but some defect in the integrity of the federal habeas proceedings,’\\nthen a Rule 60(b) motion is proper.” Coleman, 768 F.3d at 371 (quoting Gonzalez, 545 U.S.\\nat 532).\\n 8\\n\\f Case: 18-70022 Document: 00514865791 Page: 9 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\ninitial § 2255 motion, Robinson moved for a COA on his penalty-phase IAC\\nclaim. The court denied the application. Robinson then sought a COA from\\nthis court, but we also declined. The Supreme Court denied Robinson’s petition\\nfor writ of certiorari. Robinson v. United States, 565 U.S. 827 (2011).\\n\\n Robinson cites Buck v. Davis, 137 S. Ct. 759, 774 (2017), in which the\\nCourt reaffirmed that “[a] ‘court of appeals should limit its examination [at the\\nCOA stage] to a threshold inquiry into the underlying merit of [the] claims,’\\nand ask ‘only if the District Court’s decision was debatable.’” Id. (quoting\\nMiller-El v. Cockrell, 537 U.S. 322, 327, 348 (2003)). Robinson maintains that\\nboth the district court and this circuit erred when each declined to issue a COA\\nto him because both courts “effectively required him to prove he would succeed\\non appeal before granting the right to appeal.” Robinson asserts that both\\ncourts should have merely determined whether “it was at least debatable that\\nhe was deprived of the effective assistance of counsel at the penalty phase of\\nhis trial.”\\n\\n Robinson avers that the district court wrongly decided that “[t]he denial\\nof a COA did not preclude a merits determination,” because “merits review by\\nan appellate court is . . . its own independent proceeding that the appellant has\\na right to access.” Because “appellate merits review is a separate entity, . . .\\nan erroneous procedural ruling that precludes appellate merits review is\\nentitled to reconsideration under Rule 60(b).”\\n\\n The government maintains that Robinson’s denial-of-COA claim “is not\\na proper basis for a Rule 60(b)(6) motion because it does not seek to reopen a\\nruling that precluded a merits determination of his [IAC] claim.” Rather, Rob-\\ninson “seeks to reopen a ruling (the denial of a COA) that followed the district\\ncourt’s merits-based ruling on [his] [IAC] claim.” The government emphasizes\\nthat “a Rule 60(b) motion that seeks to revisit the federal court’s denial on the\\n 9\\n\\f Case: 18-70022 Document: 00514865791 Page: 10 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\nmerits of a claim for relief should be treated as a successive habeas petition”\\n(quoting Gonzalez, 545 U.S. at 534). 10 Asserting that Robinson’s Rule 60(b)\\nmotion attempts to do just that, the government contends that the district\\ncourt correctly determined the motion was a second or successive § 2255\\nmotion. 11\\n\\n The district court correctly concluded that Robinson “badly misreads\\nGonzalez.” The denial of a COA on Robinson’s IAC claim did not preclude a\\nmerits determination. Instead, the court reviewed and denied the claim on its\\nmerits as part of Robinson’s initial § 2255 motion. Because his Rule 60(b)\\nmotion attacks the district court’s merits-based resolution of his IAC claim, it\\nis best viewed as a second or successive petition. 12 The court did not err in\\nfinding that it had “no jurisdiction to consider [the motion].”\\n\\n C.\\n Robinson asserts that the district court erred in determining that his\\nrequest to interview the jurors was a second or successive § 2255 motion. He\\ncontends that “he was unreasonably barred from interviewing the trial jurors,\\nthus depriving him of a reasonable post-conviction investigation.” Citing In re\\nSessions, 672 F.2d 564, 566 (5th Cir. 1982), Robinson maintains that “it is well-\\nsettled law that a denial of discovery is not akin to a denial on the merits of a\\n\\n\\n 10The government highlights that “Robinson points to no authority holding that a\\nruling that precludes appellate review is the same as a ruling that precludes a merits\\ndetermination.”\\n 11 The government also avers that Buck does not “stand for the proposition that the\\ndenial of a COA is a proper basis for a Rule 60(b) motion” because “the denial of the COA was\\nnot the basis for Buck’s Rule 60(b) motion.” Instead, the inverse was true: “Buck sought a\\nCOA to appeal the denial of his Rule 60(b) motion . . . .”\\n 12See Gonzalez 545 U.S. at 532; Edwards, 865 F.3d at 203. The district court deter-\\nmined that Robinson’s motion was, “‘if not in substance a habeas corpus application, at least\\nsimilar enough that failing to subject it to the same requirements would be inconsistent with\\nthe statute’ governing successive petitions” (quoting Gonzalez, 545 U.S. at 531).\\n 10\\n\\f Case: 18-70022 Document: 00514865791 Page: 11 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\nclaim for relief.” 13 He cites Mitchell v. Rees, 261 F. App’x 825, 828–29 (6th Cir.\\n2008), for the proposition that “if [reopening] a case for the purposes of holding\\nan evidentiary hearing is a valid use of Rule 60(b), then [reopening] to conduct\\njuror interviews must certainly be valid.”\\n\\n Robinson avers that the district court was not correct that his “request\\n. . . seeks to develop evidence in support of an impartial-jury claim under the\\nSixth Amendment.” He contends that as part of his first habeas petition, he\\nsought to interview jurors and that “the reason that [an impartial-jury] claim\\nwas not raised to the [d]istrict [c]ourt in Robinson’s amended [§] 2255 motion\\nwas because the court prevented Robinson from conducting discovery.” Con-\\nsequently, “Robinson’s inability to raise an [impartial-jury] claim is a prime\\nexample of a defect in the integrity of the habeas proceedings.”\\n\\n In response, the government maintains that Robinson’s Rule 60(b)\\nmotion seeks to “reopen the [§] 2255 proceedings so that he [can] interview\\njurors ‘to determine what role, if any, racial bias played in his convictions and\\nsentences.’” The government notes, correctly, that “[a] habeas petitioner,\\nunlike the usual civil litigant in federal court, is not entitled to discovery as a\\nmatter of ordinary course.” Bracy v. Gramley, 520 U.S. 899, 904 (1997).\\nRather, as we stated in United States v. Fields, 761 F.3d 443, 478 (5th Cir.\\n2014), “[a] petitioner demonstrates ‘good cause’ [for discovery] under Rule 6(a)\\n[of the Rules Governing § 2255 Proceedings] ‘where specific allegations before\\nthe court show reason to believe that a petitioner may, if the facts are fully\\ndeveloped, be able to demonstrate that he is . . . entitled to relief” (quoting\\nBracy, 520 U.S. at 908–09). 14\\n\\n\\n See also Wellons v. Hall, 558 U.S. 220, 223 (2010) (per curiam). Robinson concedes,\\n 13\\n\\nhowever, that “Sessions does not concern Rule 60(b) motions.”\\n 14 Rule 6(a) of the Rules Governing § 2255 Proceedings “does not authorize fishing\\n 11\\n\\f Case: 18-70022 Document: 00514865791 Page: 12 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\n The government emphasizes that Robinson’s previous request to inter-\\nview jurors, filed as part of his first § 2255 petition, did not concern a potential\\nimpartial-jury claim, but instead related to his Batson and IAC claims. The\\ngovernment also highlights that when he made his initial interview request,\\nRobinson expressly acknowledged that he did not have a viable impartial-jury\\nclaim. Accordingly, although Robinson “certainly had the ability to bring the\\nclaim in his original [§] 2255 motion or to seek leave to amend his motion to\\nadd the claim,” he “chose not to because . . . there was no evidence to support\\nsuch a claim.” 15\\n\\n The best view is that Robinson is attempting to advance a new habeas\\nclaim related to jury impartiality (in light of Pena-Rodriguez v. Colorado, 137\\nS. Ct. 855 (2017)) under the guise of a Rule 60(b)(6) motion. His “motion seeks\\nto re-open the proceedings for the purpose of adding new claims” and, as such,\\nis “the definition of a successive claim.” Edwards, 865 F.3d at 204.\\n\\n The denial of Robinson’s discovery request during his initial habeas\\nproceedings—a request that was then related to his Batson and IAC claims—\\ndid not prevent a merits determination on those issues. Moreover, Robinson\\nwas not prevented from litigating his impartial-jury claim because of “a denial\\nfor such reasons as failure to exhaust, procedural default, or statute-of-\\nlimitations bar.” See Gonzalez, 545 U.S. at 532 n.4. Instead, Robinson chose\\n\\n\\n\\nexpeditions.” Ward v. Whitley, 21 F.3d 1355, 1367 (5th Cir. 1994).\\n 15 The government also posits that “[g]iven that federal courts disfavor post-verdict\\ninterviewing of jurors except where there is some showing of an illegal or prejudicial intrusion\\ninto the jury process, United States v. Riley, 544 F.2d 237, 242 (5th Cir. 1976), and that by\\nRobinson’s own admission, he could not make that requisite showing, Robinson’s alleged\\n‘inability’ to bring an impartial-jury claim hardly represents a ‘defect’ in the proceedings.” In\\nRiley, we strongly cautioned that “Courts simply [must] not denigrate jury trials by after-\\nwards ransacking the jurors in search of some ground, not previously supported by evidence,\\nfor a new trial.” Id.\\n 12\\n\\f Case: 18-70022 Document: 00514865791 Page: 13 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\nnot to bring this claim in his initial § 2255 motion because, as he acknowledged,\\nsuch a claim was frivolous. 16\\n\\n To the extent that Robinson now attempts to bring such a claim, the gov-\\nernment rightly posits that “[b]ecause the merits of Robinson’s discovery\\nrequest to interview jurors [are] wrapped up with, and dependent on, his abil-\\nity to bring a new claim for relief from the judgment of his conviction,” his\\nrequest is “a paradigmatic habeas claim.” Rodwell v. Pepe, 324 F.3d 66, 72 (1st\\nCir. 2003). 17 Accordingly, this claim is best viewed as a second or successive\\n§ 2255 motion.\\n\\n Ultimately, “[u]sing Rule 60(b) to present new claims for relief from a\\n. . . court’s judgment of conviction—even claims couched in the language of a\\ntrue Rule 60(b) motion—circumvents AEDPA’s requirement that a new claim\\nbe dismissed unless it relies on either a new rule of constitutional law or newly\\ndiscovered facts.” Gonzalez, 545 U.S. at 531. The district court did not err in\\ndetermining that Robinson’s claim is a second or successive habeas petition. 18\\n\\n\\n\\n 16The district court echoed this conclusion when it stated that “Robinson conceded he\\nhad no evidence of a Sixth Amendment violation.”\\n 17 The cases cited by Robinson are inapposite. The decision in Ruiz v. Quarterman,\\n504 F.3d 523, 526 (5th Cir. 2007), stands for the unremarkable proposition that a denial of\\n“relief based on procedural default and failure to exhaust” may properly be reviewed using a\\nRule 60(b) motion. Likewise, Balentine v. Thaler, 626 F.3d 842, 844–49 (5th Cir. 2010),\\nmerely affirmed that the denial of relief on the ground that a claim is “unexhausted and\\nprocedurally barred” may be challenged using the Rule 60(b) vehicle. Neither situation is\\npresented here. Importantly, the Ruiz court emphasized that “a Rule 60(b) motion is a\\nhabeas claim when it presents a new claim for relief, or when it presents new evidence in\\nsupport of a claim already litigated, or when it asserts a change in the substantive law gov-\\nerning the claim, or when it attacks the federal court’s previous resolution of a claim on the\\nmerits.” Ruiz, 504 F.3d at 526.\\n 18 Even if we were to find that Robinson’s impartial-jury claim did not constitute a\\nsecond or successive habeas petition, we would undoubtedly conclude that he fails to show\\nthat, as a result of the denial of his discovery request, “‘extraordinary circumstances’ [exist\\nto] justify[] the reopening of [the] final judgment” under Rule 60(b)(6). Gonzalez, 545 U.S. at\\n535 (quoting Ackermann, 340 U.S. at 199); see also Mitchell, 261 F. App’x at 828–31.\\n 13\\n\\f Case: 18-70022 Document: 00514865791 Page: 14 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\n D.\\n Robinson raises a third ground for relief in his Rule 60(b) motion. He\\nmaintains that the district court erred in finding that his challenge to the\\ndenial of his motion to amend his original § 2255 petition to include a defective-\\nindictment claim was substantive in nature. Citing a number of intervening\\nSupreme Court precedents, including Weaver v. Massachusetts, 137 S. Ct. 1899\\n(2017), and Williams v. Pennsylvania, 136 S. Ct. 1899 (2016), Robinson essen-\\ntially asserts that our determination in Robinson, 367 F.3d at 289—that the\\ngovernment’s “failure to charge [the death penalty aggravating] factors in an\\nindictment did not contribute to [his] conviction or death sentence” was harm-\\nless error “beyond a reasonable doubt”—was flawed.\\n\\n Robinson maintains that Weaver, in particular, “casts serious doubt on\\n[our] denial of Robinson’s defective indictment claim in two significant ways.”\\nFirst, “the Weaver Court’s description of the three general categories of struc-\\ntural error[ 19] make clear that this Court’s requirement that [Robinson’s]\\ndefective indictment claim affect the ‘fundamental fairness’ of his trial in order\\nto be structural was misguided.” Second, “Weaver left no doubt that this\\nCourt’s application of the harmless error standard to Robinson’s preserved\\ndefective indictment claim—a claim of structural error—was improper.”\\n\\n Robinson contends that Williams “establishes that the indictment error\\nat issue in Robinson is structural because it falls under Weaver’s rubric of an\\nerror whose effects are ‘simply too hard to measure’” (quoting Weaver,\\n\\n\\n\\n 19 The Weaver Court noted that structural error typically occurs in three instances.\\nFirst, “an error has been deemed structural in some instances if the right at issue is not\\ndesigned to protect the defendant from erroneous conviction but instead protects some other\\ninterest.” Weaver, 137 S. Ct. at 1908. Second, “an error has been deemed structural if the\\neffects of the error are simply too hard to measure.” Id. And third, “an error has been deemed\\nstructural if the error always results in fundamental unfairness.” Id.\\n 14\\n\\f Case: 18-70022 Document: 00514865791 Page: 15 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\n137 S. Ct. at 1908). 20 Ultimately, Robinson avers that “these opinions demon-\\nstrate that the earlier denial of Robinson’s motion to amend is clearly erron-\\neous; and the courts’ continued denial of Robinson’s right to litigate the impact\\nof the structural error inherent in his defective-indictment claim would work\\na manifest injustice, especially since this is a death-penalty case.”\\n\\n In response, the government asserts that “Robinson’s Rule 60(b) motion\\nis a second or successive petition because it attacks the district court’s merit-\\nbased ruling on his defective-indictment claim.” The government notes—as\\ndid the district court as part of Robinson’s initial habeas proceedings—that\\n“Robinson had ‘previously claimed, both at his trial on the merits before [the\\ndistrict court] and on direct appeal before . . . the Fifth Circuit, that the govern-\\nment’s failure to submit the death penalty aggravating factors to the grand\\njury violated the Indictment Clause of the Fifth Amendment.’” Consequently,\\nbecause we ruled otherwise on direct appeal, Robinson, 367 F.3d at 286–89,\\nthe government maintains that Robinson “lost his defective-indictment claim\\non the merits in a legal decision that was binding on the district court.” 21\\n\\n Importantly, the government highlights that Robinson did not appeal\\nthe denial of his motion to amend but instead raises the issue now, several\\nyears later, in a Rule 60(b) motion. Nonetheless, the government posits that\\n“[b]ecause Robinson’s Rule 60(b) motion attacks the district court’s merits-\\nbased resolution of his proposed [defective-indictment] claim, it is a second or\\n\\n\\n 20 Robinson claims that McCoy v. Louisiana, 138 S. Ct. 1500, 1509 (2018), “undermines\\n[our] treatment of his [defective-indictment] claim as if it were unpreserved (and therefore\\nsubject to harmless error analysis).”\\n 21 See also United States v. Kalish, 780 F.2d 506, 508 (5th Cir. 1986) (emphasizing\\nthat we do not consider, on collateral review, issues that were previously raised and decided\\non direct appeal); United States v. Jones, 614 F.2d 80, 82 (5th Cir. 1980) (noting that we are\\n“not required on [§] 2255 motions to reconsider claims of error raised and disposed of on direct\\nappeal”).\\n 15\\n\\f Case: 18-70022 Document: 00514865791 Page: 16 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\nsuccessive [§] 2255 motion.”\\n\\n At bottom, Robinson challenges not “some defect in the integrity of the\\nhabeas proceedings,” Gonzalez, 545 U.S. at 532, but rather our previous resolu-\\ntion, on the merits, of his defective-indictment claim, Robinson, 367 F.3d\\nat 286–89. Attempting to disguise this claim, which was definitively resolved\\non direct appeal nearly fifteen years ago, 22 Robinson submits that the district\\ncourt’s refusal to allow, on collateral review, an amendment to his habeas peti-\\ntion to include defective-indictment claim was a procedural defect in the integ-\\nrity of the habeas proceedings.\\n\\n The court’s refusal, however, was nothing of the sort. Looking to binding\\ncircuit precedent, including Kadish and Jones, the district court concluded that\\nthe claim was frivolous because its merits had already been determined on dir-\\nect appeal. Consequently, the court properly denied amendment in the merits-\\nbased decision.\\n\\n In its transfer order, the district court noted that “Robinson’s argument\\nis based solely on a purported change in substantive law regarding the defini-\\ntion of structural error which, he asserts, would alter the outcome of his appel-\\nlate claim.” 23 AEDPA forecloses such a claim here because it potentially cir-\\n\\n\\n\\n 22 Notably, Robinson does not assert that the intervening Supreme Court caselaw,\\nincluding Weaver and Williams, announced “a new rule of constitutional law, made retroac-\\ntive to cases on collateral review by the Supreme Court, that was previously unavailable.”\\n28 U.S.C. § 2255(h)(2). Consequently, because of the strict requirements for second or succes-\\nsive habeas petitions, Robinson attempts to bring this claim before the district court using a\\nRule 60(b)(6) procedural vehicle. In any event, however, Weaver and Williams were only\\nchanges in decisional law and “did not create an extraordinary circumstance and thus [can-\\nnot] create[] a basis for [Robinson] to re-open his proceedings as he now wishes to do.”\\nEdwards, 865 F.3d at 208. Thus, even if Robinson’s second-or-successive claim were some-\\nhow construed as properly before us in a Rule 60(b)(6) motion, it would still fail.\\n 23The court also noted that “[t]his is the type of end-run around the successive petition\\nrules that Gonzalez prohibits.”\\n 16\\n\\f Case: 18-70022 Document: 00514865791 Page: 17 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\ncumvents § 2255’s successive-petition requirements. 28 U.S.C. § 2255(h)(2);\\nsee also id. § 2244. The district court did not err in determining that the motion\\nwas, in actuality, a second or successive habeas petition.\\n\\n III.\\n Because we conclude that Robinson’s Rule 60(b) motion is a second or\\nsuccessive § 2255 motion, we also address his motion for leave to file a succes-\\nsive petition concerning his impartial-jury claim.\\n\\n A.\\n “Before a second or successive [habeas] application . . . is filed in the dis-\\ntrict court, the applicant shall move in the appropriate court of appeals for an\\norder authorizing the district court to consider the application.” 28 U.S.C.\\n§ 2244(b)(3)(A). Relevant here, we may authorize such a finding “only if the\\nmovant makes a prima facie showing that his claims rely upon ‘a new rule of\\nconstitutional law, made retroactive to cases on collateral review by the\\nSupreme Court, that was previously unavailable.’” In re Jackson, 776 F.3d\\n292, 293 (5th Cir. 2015) (per curiam) (quoting 28 U.S.C. § 2255(h)(2)); see also\\n28 U.S.C. § 2244(b)(3)(C).\\n\\n “A ‘prima facie showing’ is ‘simply a sufficient showing of possible merit\\nto warrant a fuller exploration by the district court.’” In re Simpson,\\n555 F. App’x 369, 371 (5th Cir. 2014) (per curiam) (quoting Reyes–Requena v.\\nUnited States, 243 F.3d 893, 899 (5th Cir. 2001)). That standard is satisfied\\nwhere the movant “put[s] forth minimally sufficient evidence to make a prima\\nfacie case” such that “there is sufficient, albeit slight, merit in the [petitioner’s]\\nmotion to warrant further exploration by the district court.” In re Hearn, 418\\nF.3d 444, 447–48 (5th Cir. 2005).\\n\\n\\n\\n 17\\n\\f Case: 18-70022 Document: 00514865791 Page: 18 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\n B.\\n Robinson “seeks leave to file a successive § 2255 motion on the ground\\nthat . . . [Pena-Rodriguez] . . . announced a new rule of constitutional law made\\nretroactively applicable on collateral review.” Simpson, 555 F. App’x at 370–\\n71. In Pena-Rodriguez, 137 S. Ct. at 861, the Court examined “whether there\\nis an exception to the no-impeachment rule when, after the jury is discharged,\\na juror comes forward with compelling evidence that another juror made clear\\nand explicit statements indicating that racial animus was a significant moti-\\nvating factor in his or her vote to convict.” It held,\\n [W]here a juror makes a clear statement that indicates he or she\\n relied on racial stereotypes or animus to convict a criminal defen-\\n dant, the Sixth Amendment requires that the no-impeachment\\n rule give way in order to permit the trial court to consider the evi-\\n dence of the juror’s statement and any resulting denial of the jury\\n trial guarantee.\\nId. at 869.\\n The Pena-Rodriguez Court cautioned that “[n]ot every offhand comment\\nindicating racial bias or hostility will justify setting aside the no-impeachment\\nbar to allow further judicial inquiry.” Id. Consequently, “[f]or the inquiry to\\nproceed, there must be a showing that one or more jurors made statements\\nexhibiting overt racial bias that cast serious doubt on the fairness and impar-\\ntiality of the jury’s deliberations and resulting verdict.” Id. Such a statement\\nmust “tend to show that racial animus was a significant motivating factor in\\nthe juror’s vote to convict.” Id. Ultimately, “[w]hether that threshold showing\\nhas been satisfied is a matter committed to the substantial discretion of the\\ntrial court in light of all the circumstances, including the content and timing of\\nthe alleged statements and the reliability of the proffered evidence.” Id.\\n\\n C.\\n The Supreme Court has not expressly stated whether Pena-Rodriguez\\n 18\\n\\f Case: 18-70022 Document: 00514865791 Page: 19 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\nannounced “a new rule of constitutional law, made retroactive to cases on col-\\nlateral review . . . that was previously unavailable.” 28 U.S.C. § 2255(h)(2).\\nNonetheless, Robinson avers that Tharpe v. Sellers, 138 S. Ct. 545, 545–47\\n(2018) (per curiam), “indicate[s] that Pena-Rodriguez is indeed retroactively\\napplicable.”\\n\\n In response, the government notes that the per curiam opinion in Tharpe\\n“failed to mention Pena-Rodriguez at all.” The government also highlights lan-\\nguage in a dissenting opinion filed by three Justices in Tharpe, 138 S. Ct. at\\n547–53 (Thomas, J., dissenting). “[N]o reasonable jurist could argue that\\nPena–Rodriguez applies retroactively on collateral review.” Id. at 551. Pena-\\nRodriguez “established a new rule: The opinion states that it is answering a\\nquestion ‘left open’ by this Court’s earlier precedents.” Id. (quoting Pena-\\nRodriguez, 137 S. Ct. at 867). Further, “[a] new rule does not apply retroac-\\ntively unless it is substantive or a ‘watershed rul[e] of criminal procedure.’” Id.\\n(quoting Teague v. Lane, 489 U.S. 288, 311 (1989) (plurality opinion)). Conse-\\nquently, “[s]ince Pena-Rodriguez permits a trial court ‘to consider [certain]\\nevidence,’ 137 S. Ct. at 869–70, and does not ‘alte[r] the range of conduct or the\\nclass of persons that the law punishes,’ Schriro v. Summerlin, 542 U.S. 348,\\n353 (2004), it cannot be a substantive rule.” Id.\\n\\n Although Robinson’s contention that Pena-Rodriguez (in conjunction\\nwith Tharpe) announced a new substantive rule that applies retroactively to\\ncases on collateral review is exceedingly doubtful, we need not reach that issue\\nhere. Even if the rule announced in Pena-Rodriguez did apply retroactively to\\ncases on collateral review, Robinson fails to make the requisite prima facie\\nshowing of possible merit necessary, under 28 U.S.C. §§ 2244(b)(3)(C) and\\n2255(h)(2), to warrant the certification of his second or successive habeas\\nmotion. Over the past seventeen years, Robinson has proffered absolutely no\\n 19\\n\\f Case: 18-70022 Document: 00514865791 Page: 20 Date Filed: 03/08/2019\\n\\n\\n\\n No. 18-10732\\n No. 18-70022\\nevidence of juror misconduct or bias. 24 Accordingly, we decline, as did the\\ndistrict court, Robinson’s invitation to join his “improper fishing expedition in\\nsupport of a hypothetical claim.” Because Robinson fails to “put forth mini-\\nmally sufficient evidence to make a prima facie case” and there is not “suffici-\\nent . . . merit in [his] motion to warrant further exploration by the district\\ncourt,” we deny the motion for authorization to file a second or successive\\n§ 2255 petition. See Hearn, 418 F.3d at 447–48.\\n\\n In sum, the district court correctly construed Robinson’s Rule 60(b)(6)\\nmotion as a second-or-successive petition for habeas relief. Because Robinson\\nfails to meet the requisite standard for certification of a second or successive\\n§ 2255 petition, we DENY the motion for authorization and DISMISS the\\nappeal for want of jurisdiction.\\n\\n\\n\\n\\n 24 Here, and unlike in Pena–Rodriguez, 137 S. Ct. at 869, there is no evidence of “a\\njuror mak[ing] a clear statement that indicates he or she relied on racial stereotypes or\\nanimus to convict.” Robinson seemingly concedes as much when he claims that he “should\\nbe permitted to conduct an investigation . . . to determine what role, if any, racial bias played\\nin his convictions and sentences” (emphasis added).\\n 20\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1080,"cells":{"id":{"kind":"number","value":8443910,"string":"8,443,910"},"name":{"kind":"string","value":"Nancy MORROW Alvin Russell Moon, on Behalf of Estate of Austin Russell Moon, on Behalf of C.D., a Minor Christa Donahue, on Behalf of A.D., a Minor v. Jonathan MEACHUM"},"name_abbreviation":{"kind":"string","value":"Morrow v. Meachum"},"decision_date":{"kind":"string","value":"2019-03-08"},"docket_number":{"kind":"string","value":"No. 17-11243"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Costa, Davis, Oldham\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"020lead\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/8415341/\", \"author_raw\": \"\"}]}"},"judge1":{"kind":"string","value":"COSTA"},"judge2":{"kind":"string","value":"DAVIS"},"judge3":{"kind":"string","value":"OLDHAM"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/8443910/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":0,"string":"0"},"020lead_count":{"kind":"number","value":1,"string":"1"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Nancy MORROW Alvin Russell Moon, on Behalf of Estate of Austin Russell Moon, on Behalf of C.D., a Minor Christa Donahue, on Behalf of A.D., a Minor v. Jonathan MEACHUM\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-08\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Nancy MORROW Alvin Russell Moon, on Behalf of Estate of Austin Russell Moon, on Behalf of C.D., a Minor Christa Donahue, on Behalf of A.D., a Minor v. Jonathan MEACHUM\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-08\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1081,"cells":{"id":{"kind":"number","value":4598522,"string":"4,598,522"},"name":{"kind":"string","value":"James A. LATIOLAIS, Plaintiff-Appellee v. HUNTINGTON INGALLS, INCORPORATED, Formerly Known as Northrop Grumman Shipbuilding, Incorporated, Formerly Known as Northrop Grumman Ship Systems, Incorporated, Formerly Known as Avondale Industries, Incorporated, Defendant-Appellant"},"name_abbreviation":{"kind":"string","value":"James Latiolais v. Eagle, Incorporated"},"decision_date":{"kind":"string","value":"2019-03-11"},"docket_number":{"kind":"string","value":"18-30652"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Jones, Haynes, Oldham\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"020lead\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/9888136/\", \"author_raw\": \"\"}, {\"author\": \"\", \"type\": \"040dissent\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/9888137/\", \"author_raw\": \"\"}, {\"author\": \"EDITH H. JONES, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 18-30652 Document: 00514866594 Page: 1 Date Filed: 03/11/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n\\n United States Court of Appeals\\n\\n No. 18-30652\\n Fifth Circuit\\n\\n FILED\\n March 11, 2019\\n\\nJAMES A. LATIOLAIS, Lyle W. Cayce\\n Clerk\\n Plaintiff - Appellee\\n\\nv.\\n\\nHUNTINGTON INGALLS, INCORPORATED, formerly known as\\nNorthrop Grumman Shipbuilding, Incorporated, formerly known as\\nNorthrop Grumman Ship Systems, Incorporated, formerly known as\\nAvondale Industries, Incorporated,\\n\\n Defendant - Appellant\\n\\n\\n\\n Appeal from the United States District Court\\n for the Eastern District of Louisiana\\n\\n\\nBefore JONES, HAYNES, and OLDHAM, Circuit Judges.\\nEDITH H. JONES, Circuit Judge:\\n Like several actions before it, this case involves a Plaintiff who was\\nexposed to asbestos at the Avondale shipyard and eventually contracted\\nmesothelioma. The Defendant removed the case to federal court pursuant to\\n28 U.S.C. § 1442(a)(1), the “federal officer removal statute,” but the district\\ncourt remanded to state court. Constrained by a welter of conflicting\\nprecedent, we must affirm.\\n\\n Case: 18-30652 Document: 00514866594 Page: 2 Date Filed: 03/11/2019\\n\\n\\n\\n No. 18-30652\\n BACKGROUND\\n During the 1960s and 1970s, the United States Navy contracted with\\nthe Defendant Avondale 1 to build and refurbish naval vessels. Most of the\\ncontracts in the 1960s required asbestos for thermal insulation. According to\\nAvondale’s expert, a marine engineer and naval historian, the contracts\\nobligated Avondale “to comply with government plans and specifications, and\\nthe federal government had the right to and did exercise supervision over the\\nprocess to ensure such compliance.” Importantly, however, a Navy ship\\ninspector who worked at Avondale during the 1960s testified that he and his\\ncolleagues “neither monitored nor enforced safety regulations” and “on the job\\nsafety during the construction of vessels for the United States government was\\nthe responsibility of Avondale Shipyards’ safety department.”\\n The Plaintiff, James Latiolais, formerly a machinist aboard the USS\\nTAPPAHANNOCK, was exposed to asbestos while his ship underwent\\nrefurbishing at Avondale for several months. During the refurbishing process,\\nLatiolais spent most of each day on the ship. In 2017, Latiolais was diagnosed\\nwith mesothelioma. He died in October, 2017. 2\\n Latiolais sued Avondale in Louisiana state court for causing him to\\ncontract mesothelioma. He asserts, inter alia, that Avondale negligently failed\\nto warn him about asbestos hazards and failed to provide adequate safety\\nequipment. He did not allege strict liability claims against Avondale.\\n Avondale removed the case to federal court under 28 U.S.C. § 1442(a)(1).\\nLatiolais sought remand, however, and the district court granted the motion.\\n\\n\\n\\n The Defendant Huntington Ingalls was formerly known by many names including\\n 1\\n\\nNorthrop Grumman Shipbuilding and Avondale Industries. Because the parties refer to the\\nDefendant as Avondale, the court does the same.\\n 2Although Latiolais died shortly after filing his petition in Louisiana state court, no\\nparty argues that his death affects any issue in this appeal.\\n 2\\n\\n Case: 18-30652 Document: 00514866594 Page: 3 Date Filed: 03/11/2019\\n\\n\\n\\n No. 18-30652\\nIt ruled in relevant part that because Avondale had not met the “causal nexus”\\nrequirement for officer removal, i.e. had not shown that the United States or\\nany of its officials exercised any control over Avondale’s safety practices,\\nremoval under this statute was improper. Avondale timely appealed.\\n STANDARD OF REVIEW\\n Although an order remanding a case to state court is not generally\\nreviewable, “an order remanding a case to the State court from which it was\\nremoved pursuant to section 1442 or 1443 of this title shall be reviewable by\\nappeal or otherwise.” 28 U.S.C. § 1447(d). “We review the district court’s\\nremand order de novo without a thumb on the remand side of the scale.”\\nLegendre v. Huntington Ingalls, Inc., 885 F.3d 398, 400 (5th Cir. 2018)\\n(quotation marks omitted).\\n DISCUSSION\\n On appeal, Avondale makes three arguments as to why officer removal\\nis proper. First, as amended in 2011, the removal statute now requires only\\nthat a federal directive “relates to”—but not necessarily has a causal\\nrelationship to—the Plaintiffs’ injuries. Second, Avondale asserts that it has\\nsatisfied the causal nexus requirement by showing “that its relationship with\\nMr. Latiolais derived solely from its work for the federal government.” Third,\\nAvondale seeks to avoid precedents of this court contrary to the foregoing\\npropositions. Unfortunately, the failure of the third argument dooms the\\nothers.\\n\\n\\n\\n\\n 3\\n\\n Case: 18-30652 Document: 00514866594 Page: 4 Date Filed: 03/11/2019\\n\\n\\n\\n No. 18-30652\\nI. The “relating to” language\\n The federal officer removal statute was amended in 2011 to broaden the\\nbasis for removal to federal court of claims brought against officers or agents\\nof the federal government and those working under its direction. Thus, the\\nstatute states that an action filed in state court may be removed to federal\\ncourt by: “[t]he United States or any agency thereof or any officer (or any\\nperson acting under that officer) of the United States or of any agency thereof,\\nin an official or individual capacity, for or relating to any act under color of such\\noffice.” 28 U.S.C. § 1442(a)(1) (emphasis added).\\n The Supreme Court has observed more than once that when the term\\n“relating to” appears in a statute, it implies broad and comprehensive coverage.\\nSee, e.g., Morales v. Grans World Airlines, Inc., 504 U.S. 374, 383,\\n112 S. Ct. 2031, 2037 (1992) (“The ordinary meaning of these words is a broad\\none—‘to stand in some relation; to have bearing or concern; to pertain; refer;\\nto bring into association with or connection with.’”) (quoting BLACK’s LAW\\nDICT. 1158 (5th ed. 1979)); see also Shaw v. Delta Air Lines, Inc., 463 U.S. 85,\\n96-98, 103 S. Ct. 2890, 2899-2900 (1983). From the text alone, enhanced by\\nthe Supreme Court’s understanding of its language, Avondale’s argument has\\nconsiderable appeal. Avondale’s work, after all, clearly related to the federal\\ngovernment’s directive to employ asbestos insulation. Under the “relating to”\\ntest, Avondale would preserve a federal venue.\\n In this court, however, what’s past is prologue. Before the amendment,\\nSection 1442 authorized removal of a suit against a federal officer, or person\\nacting under a federal officer, only when the suit was “for any act under color\\nof such office.” 28 U.S.C. § 1442(a)(1) (1996) (emphasis added). To successfully\\nremove a case under the earlier version, this court held, quite reasonably, that\\na defendant must show that it is a person within the meaning of the statute,\\nthat it has a colorable federal defense, that it acted pursuant to a federal\\n 4\\n\\n Case: 18-30652 Document: 00514866594 Page: 5 Date Filed: 03/11/2019\\n\\n\\n\\n No. 18-30652\\nofficer’s directions and that a causal nexus exists between its actions under\\ncolor of federal office and the plaintiff’s claims. Winters v. Diamond Shamrock\\nChem. Co., 149 F.3d 387, 398-400 (5th Cir. 1998). Further, under the causal\\nnexus test, “mere federal involvement does not satisfy the causal nexus\\nrequirement; instead, the defendant must show that its actions taken pursuant\\nto the government’s direction or control caused the plaintiff’s specific injuries.”\\nSavoie v. Huntington Ingalls, Inc., 817 F.3d 457, 462 (5th Cir. 2016).\\n This court applied to the post-2011 amended statute the “causal nexus”\\ntest articulated for the prior statute. Bartel v. Alcoa S.S. Co., Inc.,\\n805 F.3d 169, 172 (5th Cir. 2015). In Bartel, the court quoted the post-2011\\nstatute but adopted the same causal nexus test that pre-dates the new statute.\\nId. at 172, 174-75. Three years later, when Avondale raised the same textual\\nargument that it makes now, the court held that Bartel’s status as precedent\\nprecluded one panel from overruling the former decision. Legendre v.\\nHuntington Ingalls, Inc., 885 F.3d 398, 403 (5th Cir. 2018). Although this\\ncourt’s precedents on the interpretation of Section 1442(a)(1) have proliferated\\nsince Bartel, the reasoning of Legendre continues to control our work.\\n It is true that in Zeringue, a case decided after Bartel but before\\nLegendre, this court appeared to relax the causal nexus standard in light of the\\npost-2011 “relating to” language, but reliance on that case is not appropriate.\\nZeringue v. Crane Company, 846 F.3d 785, 793 (5th Cir. 2017). Zeringue\\nexplained that the addition of the phrase “relating to” in the removal statute\\n“broadens the scope of the statute as the ordinary meaning of [relating to] is a\\nbroad one,” but “[i]t remains, however, that the causal nexus inquiry must . . .\\nbe tailored to fit the facts of each case.” Id. (quotation marks omitted).\\nAlthough these statements appear to give effect to the post-2011 “relating to”\\nlanguage, Zeringue ruled only on the propriety of removing a strict liability\\nclaim under this statute and specifically declined to consider a negligence-\\n 5\\n\\n Case: 18-30652 Document: 00514866594 Page: 6 Date Filed: 03/11/2019\\n\\n\\n\\n No. 18-30652\\nbased failure to warn claim. Before Zeringue, however, in a case brought\\nagainst Avondale, this court had decided that claims for negligent exposure to\\nasbestos could not be removed pursuant to Bartel. Savoie, 817 F.3d at 463.\\n In a case with similar facts to this one, the Savoie court relied on Bartel\\nand found no causal nexus between Avondale’s conduct and government\\nrequirements. Even though the government contracts required Avondale to\\nbuild ships with asbestos, “the government had no control over the shipyard’s\\nsafety procedures” and “the Navy neither imposed any special safety\\nrequirements on the shipyard nor prevented the shipyard from imposing its\\nown safety procedures.” Id. Accordingly, “the government’s directions to the\\nshipyard via the contract specifications did not cause the alleged negligence,\\nand those claims do not support removal.” Id.\\n In contrast, the Savoie plaintiff’s strict liability claims were held to\\nsupport removal, 3 and the court explained that, “[u]nlike claims based on\\nnegligence, those based on strict liability do not turn on discretionary decisions\\nmade by the shipyard.” Id. at 465. “Thus, it is the government’s detailed\\nspecifications, which the shipyard was contractually obligated to follow, that\\nrequired the use of asbestos that allegedly caused [the Plaintiff’s] death. This\\nis enough to show a causal nexus between the . . . strict liability claims and the\\nshipyard’s actions under the color of federal authority.” Id. at 465-66. 4\\n The dichotomy between Zeringue and Savoie was adhered to by\\nLegendre, where the plaintiffs sued Avondale for the plaintiff’s asbestos\\n\\n\\n\\n 3The court concluded that removal was proper because “removal of the entire case is\\nappropriate so long as a single claim satisfies the federal officer removal statute.” Savoie,\\n817 F.3d at 463.\\n\\n 4 Mere use of asbestos is a strict liability claim, whereas failure to warn is a negligence\\nclaim. See Savoie, 817 F.3d at 465 (“The strict liability claims rest on the mere use of asbestos\\n. . . [u]nlike claims based on negligence, those based on strict liability do not turn on\\ndiscretionary decisions made by the shipyard.”).\\n 6\\n\\n Case: 18-30652 Document: 00514866594 Page: 7 Date Filed: 03/11/2019\\n\\n\\n\\n No. 18-30652\\ndisease based on the theory of negligent failure to warn, not strict liability.\\nLegendre, 885 F.3d at 399. Legendre explained that “in Zeringue, we\\nrecognized that the 2011 amendment shifted the causal nexus calculus” but\\n“[i]mportantly, in Zeringue, we explicitly reaffirmed Bartel.” Id. at 401-02.\\nLegendre also relied on Savoie. Id. at 401.\\n All of these cases post-date the 2011 amendment to Section 1442(a)(1),\\nand all continue to cite Bartel, while drawing a distinction for removal\\npurposes between claims for negligence (not removable) and strict liability\\n(removable) pursuant to the causal nexus test. We are bound by this series of\\ncases.\\nII. The Causal Nexus Test\\n Avondale attempts to demonstrate that even under the causal nexus test\\nused in our case law, removal may be sustained. This contention is not\\npersuasive.\\n Avondale’s evidence has not changed since Legendre. Although the\\ngovernment contractually required Avondale to use asbestos in refurbishing\\nthe Navy vessels, Avondale once again “makes no showing that it was not free\\nto adopt the safety measures the plaintiffs now allege would have prevented\\ntheir injuries.” Legendre, 885 F.3d at 403 (quotation marks omitted). From all\\nappearances, Navy vessel inspectors at Avondale “neither monitored nor\\nenforced safety regulations” and “on the job safety during the construction of\\nvessels for the United States government was the responsibility of Avondale\\nShipyards’ safety department.” Avondale points to nothing to rebut this\\nevidence. As the district court concluded, “[b]ased on the evidence produced by\\nboth parties, there is nothing to suggest that the Navy, in its official authority,\\nissued any orders, specifications, or directives relating to safety procedures.”\\nAccordingly, Avondale has not shown a causal nexus under analogous exposure\\nfacts.\\n 7\\n\\n Case: 18-30652 Document: 00514866594 Page: 8 Date Filed: 03/11/2019\\n\\n\\n\\n No. 18-30652\\n Avondale alleges instead that it has satisfied the causal nexus\\nrequirement because “its relationship with Mr. Latiolais derived solely from\\nits work for the federal government.” Avondale contends that in the Bartel line\\nof cases, the plaintiffs were former employees (or their family members) who\\nsued the employer defendants, whereas Latiolais, a Navy man, was never\\nemployed by Avondale, and Avondale’s contact with him occurred solely\\nbecause of its contracts with the federal government. In other words,\\nAvondale’s contention is that because its contact with Latiolais was solely due\\nto its government work on the Navy ship on which Latiolais served, officer\\nremoval is proper.\\n This contention might have prevailed but for the discussions in our other\\ncases. Avondale relies on three pre-Bartel Supreme Court cases and Zeringue\\nfor its proposition. See Maryland v. Soper, 270 U.S. 9, 46 S. Ct. 185 (1926);\\nWillingham v. Morgan, 395 U.S. 402, 89 S. Ct. 1813 (1969); Jefferson County\\nv. Acker, 527 U.S. 423, 119 S. Ct. 2069 (1999). To be sure, those cases contain\\nstatements suggesting that removal is proper if the defendant’s relationship\\nwith the plaintiff is derived solely from the defendant’s official federal duties.\\nFor example, Willingham ruled:\\n In a civil suit of this nature, we think it was sufficient for\\n petitioners to have shown that their relationship to respondent\\n derived solely from their official duties . . . In this case, once\\n petitioners had shown that their only contact with respondent\\n occurred inside the penitentiary, while they were performing their\\n duties, we believe that they had demonstrated the required ‘causal\\n connection.’\\n\\nWillingham, 395 U.S. at 409; 89 S. Ct. at 1817 (footnote omitted). Further, in\\nZeringue, this court quoted Willingham, noting that “‘it [is] sufficient’ for a\\nfederal officer in a civil suit to establish the requisite causal connection by\\nshowing that the officer’s ‘relationship to [the plaintiff] derived solely from [the\\n\\n 8\\n\\n Case: 18-30652 Document: 00514866594 Page: 9 Date Filed: 03/11/2019\\n\\n\\n\\n No. 18-30652\\nofficer’s] official duties.’” Zeringue, 846 F.3d at 793 (quoting Willingham,\\n395 U.S. at 409, 89 S. Ct. at 1817) (alterations and emphasis in Zeringue).\\nIndeed, the Zeringue court reasoned pursuant to this rule that the defendant\\nhad met the causal nexus requirement because its “relationship with [the\\nplaintiff] derives solely from its official authority to provide parts to the Navy,\\nand that official authority relates to [the defendant’s] allegedly improper\\nactions, namely its use of asbestos.” Zeringue, 846 F.3d at 793-94 (emphasis\\nin original).\\n Whatever force could be derived from these statements in Zeringue,\\nhowever, was weakened by its assurance that “[o]ur recent holding in Bartel .\\n. . is not to the contrary.” Id. at 794. Zeringue continued that in Bartel, the\\ncharged conduct of failure to warn of the dangers of asbestos “was private\\nconduct that implicated no federal interest. Because the very purpose of the\\ncausal nexus requirement is to ensure that removal only arises when a federal\\ninterest in the matter exists, an extension of § 1442 to allow those defendants\\nto remove would have stretched the causal nexus requirement to the point of\\nirrelevance.” Id. at 794 (quotation marks omitted). One year later, Legendre\\nquoted Zeringue for these same propositions. Legendre, 885 F.3d at 402.\\nLegendre added, “[i]mportantly, in Zeringue we explicitly reaffirmed Bartel.\\nWe described the charged conduct in Bartel as failing to warn, train, and adopt\\nsafety procedures regarding asbestos. These actions we explained, were\\nprivate conduct that implicated no federal interests.” Id. at 402 (citations and\\nquotation marks omitted). Accordingly, the Bartel defendants did not meet the\\ncausal nexus requirement. Id.\\n Because Latiolais’s claims are the same failure to warn claims that both\\nZeringue and Legendre held implicated no federal interests, we cannot hold\\nthat this case meets the causal nexus requirement.\\n\\n\\n 9\\n\\n Case: 18-30652 Document: 00514866594 Page: 10 Date Filed: 03/11/2019\\n\\n\\n\\n No. 18-30652\\nIII. The rule of orderliness and need to reconsider Bartel en banc\\n Avondale argues that Legendre misapplied the rule of orderliness vis-a-\\nvis Bartel and that Bartel should not control this case “because it did not\\nmeaningfully consider or address the effect of the 2011 amendment.” Legendre\\nexplained that, “[t]his court adheres to a rule of orderliness, under which a\\npanel may not overturn a controlling precedent absent an intervening change\\nin law, such as by a statutory amendment, or the Supreme Court, or our en\\nbanc court.” Legendre, 885 F.3d at 403 (quotation marks omitted). “The 2011\\namendment was, of course, not ‘intervening’; Bartel was decided after the\\nchange and quoted the new ‘relating to’ language. Bartel’s articulation of the\\ncausal nexus standard, and its requirement that the claimed negligence\\nconflict with a federal directive, was integral to the result. We are therefore\\nbound by the Bartel standard.” Id. Avondale cites no case in which this court\\nbypassed the rule of orderliness because a later panel found unconvincing the\\nearlier panel’s statutory interpretation. This appeal is accordingly governed\\nby Bartel and Legendre.\\n Nevertheless, Bartel should be reconsidered en banc in order to align our\\nprecedent with the statute’s evolution. As discussed above, “[b]efore 2011,\\n§ 1442 allowed the removal of a state suit against a federal officer, or person\\nacting under a federal officer, only when the state suit was ‘for any act under\\ncolor of such office.’” Zeringue, 846 F.3d at 793. In 2011, however, Congress\\namended the statute “to allow the removal of a state suit ‘for or relating to any\\nact under color of such office.’” Id. Thus, Congress specifically added the words\\n“relating to” into § 1442. Those words have meaning, and the meaning is\\nplainly broader than that of the predecessor provision.\\n Bartel’s causal nexus standard simply does not give effect to the words\\n“relating to.” This case exemplifies the problem. Avondale refurbished vessels\\nusing asbestos insulation as directed by the Navy. Because Avondale ran its\\n 10\\n\\n Case: 18-30652 Document: 00514866594 Page: 11 Date Filed: 03/11/2019\\n\\n\\n\\n No. 18-30652\\nown safety department free of Navy directives, however, any alleged failure by\\nAvondale to warn its employees or others about asbestos is not an act under\\ncolor of federal office, so Avondale is not being sued “for” a federal act.\\nHowever, Avondale’s failure to warn about asbestos certainly “relates to” its\\nfederal act of building the ships. Applying the post-2011 statutory language\\nwould change the outcome of this appeal and would authorize removal of many\\nmore cases than the causal nexus test permits.\\n Finally, Legendre explained that “although we are bound by precedent,\\nwe note that other circuits have read the 2011 amendments to eliminate the\\nold ‘causal nexus’ requirement.” Id. at 403. The Third and Fourth Circuits\\nshifted their jurisprudence away from the causal nexus test and now require\\nonly a “connection” or “association.” Specifically, the Third Circuit, after\\ndiscussing the addition of the phrase “relating to,” held “it is sufficient for there\\nto be a ‘connection’ or ‘association’ between the act in question and the federal\\noffice.” In re Commonwealth’s Motion to Appoint Counsel Against or Directed\\nto Defender Association of Philadelphia, 790 F.3d 457, 471 (3d Cir. 2015). The\\nFourth Circuit agreed that the addition of “relating to” “broaden[ed] the\\nuniverse of acts that enable federal removal such that there need only be a\\nconnection or association between the act in question and the federal office.”\\nSawyer v. Foster Wheeler LLC, 860 F.3d 249, 258 (4th Cir. 2017) (emphasis in\\noriginal) (quotation marks and internal citation omitted). 5 Federal courts\\nshould be in harmony concerning the interpretation of statutes governing\\nessential procedures like removal. This court is out of step with Congress and\\nour sister circuits.\\n\\n\\n 5 The Eleventh Circuit has also considered the “relating to” language, but the court’s\\nposition is less clear. See Caver v. Central Alabama Electric Coop., 845 F.3d 1135, 1144-45 &\\nn.8 (11th Cir. 2017) (citing the Third Circuit’s “connection or association” language but\\napplying a “causal connection” test).\\n\\n 11\\n\\n Case: 18-30652 Document: 00514866594 Page: 12 Date Filed: 03/11/2019\\n\\n\\n\\n No. 18-30652\\n CONCLUSION\\n For the foregoing reasons, but in hopes that our precedents will be\\nreordered, the remand order of the district court must be AFFIRMED.\\n\\n\\n\\n\\n 12\\n\\n Case: 18-30652 Document: 00514866594 Page: 13 Date Filed: 03/11/2019\\n\\n\\n\\n No. 18-30652\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4375775/\", \"author_raw\": \"EDITH H. JONES, Circuit Judge:\"}, {\"author\": \"HAYNES, Circuit Judge, dissenting\", \"type\": \"dissent\", \"text\": \"HAYNES, Circuit Judge, dissenting:\\n I respectfully dissent from the court’s decision to extend Bartel v. Alcoa\\nSteamship Co., 805 F.3d 169 (5th Cir. 2015), to the facts of this case. I agree\\nthat we are bound by the legal standard that Bartel and progeny established.\\nBut even under that standard, Avondale should prevail on the jurisdictional\\nissue.\\n The core fact that distinguishes this case from Bartel is that Latiolais\\nwas a member of the Navy. He was subject to Avondale’s actions exclusively\\nbecause the Navy assigned him to the USS TAPPAHANNOCK. The Navy\\nalone, not Avondale, could control Latiolais’s actions.\\n Our case law, including Bartel, has never addressed such a situation. 1\\nThough we are bound to apply the standard that Bartel uses—the causal nexus\\ntest—the result is not predetermined.\\n Latiolais’s status as a Navy man and Avondale’s status as a contractor\\nfor the Navy satisfies the causal nexus test. The Supreme Court has held that\\nthe causal nexus test is satisfied when defendants “have shown that their\\nrelationship to [a plaintiff] derived solely from their official duties.”\\nWillingham v. Morgan, 395 U.S. 402, 409 (1969). Latiolais had no relationship\\nwith Avondale other than through its contract to refurbish the USS\\nTAPPAHANNOCK. Their relationship is therefore “derived solely” from\\nAvondale’s official duties.\\n The majority opinion seems to agree with this point, noting that\\nWillingham “suggest[s] that removal is proper” based on that test, but it\\nreasons that our decision in Zeringue v. Crane Co., 846 F.3d 785 (5th Cir. 2017),\\nforbids it. Zeringue does not prohibit removal. Zeringue does say that\\n\\n\\n 1Because this case differs significantly from the Bartel line of cases, it is not a good\\nvehicle to take the underlying issue en banc even assuming arguendo that the Bartel line of\\ncases are wrong.\\n 13\\n\\n Case: 18-30652 Document: 00514866594 Page: 14 Date Filed: 03/11/2019\\n\\n\\n\\n No. 18-30652\\nnegligence claims like those in Bartel involve “private conduct that implicated\\nno federal interest.” Zeringue, 846 F.3d at 794. But that statement must be\\nread in light of the facts of Bartel, which involved an employee of a private,\\nfederal contractor suing the contractor. There, the relationship involves\\nprivate conduct because it centers on a private contractor directing the work of\\nits private employees—a relationship that would exist independent of federal\\ninvolvement. But here, the relationship is not wholly private. Both Avondale\\nand Latiolais were at the ship at the direction of the federal government and\\nneither could control the other’s behavior. The treatment of federal workers\\nby a contractor for the federal government implicates a “federal interest.” Id.\\n Other circuits have reached the same result based on nearly identical\\nfacts. See Ruppel v. CBS Corp., 701 F.3d 1176, 1179, 1181 (7th Cir. 2012)\\n(concluding that a Navy man satisfied the causal nexus test against for his\\nnegligence claim against contractor that “manufactured, sold, distributed, or\\ninstalled” turbines with asbestos under the direction of the navy); Bennett v.\\nMIS Corp., 607 F.3d 1076, 1088, 1091 (6th Cir. 2010) (concluding the causal\\nnexus test was satisfied for FAA employees against a company that remediated\\nmold at their work site). I would follow these cases and conclude that the\\ndistrict court had jurisdiction; therefore, I respectfully dissent.\\n\\n\\n\\n\\n 14\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4375775/\", \"author_raw\": \"HAYNES, Circuit Judge, dissenting\"}]}"},"judge1":{"kind":"string","value":"JONES"},"judge2":{"kind":"string","value":"HAYNES"},"judge3":{"kind":"string","value":"OLDHAM"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":4,"string":"4"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":2,"string":"2"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":2,"string":"2"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4598522/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":1,"string":"1"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":1,"string":"1"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: James A. LATIOLAIS, Plaintiff-Appellee v. HUNTINGTON INGALLS, INCORPORATED, Formerly Known as Northrop Grumman Shipbuilding, Incorporated, Formerly Known as Northrop Grumman Ship Systems, Incorporated, Formerly Known as Avondale Industries, Incorporated, Defendant-Appellant\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-11\nOpinion type: majority\nHas dissenting opinion: Yes\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 18-30652 Document: 00514866594 Page: 1 Date Filed: 03/11/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\n\n United States Court of Appeals\n\n No. 18-30652\n Fifth Circuit\n\n FILED\n March 11, 2019\n\nJAMES A. LATIOLAIS, Lyle W. Cayce\n Clerk\n Plaintiff - Appellee\n\nv.\n\nHUNTINGTON INGALLS, INCORPORATED, formerly known as\nNorthrop Grumman Shipbuilding, Incorporated, formerly known as\nNorthrop Grumman Ship Systems, Incorporated, formerly known as\nAvondale Industries, Incorporated,\n\n Defendant - Appellant\n\n\n\n Appeal from the United States District Court\n for the Eastern District of Louisiana\n\n\nBefore JONES, HAYNES, and OLDHAM, Circuit Judges.\nEDITH H. JONES, Circuit Judge:\n Like several actions before it, this case involves a Plaintiff who was\nexposed to asbestos at the Avondale shipyard and eventually contracted\nmesothelioma. The Defendant removed the case to federal court pursuant to\n28 U.S.C. § 1442(a)(1), the “federal officer removal statute,” but the district\ncourt remanded to state court. Constrained by a welter of conflicting\nprecedent, we must affirm.\n\n Case: 18-30652 Document: 00514866594 Page: 2 Date Filed: 03/11/2019\n\n\n\n No. 18-30652\n BACKGROUND\n During the 1960s and 1970s, the United States Navy contracted with\nthe Defendant Avondale 1 to build and refurbish naval vessels. Most of the\ncontracts in the 1960s required asbestos for thermal insulation. According to\nAvondale’s expert, a marine engineer and naval historian, the contracts\nobligated Avondale “to comply with government plans and specifications, and\nthe federal government had the right to and did exercise supervision over the\nprocess to ensure such compliance.” Importantly, however, a Navy ship\ninspector who worked at Avondale during the 1960s testified that he and his\ncolleagues “neither monitored nor enforced safety regulations” and “on the job\nsafety during the construction of vessels for the United States government was\nthe responsibility of Avondale Shipyards’ safety department.”\n The Plaintiff, James Latiolais, formerly a machinist aboard the USS\nTAPPAHANNOCK, was exposed to asbestos while his ship underwent\nrefurbishing at Avondale for several months. During the refurbishing process,\nLatiolais spent most of each day on the ship. In 2017, Latiolais was diagnosed\nwith mesothelioma. He died in October, 2017. 2\n Latiolais sued Avondale in Louisiana state court for causing him to\ncontract mesothelioma. He asserts, inter alia, that Avondale negligently failed\nto warn him about asbestos hazards and failed to provide adequate safety\nequipment. He did not allege strict liability claims against Avondale.\n Avondale removed the case to federal court under 28 U.S.C. § 1442(a)(1).\nLatiolais sought remand, however, and the district court granted the motion.\n\n\n\n The Defendant Huntington Ingalls was formerly known by many names including\n 1\n\nNorthrop Grumman Shipbuilding and Avondale Industries. Because the parties refer to the\nDefendant as Avondale, the court does the same.\n 2Although Latiolais died shortly after filing his petition in Louisiana state court, no\nparty argues that his death affects any issue in this appeal.\n 2\n\n Case: 18-30652 Document: 00514866594 Page: 3 Date Filed: 03/11/2019\n\n\n\n No. 18-30652\nIt ruled in relevant part that because Avondale had not met the “causal nexus”\nrequirement for officer removal, i.e. had not shown that the United States or\nany of its officials exercised any control over Avondale’s safety practices,\nremoval under this statute was improper. Avondale timely appealed.\n STANDARD OF REVIEW\n Although an order remanding a case to state court is not generally\nreviewable, “an order remanding a case to the State court from which it was\nremoved pursuant to section 1442 or 1443 of this title shall be reviewable by\nappeal or otherwise.” 28 U.S.C. § 1447(d). “We review the district court’s\nremand order de novo without a thumb on the remand side of the scale.”\nLegendre v. Huntington Ingalls, Inc., 885 F.3d 398, 400 (5th Cir. 2018)\n(quotation marks omitted).\n DISCUSSION\n On appeal, Avondale makes three arguments as to why officer removal\nis proper. First, as amended in 2011, the removal statute now requires only\nthat a federal directive “relates to”—but not necessarily has a causal\nrelationship to—the Plaintiffs’ injuries. Second, Avondale asserts that it has\nsatisfied the causal nexus requirement by showing “that its relationship with\nMr. Latiolais derived solely from its work for the federal government.” Third,\nAvondale seeks to avoid precedents of this court contrary to the foregoing\npropositions. Unfortunately, the failure of the third argument dooms the\nothers.\n\n\n\n\n 3\n\n Case: 18-30652 Document: 00514866594 Page: 4 Date Filed: 03/11/2019\n\n\n\n No. 18-30652\nI. The “relating to” language\n The federal officer removal statute was amended in 2011 to broaden the\nbasis for removal to federal court of claims brought against officers or agents\nof the federal government and those working under its direction. Thus, the\nstatute states that an action filed in state court may be removed to federal\ncourt by: “[t]he United States or any agency thereof or any officer (or any\nperson acting under that officer) of the United States or of any agency thereof,\nin an official or individual capacity, for or relating to any act under color of such\noffice.” 28 U.S.C. § 1442(a)(1) (emphasis added).\n The Supreme Court has observed more than once that when the term\n“relating to” appears in a statute, it implies broad and comprehensive coverage.\nSee, e.g., Morales v. Grans World Airlines, Inc., 504 U.S. 374, 383,\n112 S. Ct. 2031, 2037 (1992) (“The ordinary meaning of these words is a broad\none—‘to stand in some relation; to have bearing or concern; to pertain; refer;\nto bring into association with or connection with.’”) (quoting BLACK’s LAW\nDICT. 1158 (5th ed. 1979)); see also Shaw v. Delta Air Lines, Inc., 463 U.S. 85,\n96-98, 103 S. Ct. 2890, 2899-2900 (1983). From the text alone, enhanced by\nthe Supreme Court’s understanding of its language, Avondale’s argument has\nconsiderable appeal. Avondale’s work, after all, clearly related to the federal\ngovernment’s directive to employ asbestos insulation. Under the “relating to”\ntest, Avondale would preserve a federal venue.\n In this court, however, what’s past is prologue. Before the amendment,\nSection 1442 authorized removal of a suit against a federal officer, or person\nacting under a federal officer, only when the suit was “for any act under color\nof such office.” 28 U.S.C. § 1442(a)(1) (1996) (emphasis added). To successfully\nremove a case under the earlier version, this court held, quite reasonably, that\na defendant must show that it is a person within the meaning of the statute,\nthat it has a colorable federal defense, that it acted pursuant to a federal\n 4\n\n Case: 18-30652 Document: 00514866594 Page: 5 Date Filed: 03/11/2019\n\n\n\n No. 18-30652\nofficer’s directions and that a causal nexus exists between its actions under\ncolor of federal office and the plaintiff’s claims. Winters v. Diamond Shamrock\nChem. Co., 149 F.3d 387, 398-400 (5th Cir. 1998). Further, under the causal\nnexus test, “mere federal involvement does not satisfy the causal nexus\nrequirement; instead, the defendant must show that its actions taken pursuant\nto the government’s direction or control caused the plaintiff’s specific injuries.”\nSavoie v. Huntington Ingalls, Inc., 817 F.3d 457, 462 (5th Cir. 2016).\n This court applied to the post-2011 amended statute the “causal nexus”\ntest articulated for the prior statute. Bartel v. Alcoa S.S. Co., Inc.,\n805 F.3d 169, 172 (5th Cir. 2015). In Bartel, the court quoted the post-2011\nstatute but adopted the same causal nexus test that pre-dates the new statute.\nId. at 172, 174-75. Three years later, when Avondale raised the same textual\nargument that it makes now, the court held that Bartel’s status as precedent\nprecluded one panel from overruling the former decision. Legendre v.\nHuntington Ingalls, Inc., 885 F.3d 398, 403 (5th Cir. 2018). Although this\ncourt’s precedents on the interpretation of Section 1442(a)(1) have proliferated\nsince Bartel, the reasoning of Legendre continues to control our work.\n It is true that in Zeringue, a case decided after Bartel but before\nLegendre, this court appeared to relax the causal nexus standard in light of the\npost-2011 “relating to” language, but reliance on that case is not appropriate.\nZeringue v. Crane Company, 846 F.3d 785, 793 (5th Cir. 2017). Zeringue\nexplained that the addition of the phrase “relating to” in the removal statute\n“broadens the scope of the statute as the ordinary meaning of [relating to] is a\nbroad one,” but “[i]t remains, however, that the causal nexus inquiry must . . .\nbe tailored to fit the facts of each case.” Id. (quotation marks omitted).\nAlthough these statements appear to give effect to the post-2011 “relating to”\nlanguage, Zeringue ruled only on the propriety of removing a strict liability\nclaim under this statute and specifically declined to consider a negligence-\n 5\n\n Case: 18-30652 Document: 00514866594 Page: 6 Date Filed: 03/11/2019\n\n\n\n No. 18-30652\nbased failure to warn claim. Before Zeringue, however, in a case brought\nagainst Avondale, this court had decided that claims for negligent exposure to\nasbestos could not be removed pursuant to Bartel. Savoie, 817 F.3d at 463.\n In a case with similar facts to this one, the Savoie court relied on Bartel\nand found no causal nexus between Avondale’s conduct and government\nrequirements. Even though the government contracts required Avondale to\nbuild ships with asbestos, “the government had no control over the shipyard’s\nsafety procedures” and “the Navy neither imposed any special safety\nrequirements on the shipyard nor prevented the shipyard from imposing its\nown safety procedures.” Id. Accordingly, “the government’s directions to the\nshipyard via the contract specifications did not cause the alleged negligence,\nand those claims do not support removal.” Id.\n In contrast, the Savoie plaintiff’s strict liability claims were held to\nsupport removal, 3 and the court explained that, “[u]nlike claims based on\nnegligence, those based on strict liability do not turn on discretionary decisions\nmade by the shipyard.” Id. at 465. “Thus, it is the government’s detailed\nspecifications, which the shipyard was contractually obligated to follow, that\nrequired the use of asbestos that allegedly caused [the Plaintiff’s] death. This\nis enough to show a causal nexus between the . . . strict liability claims and the\nshipyard’s actions under the color of federal authority.” Id. at 465-66. 4\n The dichotomy between Zeringue and Savoie was adhered to by\nLegendre, where the plaintiffs sued Avondale for the plaintiff’s asbestos\n\n\n\n 3The court concluded that removal was proper because “removal of the entire case is\nappropriate so long as a single claim satisfies the federal officer removal statute.” Savoie,\n817 F.3d at 463.\n\n 4 Mere use of asbestos is a strict liability claim, whereas failure to warn is a negligence\nclaim. See Savoie, 817 F.3d at 465 (“The strict liability claims rest on the mere use of asbestos\n. . . [u]nlike claims based on negligence, those based on strict liability do not turn on\ndiscretionary decisions made by the shipyard.”).\n 6\n\n Case: 18-30652 Document: 00514866594 Page: 7 Date Filed: 03/11/2019\n\n\n\n No. 18-30652\ndisease based on the theory of negligent failure to warn, not strict liability.\nLegendre, 885 F.3d at 399. Legendre explained that “in Zeringue, we\nrecognized that the 2011 amendment shifted the causal nexus calculus” but\n“[i]mportantly, in Zeringue, we explicitly reaffirmed Bartel.” Id. at 401-02.\nLegendre also relied on Savoie. Id. at 401.\n All of these cases post-date the 2011 amendment to Section 1442(a)(1),\nand all continue to cite Bartel, while drawing a distinction for removal\npurposes between claims for negligence (not removable) and strict liability\n(removable) pursuant to the causal nexus test. We are bound by this series of\ncases.\nII. The Causal Nexus Test\n Avondale attempts to demonstrate that even under the causal nexus test\nused in our case law, removal may be sustained. This contention is not\npersuasive.\n Avondale’s evidence has not changed since Legendre. Although the\ngovernment contractually required Avondale to use asbestos in refurbishing\nthe Navy vessels, Avondale once again “makes no showing that it was not free\nto adopt the safety measures the plaintiffs now allege would have prevented\ntheir injuries.” Legendre, 885 F.3d at 403 (quotation marks omitted). From all\nappearances, Navy vessel inspectors at Avondale “neither monitored nor\nenforced safety regulations” and “on the job safety during the construction of\nvessels for the United States government was the responsibility of Avondale\nShipyards’ safety department.” Avondale points to nothing to rebut this\nevidence. As the district court concluded, “[b]ased on the evidence produced by\nboth parties, there is nothing to suggest that the Navy, in its official authority,\nissued any orders, specifications, or directives relating to safety procedures.”\nAccordingly, Avondale has not shown a causal nexus under analogous exposure\nfacts.\n 7\n\n Case: 18-30652 Document: 00514866594 Page: 8 Date Filed: 03/11/2019\n\n\n\n No. 18-30652\n Avondale alleges instead that it has satisfied the causal nexus\nrequirement because “its relationship with Mr. Latiolais derived solely from\nits work for the federal government.” Avondale contends that in the Bartel line\nof cases, the plaintiffs were former employees (or their family members) who\nsued the employer defendants, whereas Latiolais, a Navy man, was never\nemployed by Avondale, and Avondale’s contact with him occurred solely\nbecause of its contracts with the federal government. In other words,\nAvondale’s contention is that because its contact with Latiolais was solely due\nto its government work on the Navy ship on which Latiolais served, officer\nremoval is proper.\n This contention might have prevailed but for the discussions in our other\ncases. Avondale relies on three pre-Bartel Supreme Court cases and Zeringue\nfor its proposition. See Maryland v. Soper, 270 U.S. 9, 46 S. Ct. 185 (1926);\nWillingham v. Morgan, 395 U.S. 402, 89 S. Ct. 1813 (1969); Jefferson County\nv. Acker, 527 U.S. 423, 119 S. Ct. 2069 (1999). To be sure, those cases contain\nstatements suggesting that removal is proper if the defendant’s relationship\nwith the plaintiff is derived solely from the defendant’s official federal duties.\nFor example, Willingham ruled:\n In a civil suit of this nature, we think it was sufficient for\n petitioners to have shown that their relationship to respondent\n derived solely from their official duties . . . In this case, once\n petitioners had shown that their only contact with respondent\n occurred inside the penitentiary, while they were performing their\n duties, we believe that they had demonstrated the required ‘causal\n connection.’\n\nWillingham, 395 U.S. at 409; 89 S. Ct. at 1817 (footnote omitted). Further, in\nZeringue, this court quoted Willingham, noting that “‘it [is] sufficient’ for a\nfederal officer in a civil suit to establish the requisite causal connection by\nshowing that the officer’s ‘relationship to [the plaintiff] derived solely from [the\n\n 8\n\n Case: 18-30652 Document: 00514866594 Page: 9 Date Filed: 03/11/2019\n\n\n\n No. 18-30652\nofficer’s] official duties.’” Zeringue, 846 F.3d at 793 (quoting Willingham,\n395 U.S. at 409, 89 S. Ct. at 1817) (alterations and emphasis in Zeringue).\nIndeed, the Zeringue court reasoned pursuant to this rule that the defendant\nhad met the causal nexus requirement because its “relationship with [the\nplaintiff] derives solely from its official authority to provide parts to the Navy,\nand that official authority relates to [the defendant’s] allegedly improper\nactions, namely its use of asbestos.” Zeringue, 846 F.3d at 793-94 (emphasis\nin original).\n Whatever force could be derived from these statements in Zeringue,\nhowever, was weakened by its assurance that “[o]ur recent holding in Bartel .\n. . is not to the contrary.” Id. at 794. Zeringue continued that in Bartel, the\ncharged conduct of failure to warn of the dangers of asbestos “was private\nconduct that implicated no federal interest. Because the very purpose of the\ncausal nexus requirement is to ensure that removal only arises when a federal\ninterest in the matter exists, an extension of § 1442 to allow those defendants\nto remove would have stretched the causal nexus requirement to the point of\nirrelevance.” Id. at 794 (quotation marks omitted). One year later, Legendre\nquoted Zeringue for these same propositions. Legendre, 885 F.3d at 402.\nLegendre added, “[i]mportantly, in Zeringue we explicitly reaffirmed Bartel.\nWe described the charged conduct in Bartel as failing to warn, train, and adopt\nsafety procedures regarding asbestos. These actions we explained, were\nprivate conduct that implicated no federal interests.” Id. at 402 (citations and\nquotation marks omitted). Accordingly, the Bartel defendants did not meet the\ncausal nexus requirement. Id.\n Because Latiolais’s claims are the same failure to warn claims that both\nZeringue and Legendre held implicated no federal interests, we cannot hold\nthat this case meets the causal nexus requirement.\n\n\n 9\n\n Case: 18-30652 Document: 00514866594 Page: 10 Date Filed: 03/11/2019\n\n\n\n No. 18-30652\nIII. The rule of orderliness and need to reconsider Bartel en banc\n Avondale argues that Legendre misapplied the rule of orderliness vis-a-\nvis Bartel and that Bartel should not control this case “because it did not\nmeaningfully consider or address the effect of the 2011 amendment.” Legendre\nexplained that, “[t]his court adheres to a rule of orderliness, under which a\npanel may not overturn a controlling precedent absent an intervening change\nin law, such as by a statutory amendment, or the Supreme Court, or our en\nbanc court.” Legendre, 885 F.3d at 403 (quotation marks omitted). “The 2011\namendment was, of course, not ‘intervening’; Bartel was decided after the\nchange and quoted the new ‘relating to’ language. Bartel’s articulation of the\ncausal nexus standard, and its requirement that the claimed negligence\nconflict with a federal directive, was integral to the result. We are therefore\nbound by the Bartel standard.” Id. Avondale cites no case in which this court\nbypassed the rule of orderliness because a later panel found unconvincing the\nearlier panel’s statutory interpretation. This appeal is accordingly governed\nby Bartel and Legendre.\n Nevertheless, Bartel should be reconsidered en banc in order to align our\nprecedent with the statute’s evolution. As discussed above, “[b]efore 2011,\n§ 1442 allowed the removal of a state suit against a federal officer, or person\nacting under a federal officer, only when the state suit was ‘for any act under\ncolor of such office.’” Zeringue, 846 F.3d at 793. In 2011, however, Congress\namended the statute “to allow the removal of a state suit ‘for or relating to any\nact under color of such office.’” Id. Thus, Congress specifically added the words\n“relating to” into § 1442. Those words have meaning, and the meaning is\nplainly broader than that of the predecessor provision.\n Bartel’s causal nexus standard simply does not give effect to the words\n“relating to.” This case exemplifies the problem. Avondale refurbished vessels\nusing asbestos insulation as directed by the Navy. Because Avondale ran its\n 10\n\n Case: 18-30652 Document: 00514866594 Page: 11 Date Filed: 03/11/2019\n\n\n\n No. 18-30652\nown safety department free of Navy directives, however, any alleged failure by\nAvondale to warn its employees or others about asbestos is not an act under\ncolor of federal office, so Avondale is not being sued “for” a federal act.\nHowever, Avondale’s failure to warn about asbestos certainly “relates to” its\nfederal act of building the ships. Applying the post-2011 statutory language\nwould change the outcome of this appeal and would authorize removal of many\nmore cases than the causal nexus test permits.\n Finally, Legendre explained that “although we are bound by precedent,\nwe note that other circuits have read the 2011 amendments to eliminate the\nold ‘causal nexus’ requirement.” Id. at 403. The Third and Fourth Circuits\nshifted their jurisprudence away from the causal nexus test and now require\nonly a “connection” or “association.” Specifically, the Third Circuit, after\ndiscussing the addition of the phrase “relating to,” held “it is sufficient for there\nto be a ‘connection’ or ‘association’ between the act in question and the federal\noffice.” In re Commonwealth’s Motion to Appoint Counsel Against or Directed\nto Defender Association of Philadelphia, 790 F.3d 457, 471 (3d Cir. 2015). The\nFourth Circuit agreed that the addition of “relating to” “broaden[ed] the\nuniverse of acts that enable federal removal such that there need only be a\nconnection or association between the act in question and the federal office.”\nSawyer v. Foster Wheeler LLC, 860 F.3d 249, 258 (4th Cir. 2017) (emphasis in\noriginal) (quotation marks and internal citation omitted). 5 Federal courts\nshould be in harmony concerning the interpretation of statutes governing\nessential procedures like removal. This court is out of step with Congress and\nour sister circuits.\n\n\n 5 The Eleventh Circuit has also considered the “relating to” language, but the court’s\nposition is less clear. See Caver v. Central Alabama Electric Coop., 845 F.3d 1135, 1144-45 &\nn.8 (11th Cir. 2017) (citing the Third Circuit’s “connection or association” language but\napplying a “causal connection” test).\n\n 11\n\n Case: 18-30652 Document: 00514866594 Page: 12 Date Filed: 03/11/2019\n\n\n\n No. 18-30652\n CONCLUSION\n For the foregoing reasons, but in hopes that our precedents will be\nreordered, the remand order of the district court must be AFFIRMED.\n\n\n\n\n 12\n\n Case: 18-30652 Document: 00514866594 Page: 13 Date Filed: 03/11/2019\n\n\n\n No. 18-30652\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: James A. LATIOLAIS, Plaintiff-Appellee v. HUNTINGTON INGALLS, INCORPORATED, Formerly Known as Northrop Grumman Shipbuilding, Incorporated, Formerly Known as Northrop Grumman Ship Systems, Incorporated, Formerly Known as Avondale Industries, Incorporated, Defendant-Appellant\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-11\\nOpinion type: majority\\nHas dissenting opinion: Yes\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 18-30652 Document: 00514866594 Page: 1 Date Filed: 03/11/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n\\n United States Court of Appeals\\n\\n No. 18-30652\\n Fifth Circuit\\n\\n FILED\\n March 11, 2019\\n\\nJAMES A. LATIOLAIS, Lyle W. Cayce\\n Clerk\\n Plaintiff - Appellee\\n\\nv.\\n\\nHUNTINGTON INGALLS, INCORPORATED, formerly known as\\nNorthrop Grumman Shipbuilding, Incorporated, formerly known as\\nNorthrop Grumman Ship Systems, Incorporated, formerly known as\\nAvondale Industries, Incorporated,\\n\\n Defendant - Appellant\\n\\n\\n\\n Appeal from the United States District Court\\n for the Eastern District of Louisiana\\n\\n\\nBefore JONES, HAYNES, and OLDHAM, Circuit Judges.\\nEDITH H. JONES, Circuit Judge:\\n Like several actions before it, this case involves a Plaintiff who was\\nexposed to asbestos at the Avondale shipyard and eventually contracted\\nmesothelioma. The Defendant removed the case to federal court pursuant to\\n28 U.S.C. § 1442(a)(1), the “federal officer removal statute,” but the district\\ncourt remanded to state court. Constrained by a welter of conflicting\\nprecedent, we must affirm.\\n\\n Case: 18-30652 Document: 00514866594 Page: 2 Date Filed: 03/11/2019\\n\\n\\n\\n No. 18-30652\\n BACKGROUND\\n During the 1960s and 1970s, the United States Navy contracted with\\nthe Defendant Avondale 1 to build and refurbish naval vessels. Most of the\\ncontracts in the 1960s required asbestos for thermal insulation. According to\\nAvondale’s expert, a marine engineer and naval historian, the contracts\\nobligated Avondale “to comply with government plans and specifications, and\\nthe federal government had the right to and did exercise supervision over the\\nprocess to ensure such compliance.” Importantly, however, a Navy ship\\ninspector who worked at Avondale during the 1960s testified that he and his\\ncolleagues “neither monitored nor enforced safety regulations” and “on the job\\nsafety during the construction of vessels for the United States government was\\nthe responsibility of Avondale Shipyards’ safety department.”\\n The Plaintiff, James Latiolais, formerly a machinist aboard the USS\\nTAPPAHANNOCK, was exposed to asbestos while his ship underwent\\nrefurbishing at Avondale for several months. During the refurbishing process,\\nLatiolais spent most of each day on the ship. In 2017, Latiolais was diagnosed\\nwith mesothelioma. He died in October, 2017. 2\\n Latiolais sued Avondale in Louisiana state court for causing him to\\ncontract mesothelioma. He asserts, inter alia, that Avondale negligently failed\\nto warn him about asbestos hazards and failed to provide adequate safety\\nequipment. He did not allege strict liability claims against Avondale.\\n Avondale removed the case to federal court under 28 U.S.C. § 1442(a)(1).\\nLatiolais sought remand, however, and the district court granted the motion.\\n\\n\\n\\n The Defendant Huntington Ingalls was formerly known by many names including\\n 1\\n\\nNorthrop Grumman Shipbuilding and Avondale Industries. Because the parties refer to the\\nDefendant as Avondale, the court does the same.\\n 2Although Latiolais died shortly after filing his petition in Louisiana state court, no\\nparty argues that his death affects any issue in this appeal.\\n 2\\n\\n Case: 18-30652 Document: 00514866594 Page: 3 Date Filed: 03/11/2019\\n\\n\\n\\n No. 18-30652\\nIt ruled in relevant part that because Avondale had not met the “causal nexus”\\nrequirement for officer removal, i.e. had not shown that the United States or\\nany of its officials exercised any control over Avondale’s safety practices,\\nremoval under this statute was improper. Avondale timely appealed.\\n STANDARD OF REVIEW\\n Although an order remanding a case to state court is not generally\\nreviewable, “an order remanding a case to the State court from which it was\\nremoved pursuant to section 1442 or 1443 of this title shall be reviewable by\\nappeal or otherwise.” 28 U.S.C. § 1447(d). “We review the district court’s\\nremand order de novo without a thumb on the remand side of the scale.”\\nLegendre v. Huntington Ingalls, Inc., 885 F.3d 398, 400 (5th Cir. 2018)\\n(quotation marks omitted).\\n DISCUSSION\\n On appeal, Avondale makes three arguments as to why officer removal\\nis proper. First, as amended in 2011, the removal statute now requires only\\nthat a federal directive “relates to”—but not necessarily has a causal\\nrelationship to—the Plaintiffs’ injuries. Second, Avondale asserts that it has\\nsatisfied the causal nexus requirement by showing “that its relationship with\\nMr. Latiolais derived solely from its work for the federal government.” Third,\\nAvondale seeks to avoid precedents of this court contrary to the foregoing\\npropositions. Unfortunately, the failure of the third argument dooms the\\nothers.\\n\\n\\n\\n\\n 3\\n\\n Case: 18-30652 Document: 00514866594 Page: 4 Date Filed: 03/11/2019\\n\\n\\n\\n No. 18-30652\\nI. The “relating to” language\\n The federal officer removal statute was amended in 2011 to broaden the\\nbasis for removal to federal court of claims brought against officers or agents\\nof the federal government and those working under its direction. Thus, the\\nstatute states that an action filed in state court may be removed to federal\\ncourt by: “[t]he United States or any agency thereof or any officer (or any\\nperson acting under that officer) of the United States or of any agency thereof,\\nin an official or individual capacity, for or relating to any act under color of such\\noffice.” 28 U.S.C. § 1442(a)(1) (emphasis added).\\n The Supreme Court has observed more than once that when the term\\n“relating to” appears in a statute, it implies broad and comprehensive coverage.\\nSee, e.g., Morales v. Grans World Airlines, Inc., 504 U.S. 374, 383,\\n112 S. Ct. 2031, 2037 (1992) (“The ordinary meaning of these words is a broad\\none—‘to stand in some relation; to have bearing or concern; to pertain; refer;\\nto bring into association with or connection with.’”) (quoting BLACK’s LAW\\nDICT. 1158 (5th ed. 1979)); see also Shaw v. Delta Air Lines, Inc., 463 U.S. 85,\\n96-98, 103 S. Ct. 2890, 2899-2900 (1983). From the text alone, enhanced by\\nthe Supreme Court’s understanding of its language, Avondale’s argument has\\nconsiderable appeal. Avondale’s work, after all, clearly related to the federal\\ngovernment’s directive to employ asbestos insulation. Under the “relating to”\\ntest, Avondale would preserve a federal venue.\\n In this court, however, what’s past is prologue. Before the amendment,\\nSection 1442 authorized removal of a suit against a federal officer, or person\\nacting under a federal officer, only when the suit was “for any act under color\\nof such office.” 28 U.S.C. § 1442(a)(1) (1996) (emphasis added). To successfully\\nremove a case under the earlier version, this court held, quite reasonably, that\\na defendant must show that it is a person within the meaning of the statute,\\nthat it has a colorable federal defense, that it acted pursuant to a federal\\n 4\\n\\n Case: 18-30652 Document: 00514866594 Page: 5 Date Filed: 03/11/2019\\n\\n\\n\\n No. 18-30652\\nofficer’s directions and that a causal nexus exists between its actions under\\ncolor of federal office and the plaintiff’s claims. Winters v. Diamond Shamrock\\nChem. Co., 149 F.3d 387, 398-400 (5th Cir. 1998). Further, under the causal\\nnexus test, “mere federal involvement does not satisfy the causal nexus\\nrequirement; instead, the defendant must show that its actions taken pursuant\\nto the government’s direction or control caused the plaintiff’s specific injuries.”\\nSavoie v. Huntington Ingalls, Inc., 817 F.3d 457, 462 (5th Cir. 2016).\\n This court applied to the post-2011 amended statute the “causal nexus”\\ntest articulated for the prior statute. Bartel v. Alcoa S.S. Co., Inc.,\\n805 F.3d 169, 172 (5th Cir. 2015). In Bartel, the court quoted the post-2011\\nstatute but adopted the same causal nexus test that pre-dates the new statute.\\nId. at 172, 174-75. Three years later, when Avondale raised the same textual\\nargument that it makes now, the court held that Bartel’s status as precedent\\nprecluded one panel from overruling the former decision. Legendre v.\\nHuntington Ingalls, Inc., 885 F.3d 398, 403 (5th Cir. 2018). Although this\\ncourt’s precedents on the interpretation of Section 1442(a)(1) have proliferated\\nsince Bartel, the reasoning of Legendre continues to control our work.\\n It is true that in Zeringue, a case decided after Bartel but before\\nLegendre, this court appeared to relax the causal nexus standard in light of the\\npost-2011 “relating to” language, but reliance on that case is not appropriate.\\nZeringue v. Crane Company, 846 F.3d 785, 793 (5th Cir. 2017). Zeringue\\nexplained that the addition of the phrase “relating to” in the removal statute\\n“broadens the scope of the statute as the ordinary meaning of [relating to] is a\\nbroad one,” but “[i]t remains, however, that the causal nexus inquiry must . . .\\nbe tailored to fit the facts of each case.” Id. (quotation marks omitted).\\nAlthough these statements appear to give effect to the post-2011 “relating to”\\nlanguage, Zeringue ruled only on the propriety of removing a strict liability\\nclaim under this statute and specifically declined to consider a negligence-\\n 5\\n\\n Case: 18-30652 Document: 00514866594 Page: 6 Date Filed: 03/11/2019\\n\\n\\n\\n No. 18-30652\\nbased failure to warn claim. Before Zeringue, however, in a case brought\\nagainst Avondale, this court had decided that claims for negligent exposure to\\nasbestos could not be removed pursuant to Bartel. Savoie, 817 F.3d at 463.\\n In a case with similar facts to this one, the Savoie court relied on Bartel\\nand found no causal nexus between Avondale’s conduct and government\\nrequirements. Even though the government contracts required Avondale to\\nbuild ships with asbestos, “the government had no control over the shipyard’s\\nsafety procedures” and “the Navy neither imposed any special safety\\nrequirements on the shipyard nor prevented the shipyard from imposing its\\nown safety procedures.” Id. Accordingly, “the government’s directions to the\\nshipyard via the contract specifications did not cause the alleged negligence,\\nand those claims do not support removal.” Id.\\n In contrast, the Savoie plaintiff’s strict liability claims were held to\\nsupport removal, 3 and the court explained that, “[u]nlike claims based on\\nnegligence, those based on strict liability do not turn on discretionary decisions\\nmade by the shipyard.” Id. at 465. “Thus, it is the government’s detailed\\nspecifications, which the shipyard was contractually obligated to follow, that\\nrequired the use of asbestos that allegedly caused [the Plaintiff’s] death. This\\nis enough to show a causal nexus between the . . . strict liability claims and the\\nshipyard’s actions under the color of federal authority.” Id. at 465-66. 4\\n The dichotomy between Zeringue and Savoie was adhered to by\\nLegendre, where the plaintiffs sued Avondale for the plaintiff’s asbestos\\n\\n\\n\\n 3The court concluded that removal was proper because “removal of the entire case is\\nappropriate so long as a single claim satisfies the federal officer removal statute.” Savoie,\\n817 F.3d at 463.\\n\\n 4 Mere use of asbestos is a strict liability claim, whereas failure to warn is a negligence\\nclaim. See Savoie, 817 F.3d at 465 (“The strict liability claims rest on the mere use of asbestos\\n. . . [u]nlike claims based on negligence, those based on strict liability do not turn on\\ndiscretionary decisions made by the shipyard.”).\\n 6\\n\\n Case: 18-30652 Document: 00514866594 Page: 7 Date Filed: 03/11/2019\\n\\n\\n\\n No. 18-30652\\ndisease based on the theory of negligent failure to warn, not strict liability.\\nLegendre, 885 F.3d at 399. Legendre explained that “in Zeringue, we\\nrecognized that the 2011 amendment shifted the causal nexus calculus” but\\n“[i]mportantly, in Zeringue, we explicitly reaffirmed Bartel.” Id. at 401-02.\\nLegendre also relied on Savoie. Id. at 401.\\n All of these cases post-date the 2011 amendment to Section 1442(a)(1),\\nand all continue to cite Bartel, while drawing a distinction for removal\\npurposes between claims for negligence (not removable) and strict liability\\n(removable) pursuant to the causal nexus test. We are bound by this series of\\ncases.\\nII. The Causal Nexus Test\\n Avondale attempts to demonstrate that even under the causal nexus test\\nused in our case law, removal may be sustained. This contention is not\\npersuasive.\\n Avondale’s evidence has not changed since Legendre. Although the\\ngovernment contractually required Avondale to use asbestos in refurbishing\\nthe Navy vessels, Avondale once again “makes no showing that it was not free\\nto adopt the safety measures the plaintiffs now allege would have prevented\\ntheir injuries.” Legendre, 885 F.3d at 403 (quotation marks omitted). From all\\nappearances, Navy vessel inspectors at Avondale “neither monitored nor\\nenforced safety regulations” and “on the job safety during the construction of\\nvessels for the United States government was the responsibility of Avondale\\nShipyards’ safety department.” Avondale points to nothing to rebut this\\nevidence. As the district court concluded, “[b]ased on the evidence produced by\\nboth parties, there is nothing to suggest that the Navy, in its official authority,\\nissued any orders, specifications, or directives relating to safety procedures.”\\nAccordingly, Avondale has not shown a causal nexus under analogous exposure\\nfacts.\\n 7\\n\\n Case: 18-30652 Document: 00514866594 Page: 8 Date Filed: 03/11/2019\\n\\n\\n\\n No. 18-30652\\n Avondale alleges instead that it has satisfied the causal nexus\\nrequirement because “its relationship with Mr. Latiolais derived solely from\\nits work for the federal government.” Avondale contends that in the Bartel line\\nof cases, the plaintiffs were former employees (or their family members) who\\nsued the employer defendants, whereas Latiolais, a Navy man, was never\\nemployed by Avondale, and Avondale’s contact with him occurred solely\\nbecause of its contracts with the federal government. In other words,\\nAvondale’s contention is that because its contact with Latiolais was solely due\\nto its government work on the Navy ship on which Latiolais served, officer\\nremoval is proper.\\n This contention might have prevailed but for the discussions in our other\\ncases. Avondale relies on three pre-Bartel Supreme Court cases and Zeringue\\nfor its proposition. See Maryland v. Soper, 270 U.S. 9, 46 S. Ct. 185 (1926);\\nWillingham v. Morgan, 395 U.S. 402, 89 S. Ct. 1813 (1969); Jefferson County\\nv. Acker, 527 U.S. 423, 119 S. Ct. 2069 (1999). To be sure, those cases contain\\nstatements suggesting that removal is proper if the defendant’s relationship\\nwith the plaintiff is derived solely from the defendant’s official federal duties.\\nFor example, Willingham ruled:\\n In a civil suit of this nature, we think it was sufficient for\\n petitioners to have shown that their relationship to respondent\\n derived solely from their official duties . . . In this case, once\\n petitioners had shown that their only contact with respondent\\n occurred inside the penitentiary, while they were performing their\\n duties, we believe that they had demonstrated the required ‘causal\\n connection.’\\n\\nWillingham, 395 U.S. at 409; 89 S. Ct. at 1817 (footnote omitted). Further, in\\nZeringue, this court quoted Willingham, noting that “‘it [is] sufficient’ for a\\nfederal officer in a civil suit to establish the requisite causal connection by\\nshowing that the officer’s ‘relationship to [the plaintiff] derived solely from [the\\n\\n 8\\n\\n Case: 18-30652 Document: 00514866594 Page: 9 Date Filed: 03/11/2019\\n\\n\\n\\n No. 18-30652\\nofficer’s] official duties.’” Zeringue, 846 F.3d at 793 (quoting Willingham,\\n395 U.S. at 409, 89 S. Ct. at 1817) (alterations and emphasis in Zeringue).\\nIndeed, the Zeringue court reasoned pursuant to this rule that the defendant\\nhad met the causal nexus requirement because its “relationship with [the\\nplaintiff] derives solely from its official authority to provide parts to the Navy,\\nand that official authority relates to [the defendant’s] allegedly improper\\nactions, namely its use of asbestos.” Zeringue, 846 F.3d at 793-94 (emphasis\\nin original).\\n Whatever force could be derived from these statements in Zeringue,\\nhowever, was weakened by its assurance that “[o]ur recent holding in Bartel .\\n. . is not to the contrary.” Id. at 794. Zeringue continued that in Bartel, the\\ncharged conduct of failure to warn of the dangers of asbestos “was private\\nconduct that implicated no federal interest. Because the very purpose of the\\ncausal nexus requirement is to ensure that removal only arises when a federal\\ninterest in the matter exists, an extension of § 1442 to allow those defendants\\nto remove would have stretched the causal nexus requirement to the point of\\nirrelevance.” Id. at 794 (quotation marks omitted). One year later, Legendre\\nquoted Zeringue for these same propositions. Legendre, 885 F.3d at 402.\\nLegendre added, “[i]mportantly, in Zeringue we explicitly reaffirmed Bartel.\\nWe described the charged conduct in Bartel as failing to warn, train, and adopt\\nsafety procedures regarding asbestos. These actions we explained, were\\nprivate conduct that implicated no federal interests.” Id. at 402 (citations and\\nquotation marks omitted). Accordingly, the Bartel defendants did not meet the\\ncausal nexus requirement. Id.\\n Because Latiolais’s claims are the same failure to warn claims that both\\nZeringue and Legendre held implicated no federal interests, we cannot hold\\nthat this case meets the causal nexus requirement.\\n\\n\\n 9\\n\\n Case: 18-30652 Document: 00514866594 Page: 10 Date Filed: 03/11/2019\\n\\n\\n\\n No. 18-30652\\nIII. The rule of orderliness and need to reconsider Bartel en banc\\n Avondale argues that Legendre misapplied the rule of orderliness vis-a-\\nvis Bartel and that Bartel should not control this case “because it did not\\nmeaningfully consider or address the effect of the 2011 amendment.” Legendre\\nexplained that, “[t]his court adheres to a rule of orderliness, under which a\\npanel may not overturn a controlling precedent absent an intervening change\\nin law, such as by a statutory amendment, or the Supreme Court, or our en\\nbanc court.” Legendre, 885 F.3d at 403 (quotation marks omitted). “The 2011\\namendment was, of course, not ‘intervening’; Bartel was decided after the\\nchange and quoted the new ‘relating to’ language. Bartel’s articulation of the\\ncausal nexus standard, and its requirement that the claimed negligence\\nconflict with a federal directive, was integral to the result. We are therefore\\nbound by the Bartel standard.” Id. Avondale cites no case in which this court\\nbypassed the rule of orderliness because a later panel found unconvincing the\\nearlier panel’s statutory interpretation. This appeal is accordingly governed\\nby Bartel and Legendre.\\n Nevertheless, Bartel should be reconsidered en banc in order to align our\\nprecedent with the statute’s evolution. As discussed above, “[b]efore 2011,\\n§ 1442 allowed the removal of a state suit against a federal officer, or person\\nacting under a federal officer, only when the state suit was ‘for any act under\\ncolor of such office.’” Zeringue, 846 F.3d at 793. In 2011, however, Congress\\namended the statute “to allow the removal of a state suit ‘for or relating to any\\nact under color of such office.’” Id. Thus, Congress specifically added the words\\n“relating to” into § 1442. Those words have meaning, and the meaning is\\nplainly broader than that of the predecessor provision.\\n Bartel’s causal nexus standard simply does not give effect to the words\\n“relating to.” This case exemplifies the problem. Avondale refurbished vessels\\nusing asbestos insulation as directed by the Navy. Because Avondale ran its\\n 10\\n\\n Case: 18-30652 Document: 00514866594 Page: 11 Date Filed: 03/11/2019\\n\\n\\n\\n No. 18-30652\\nown safety department free of Navy directives, however, any alleged failure by\\nAvondale to warn its employees or others about asbestos is not an act under\\ncolor of federal office, so Avondale is not being sued “for” a federal act.\\nHowever, Avondale’s failure to warn about asbestos certainly “relates to” its\\nfederal act of building the ships. Applying the post-2011 statutory language\\nwould change the outcome of this appeal and would authorize removal of many\\nmore cases than the causal nexus test permits.\\n Finally, Legendre explained that “although we are bound by precedent,\\nwe note that other circuits have read the 2011 amendments to eliminate the\\nold ‘causal nexus’ requirement.” Id. at 403. The Third and Fourth Circuits\\nshifted their jurisprudence away from the causal nexus test and now require\\nonly a “connection” or “association.” Specifically, the Third Circuit, after\\ndiscussing the addition of the phrase “relating to,” held “it is sufficient for there\\nto be a ‘connection’ or ‘association’ between the act in question and the federal\\noffice.” In re Commonwealth’s Motion to Appoint Counsel Against or Directed\\nto Defender Association of Philadelphia, 790 F.3d 457, 471 (3d Cir. 2015). The\\nFourth Circuit agreed that the addition of “relating to” “broaden[ed] the\\nuniverse of acts that enable federal removal such that there need only be a\\nconnection or association between the act in question and the federal office.”\\nSawyer v. Foster Wheeler LLC, 860 F.3d 249, 258 (4th Cir. 2017) (emphasis in\\noriginal) (quotation marks and internal citation omitted). 5 Federal courts\\nshould be in harmony concerning the interpretation of statutes governing\\nessential procedures like removal. This court is out of step with Congress and\\nour sister circuits.\\n\\n\\n 5 The Eleventh Circuit has also considered the “relating to” language, but the court’s\\nposition is less clear. See Caver v. Central Alabama Electric Coop., 845 F.3d 1135, 1144-45 &\\nn.8 (11th Cir. 2017) (citing the Third Circuit’s “connection or association” language but\\napplying a “causal connection” test).\\n\\n 11\\n\\n Case: 18-30652 Document: 00514866594 Page: 12 Date Filed: 03/11/2019\\n\\n\\n\\n No. 18-30652\\n CONCLUSION\\n For the foregoing reasons, but in hopes that our precedents will be\\nreordered, the remand order of the district court must be AFFIRMED.\\n\\n\\n\\n\\n 12\\n\\n Case: 18-30652 Document: 00514866594 Page: 13 Date Filed: 03/11/2019\\n\\n\\n\\n No. 18-30652\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1082,"cells":{"id":{"kind":"number","value":4598649,"string":"4,598,649"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"Kyle Shaw v. Karnes County, Texas"},"decision_date":{"kind":"string","value":"2019-03-11"},"docket_number":{"kind":"string","value":"17-50937"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before JONES, BARKSDALE, and WILLETT, Circuit Judges.\", \"parties\": \"\", \"opinions\": [{\"author\": \"DON R. WILLETT, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 17-50937 Document: 00514867808 Page: 1 Date Filed: 03/11/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n\\n No. 17-50937\\n FILED\\n March 11, 2019\\n Lyle W. Cayce\\nKYLE RAY SHAW, Clerk\\n\\n Plaintiff–Appellee,\\n\\nv.\\n\\nDWAYNE VILLANUEVA, in his Individual and Official Capacity as County\\nSheriff; ROBERT C. EBROM, JR., in his Individual and Official Capacity as\\nChief Deputy Sheriff,\\n\\n Defendants–Appellants.\\n\\n\\n Appeal from the United States District Court\\n for the Western District of Texas\\n\\n\\nBefore JONES, BARKSDALE, and WILLETT, Circuit Judges.\\nDON R. WILLETT, Circuit Judge:\\n This qualified-immunity appeal arises from a political feud in Karnes\\nCounty, Texas, ground zero for the Eagle Ford Shale oil boom. Squabbling, both\\npersonal and political, among county officials and activists led to Kyle Shaw’s\\narrest. Shaw sued, claiming that County Sheriff Dwayne Villanueva and Chief\\nDeputy Sheriff Robert Ebrom, among others, had conspired to violate his civil\\nrights.\\n The issue is simply stated: Did the district court err in denying qualified\\nimmunity to Villanueva and Ebrom? We answer yes given the bare-bones\\nnature of Shaw’s allegations. The Supreme Court is no-nonsense about\\npleading specificity requirements: “Threadbare recitals of the elements of a\\n\\f Case: 17-50937 Document: 00514867808 Page: 2 Date Filed: 03/11/2019\\n\\n\\n\\n No. 17-50937\\ncause of action, supported by mere conclusory statements, do not suffice.” 1\\nShaw complains he is entitled to relief. But Shaw’s complaint does not show it.\\n We REVERSE.\\n I\\n This legal dispute began as a political one. Kyle Shaw’s wife was elected\\nKarnes County Judge. 2 During her tenure, she voiced strong opinions about\\ncontroversial governance issues roiling the county. In response, a group of\\nsitting and former public officials and activists formed the Karnes County\\nPatriots. Their “collective mission,” Shaw asserts, “was to oust Judge\\nShaw . . . and secure the election of Sheriff Villanueva.” Then, she lost her\\nDemocratic primary and resigned.\\n A few months later, former Sheriff Bobby Mutz accused Kyle Shaw of\\nharassment. In his “Voluntary Statement,” Mutz alleged that Shaw harassed\\nhim in the pick-up line at Falls City Elementary School. Specifically, Mutz says\\nthat Shaw “roll[ed] his window down halfway,” “put his fingers in a gun,” and\\nshot at him—presumably gesticulating—several times. All while Mutz’s\\ngranddaughter was in the car.\\n Based on this, Deputy Sheriff Phillips prepared a probable-cause\\naffidavit for criminal harassment. The affidavit largely mirrored Mutz’s\\nstatement. A week later, Deputy Phillips submitted the probable-cause\\naffidavit to Justice of the Peace David Sotelo, procuring an arrest warrant for\\nShaw. Deputy Morin arrested Shaw the next week.\\n In the two weeks between Mutz’s original complaint and Shaw’s arrest,\\nno one from the Sheriff’s Department interviewed witnesses or followed up\\n\\n\\n\\n 1Ashcroft v. Iqbal, 556 U.S. 662, 678 (2009).\\n 2Often described as the chief executive officer of county government, county judges in\\nTexas wield an array of judicial and administrative powers, such as overseeing budgets and\\npresiding over commissioners courts, the county’s policymaking body.\\n 2\\n\\f Case: 17-50937 Document: 00514867808 Page: 3 Date Filed: 03/11/2019\\n\\n\\n\\n No. 17-50937\\nwith Mutz. After considering the allegations against Shaw, the Karnes County\\ngrand jury no-billed the case. The charges were dropped.\\n Shaw then brought several claims, but this appeal deals only with three:\\n§ 1985, false arrest, and conspiracy to violate § 1983. Shaw sued Karnes\\nCounty and five individual defendants:\\n • Dwayne Villanueva (Karnes County Sheriff);\\n • Robert C. Ebrom, Jr. (Karnes County Chief Deputy Sheriff);\\n • James Troy Phillips (another Karnes County Deputy Sheriff);\\n • David Morin (same); and\\n • Bobby Mutz (former Karnes County Sheriff).\\n Most Defendants moved to dismiss. 3 The magistrate judge partly agreed,\\nbelieving that Phillips and Morin were entitled to qualified immunity but not\\nVillanueva and Ebrom. The district court agreed, adopting the magistrate\\njudge’s factual findings and legal conclusions. Villanueva and Ebrom appealed,\\nasserting that qualified immunity should shield them too.\\n II\\n This appeal reaches us at the motion-to-dismiss stage. To survive a\\nmotion to dismiss, a complaint “must contain sufficient factual matter,\\naccepted as true, to ‘state a claim to relief that is plausible on its face.’” 4 In\\nreviewing, “[w]e accept all well pleaded facts as true and view them in the light\\nmost favorable to the plaintiff.” 5 But we don’t defer to the lower court’s legal\\nconclusions. Instead, a plaintiff must plead facts reasonably supporting the\\nlegal conclusions. 6\\n\\n\\n\\n\\n 3 Only Mutz, who no longer held office, did not join that motion.\\n 4 Phillips v. City of Dall., 781 F.3d 772, 775–76 (5th Cir. 2015) (quoting Iqbal, 556 U.S.\\nat 678).\\n 5 Heaney v. U.S. Veterans Admin., 756 F.2d 1215, 1217 (5th Cir. 1985).\\n 6 Gonzalez v. Kay, 577 F.3d 600, 603 (5th Cir. 2009) (quoting Iqbal, 556 U.S. at 678).\\n 3\\n\\f Case: 17-50937 Document: 00514867808 Page: 4 Date Filed: 03/11/2019\\n\\n\\n\\n No. 17-50937\\n We have interlocutory jurisdiction over qualified-immunity issues that\\nturn solely on questions of law. 7 When a defendant asserts qualified immunity,\\nthe plaintiff bears the burden of pleading facts that demonstrate liability and\\ndefeat immunity. 8 The plaintiff must show “(1) that the official violated a\\nstatutory or constitutional right, and (2) that the right was clearly established\\nat the time of the challenged conduct.” 9 And vicarious liability doesn’t apply to\\nBivens and § 1983 suits. 10 So each official must have independently violated\\nthe nonmovant’s rights. 11\\n III\\n Villanueva and Ebrom argue that since the court granted Phillips and\\nMorin qualified immunity, they should be immune too. They insist that Shaw’s\\nallegations are merely conclusory. Plus, they emphasize the magistrate’s\\nfinding that the arrest warrant wasn’t tainted.\\n In response, Shaw reiterates his allegation that Villanueva and Ebrom\\nhad him arrested purely because of their political feud with his wife. What’s\\nmore, Shaw says that Deputy Phillips added false information to the probable-\\ncause affidavit.\\n A\\n We first consider whether Villanueva and Ebrom are immune since\\nJustice of the Peace Sotelo issued an arrest warrant. Generally, if an\\nindependent intermediary, such as a justice of the peace, authorizes an arrest,\\nthen the initiating party cannot be liable for false arrest. We recently explained\\nthis in McLin: “[T]he intermediary’s decision breaks the chain of causation for\\n\\n\\n\\n 7 Iqbal, 556 U.S. at 671–72.\\n 8 Zapata v. Melson, 750 F.3d 481, 485 (5th Cir. 2014); McClendon v. City of Columbia,\\n305 F.3d 314, 323 (5th Cir. 2002) (en banc).\\n 9 Whitley v. Hanna, 726 F.3d 631, 638 (5th Cir. 2013) (cleaned up).\\n 10 Iqbal, 556 U.S. at 676.\\n 11 See id.\\n\\n 4\\n\\f Case: 17-50937 Document: 00514867808 Page: 5 Date Filed: 03/11/2019\\n\\n\\n\\n No. 17-50937\\nfalse arrest . . . .” 12 In fact, the initiating party can even be malicious. That\\nalone still won’t overcome the independent-intermediary doctrine. We held\\nthat 30-plus years ago in Hand. 13 And we reiterated it in 2016 in Buehler. 14\\nWe also elaborated in Buehler that the doctrine applies even if the arrestee\\nwas never convicted. 15\\n True, there is an exception to the doctrine. Under McLin, if the plaintiff\\nshows that the defendant tainted the intermediary’s decision-making process,\\nthe defendant can be liable. 16 But the plaintiff has to show that the defendant\\nmaliciously withheld relevant information or otherwise misdirected the\\nintermediary. 17 In McLin, the plaintiff alleged a series of collective and\\nindividual meetings, specific plots to pursue criminal charges, and various\\nflawed arrest-warrant drafts. 18\\n Here, the independent-intermediary doctrine applies, but the exception\\ndoesn’t.\\n\\n\\n\\n\\n 12 McLin v. Ard, 866 F.3d 682, 689 (5th Cir. 2017) (quoting Deville v. Marcantel, 567\\nF.3d 156, 170 (5th Cir. 2009)).\\n 13 Hand v. Gary, 838 F.2d 1420, 1427 (5th Cir. 1988) (“[E]ven an officer who acted with\\n\\nmalice in procuring the warrant . . . will not be liable if the facts supporting the warrant . . .\\nare put before an impartial intermediary such as a magistrate or a grand jury, for that\\nintermediary’s independent decision breaks the causal chain and insulates the initiating\\nparty.” (cleaned up)).\\n 14 Buehler v. City of Austin, 824 F.3d 548, 555 (5th Cir. 2016) (applying the\\n\\nindependent-intermediary doctrine where the grand jury found probable cause).\\n 15 Id. at 554 nn.4–5 (“Our precedents have applied [the independent intermediary\\n\\ndoctrine] even if the independent intermediary’s action occurred after the arrest, and even if\\nthe arrestee was never convicted of any crime.”).\\n 16 McLin, 866 F.3d at 689.\\n 17 Id.; see also Buehler, 824 F.3d at 554–55 (“An independent intermediary’s probable\\n\\ncause finding does not protect law enforcement officials whose malicious motive leads them\\nto withhold any relevant information, or otherwise misdirect the magistrate or the grand jury\\nby omission or commission.” (cleaned up)).\\n 18 Id. at 690–91.\\n\\n 5\\n\\f Case: 17-50937 Document: 00514867808 Page: 6 Date Filed: 03/11/2019\\n\\n\\n\\n No. 17-50937\\n Yes, Mutz’s statement was false. 19 Contrary to the statement, Shaw was\\nnot even at Falls City Elementary School on the date alleged. Still, that doesn’t\\nestablish that Villanueva or Ebrom knew Mutz was lying. Nor does it show\\nthat their subordinates knew Mutz was lying when they prepared the affidavit.\\nAnd Shaw fails to allege any other facts that show Villanueva or Ebrom\\nmisdirected Justice of the Peace Sotelo. Unlike in McLin, Shaw’s allegations\\ncome up short.\\n Rather, they strike us as similar to the skeletal allegations in Iqbal. 20\\nThere, Iqbal alleged that Ashcroft “knew of, condoned, and willfully and\\nmaliciously agreed to” violate Iqbal’s constitutional rights. 21 Iqbal also alleged\\nthat Ashcroft was the “principal architect” of an invidious policy of violating\\nprisoners’ constitutional rights. 22 But the Supreme Court held that, by\\nthemselves, these were simply bald allegations. 23\\n Consider also our unpublished opinion from this year in Curtis. 24 There,\\nthe plaintiff’s taint allegations failed at the motion-to-dismiss stage, the same\\nstage as here. The plaintiff never “allege[d] that the Appellees deceived the\\n[intermediary] or withheld material information from it.” 25 Instead, the\\nallegations were just bare assertions. And so we affirmed the district court’s\\ndecision to grant qualified immunity. 26\\n Shaw’s unadorned allegations are similarly conclusory. He has pleaded\\nno specific facts showing that Villanueva and Ebrom misdirected Sotelo into\\nissuing the arrest warrant. And so he has not established the exception to the\\n\\n 19 Again, we are at the motion to dismiss stage where we assume all well-pleaded facts\\nare true.\\n 20 556 U.S. 662 (2009).\\n 21 Id. at 680.\\n 22 Id.\\n 23 Id. at 681.\\n 24 Curtis v. Sowell, No. 18–20164, 2019 WL 654170 (5th Cir. Feb. 15, 2019).\\n 25 Id. at *2.\\n 26 Id. at *4.\\n\\n 6\\n\\f Case: 17-50937 Document: 00514867808 Page: 7 Date Filed: 03/11/2019\\n\\n\\n\\n No. 17-50937\\nindependent-intermediary doctrine. In other words, his allegations are all\\nbroth and no beans.\\n Finally, Shaw contends that Deputy Phillips doctored the complaint\\naffidavit because it contained two unfavorable details absent from Mutz’s\\nstatement. But that’s irrelevant here. The Supreme Court held in Iqbal that\\n“vicarious liability is inapplicable to Bivens and § 1983 suits.” 27 And thus in\\ndeciding qualified immunity for Villanueva and Ebrom, we do not concern\\nourselves with Phillips. 28 Besides, Shaw has not appealed Phillips’ qualified\\nimmunity.\\n In sum, the independent-intermediary doctrine applies, meaning\\nVillanueva and Ebrom are entitled to qualified immunity from Shaw’s false-\\narrest claim.\\n B\\n We next turn to Shaw’s claim that Villanueva and Ebrom violated 42\\nU.S.C. § 1985 and conspired to violate 42 U.S.C. § 1983.\\n For a § 1985 claim, Shaw must allege that Villanueva and Ebrom (1)\\nconspired; (2) for the purpose of depriving, either directly or indirectly, Shaw\\nof the equal protection of the laws, or of equal privileges and immunities under\\nthe laws; and (3) took or caused action in furtherance of the conspiracy; which\\n(4) injured Shaw or deprived him of his rights or privileges as a United States\\ncitizen. 29\\n Shaw’s threadbare assertions fall short of the sort of well-pleaded facts\\nthat would allow us to draw the reasonable inference that Appellants are liable\\nfor violating § 1985. As discussed above, Shaw has failed to allege facts to\\n\\n\\n 27 Iqbal, 556 U.S. at 676.\\n 28 And in any event, these allegations do not appear in Shaw’s complaint. At this stage\\nof litigation, we can only consider what is in the complaint.\\n 29 42 U.S.C. § 1985(3); Carpenters v. Scott, 463 U.S. 825, 828–29 (1983); Griffin v.\\n\\nBreckenridge, 403 U.S. 88, 102–03 (1971).\\n 7\\n\\f Case: 17-50937 Document: 00514867808 Page: 8 Date Filed: 03/11/2019\\n\\n\\n\\n No. 17-50937\\nsatisfy element four, an actual deprivation of his rights. He alleges no specific\\nfacts showing that Villanueva and Ebrom themselves acted in furtherance of a\\nconspiracy to violate his civil rights—though he has lots to say about what\\nPhillips, Morin, and other subordinates did. In short, Shaw’s complaint, read\\nin its entirety, is replete with conclusory allegations but devoid of specific facts\\n(or at least devoid of specific facts that are not inextricably bound up with legal\\nconclusions). Shaw thus cannot establish a § 1985 conspiracy claim.\\n As for his § 1983 conspiracy claim, we explained in our 1990 case\\nPfannstiel 30 that such claims are unique. The plaintiff must not only allege\\nfacts that “establish (1) the existence of a conspiracy involving state action,”\\nbut also “(2) a deprivation of civil rights in furtherance of the conspiracy by a\\nparty to the conspiracy.” 31 No deprivation, no § 1983 conspiracy. But again,\\nShaw asserts legal conclusions—that Villanueva and Ebrom deprived him of\\nhis civil rights—but no well-pleaded facts supporting those conclusions. Again,\\nnaked allegations or legal conclusions masquerading as something more will\\nnot thwart dismissal. As pleaded, Shaw’s conspiracy-to-violate-§ 1983\\nallegations, unsupported by sufficient factual content, are insufficient to state\\na plausible claim for relief.\\n IV\\n Post-Iqbal, formulaic recitations or bare-bones allegations will not\\nsurvive a motion to dismiss. Given the thinness of Shaw’s allegations,\\nVillanueva and Ebrom are entitled to qualified immunity. We REVERSE.\\n\\n\\n\\n\\n 30Pfannstiel v. City of Marion, 918 F.2d 1178, 1187 (5th Cir. 1990), abrogated on other\\ngrounds by Martin v. Thomas, 973 F.2d 449 (5th Cir. 1992).\\n 31 Id.\\n\\n 8\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4375902/\", \"author_raw\": \"DON R. WILLETT, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"JONES"},"judge2":{"kind":"string","value":"BARKSDALE"},"judge3":{"kind":"string","value":"WILLETT"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"JONES\": \", Circuit\", \"BARKSDALE\": \", Circuit\", \"WILLETT\": \", Circuit\"}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4598649/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Kyle Shaw v. Karnes County, Texas\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-11\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 17-50937 Document: 00514867808 Page: 1 Date Filed: 03/11/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\n United States Court of Appeals\n Fifth Circuit\n\n\n No. 17-50937\n FILED\n March 11, 2019\n Lyle W. Cayce\nKYLE RAY SHAW, Clerk\n\n Plaintiff–Appellee,\n\nv.\n\nDWAYNE VILLANUEVA, in his Individual and Official Capacity as County\nSheriff; ROBERT C. EBROM, JR., in his Individual and Official Capacity as\nChief Deputy Sheriff,\n\n Defendants–Appellants.\n\n\n Appeal from the United States District Court\n for the Western District of Texas\n\n\nBefore JONES, BARKSDALE, and WILLETT, Circuit Judges.\nDON R. WILLETT, Circuit Judge:\n This qualified-immunity appeal arises from a political feud in Karnes\nCounty, Texas, ground zero for the Eagle Ford Shale oil boom. Squabbling, both\npersonal and political, among county officials and activists led to Kyle Shaw’s\narrest. Shaw sued, claiming that County Sheriff Dwayne Villanueva and Chief\nDeputy Sheriff Robert Ebrom, among others, had conspired to violate his civil\nrights.\n The issue is simply stated: Did the district court err in denying qualified\nimmunity to Villanueva and Ebrom? We answer yes given the bare-bones\nnature of Shaw’s allegations. The Supreme Court is no-nonsense about\npleading specificity requirements: “Threadbare recitals of the elements of a\n\f Case: 17-50937 Document: 00514867808 Page: 2 Date Filed: 03/11/2019\n\n\n\n No. 17-50937\ncause of action, supported by mere conclusory statements, do not suffice.” 1\nShaw complains he is entitled to relief. But Shaw’s complaint does not show it.\n We REVERSE.\n I\n This legal dispute began as a political one. Kyle Shaw’s wife was elected\nKarnes County Judge. 2 During her tenure, she voiced strong opinions about\ncontroversial governance issues roiling the county. In response, a group of\nsitting and former public officials and activists formed the Karnes County\nPatriots. Their “collective mission,” Shaw asserts, “was to oust Judge\nShaw . . . and secure the election of Sheriff Villanueva.” Then, she lost her\nDemocratic primary and resigned.\n A few months later, former Sheriff Bobby Mutz accused Kyle Shaw of\nharassment. In his “Voluntary Statement,” Mutz alleged that Shaw harassed\nhim in the pick-up line at Falls City Elementary School. Specifically, Mutz says\nthat Shaw “roll[ed] his window down halfway,” “put his fingers in a gun,” and\nshot at him—presumably gesticulating—several times. All while Mutz’s\ngranddaughter was in the car.\n Based on this, Deputy Sheriff Phillips prepared a probable-cause\naffidavit for criminal harassment. The affidavit largely mirrored Mutz’s\nstatement. A week later, Deputy Phillips submitted the probable-cause\naffidavit to Justice of the Peace David Sotelo, procuring an arrest warrant for\nShaw. Deputy Morin arrested Shaw the next week.\n In the two weeks between Mutz’s original complaint and Shaw’s arrest,\nno one from the Sheriff’s Department interviewed witnesses or followed up\n\n\n\n 1Ashcroft v. Iqbal, 556 U.S. 662, 678 (2009).\n 2Often described as the chief executive officer of county government, county judges in\nTexas wield an array of judicial and administrative powers, such as overseeing budgets and\npresiding over commissioners courts, the county’s policymaking body.\n 2\n\f Case: 17-50937 Document: 00514867808 Page: 3 Date Filed: 03/11/2019\n\n\n\n No. 17-50937\nwith Mutz. After considering the allegations against Shaw, the Karnes County\ngrand jury no-billed the case. The charges were dropped.\n Shaw then brought several claims, but this appeal deals only with three:\n§ 1985, false arrest, and conspiracy to violate § 1983. Shaw sued Karnes\nCounty and five individual defendants:\n • Dwayne Villanueva (Karnes County Sheriff);\n • Robert C. Ebrom, Jr. (Karnes County Chief Deputy Sheriff);\n • James Troy Phillips (another Karnes County Deputy Sheriff);\n • David Morin (same); and\n • Bobby Mutz (former Karnes County Sheriff).\n Most Defendants moved to dismiss. 3 The magistrate judge partly agreed,\nbelieving that Phillips and Morin were entitled to qualified immunity but not\nVillanueva and Ebrom. The district court agreed, adopting the magistrate\njudge’s factual findings and legal conclusions. Villanueva and Ebrom appealed,\nasserting that qualified immunity should shield them too.\n II\n This appeal reaches us at the motion-to-dismiss stage. To survive a\nmotion to dismiss, a complaint “must contain sufficient factual matter,\naccepted as true, to ‘state a claim to relief that is plausible on its face.’” 4 In\nreviewing, “[w]e accept all well pleaded facts as true and view them in the light\nmost favorable to the plaintiff.” 5 But we don’t defer to the lower court’s legal\nconclusions. Instead, a plaintiff must plead facts reasonably supporting the\nlegal conclusions. 6\n\n\n\n\n 3 Only Mutz, who no longer held office, did not join that motion.\n 4 Phillips v. City of Dall., 781 F.3d 772, 775–76 (5th Cir. 2015) (quoting Iqbal, 556 U.S.\nat 678).\n 5 Heaney v. U.S. Veterans Admin., 756 F.2d 1215, 1217 (5th Cir. 1985).\n 6 Gonzalez v. Kay, 577 F.3d 600, 603 (5th Cir. 2009) (quoting Iqbal, 556 U.S. at 678).\n 3\n\f Case: 17-50937 Document: 00514867808 Page: 4 Date Filed: 03/11/2019\n\n\n\n No. 17-50937\n We have interlocutory jurisdiction over qualified-immunity issues that\nturn solely on questions of law. 7 When a defendant asserts qualified immunity,\nthe plaintiff bears the burden of pleading facts that demonstrate liability and\ndefeat immunity. 8 The plaintiff must show “(1) that the official violated a\nstatutory or constitutional right, and (2) that the right was clearly established\nat the time of the challenged conduct.” 9 And vicarious liability doesn’t apply to\nBivens and § 1983 suits. 10 So each official must have independently violated\nthe nonmovant’s rights. 11\n III\n Villanueva and Ebrom argue that since the court granted Phillips and\nMorin qualified immunity, they should be immune too. They insist that Shaw’s\nallegations are merely conclusory. Plus, they emphasize the magistrate’s\nfinding that the arrest warrant wasn’t tainted.\n In response, Shaw reiterates his allegation that Villanueva and Ebrom\nhad him arrested purely because of their political feud with his wife. What’s\nmore, Shaw says that Deputy Phillips added false information to the probable-\ncause affidavit.\n A\n We first consider whether Villanueva and Ebrom are immune since\nJustice of the Peace Sotelo issued an arrest warrant. Generally, if an\nindependent intermediary, such as a justice of the peace, authorizes an arrest,\nthen the initiating party cannot be liable for false arrest. We recently explained\nthis in McLin: “[T]he intermediary’s decision breaks the chain of causation for\n\n\n\n 7 Iqbal, 556 U.S. at 671–72.\n 8 Zapata v. Melson, 750 F.3d 481, 485 (5th Cir. 2014); McClendon v. City of Columbia,\n305 F.3d 314, 323 (5th Cir. 2002) (en banc).\n 9 Whitley v. Hanna, 726 F.3d 631, 638 (5th Cir. 2013) (cleaned up).\n 10 Iqbal, 556 U.S. at 676.\n 11 See id.\n\n 4\n\f Case: 17-50937 Document: 00514867808 Page: 5 Date Filed: 03/11/2019\n\n\n\n No. 17-50937\nfalse arrest . . . .” 12 In fact, the initiating party can even be malicious. That\nalone still won’t overcome the independent-intermediary doctrine. We held\nthat 30-plus years ago in Hand. 13 And we reiterated it in 2016 in Buehler. 14\nWe also elaborated in Buehler that the doctrine applies even if the arrestee\nwas never convicted. 15\n True, there is an exception to the doctrine. Under McLin, if the plaintiff\nshows that the defendant tainted the intermediary’s decision-making process,\nthe defendant can be liable. 16 But the plaintiff has to show that the defendant\nmaliciously withheld relevant information or otherwise misdirected the\nintermediary. 17 In McLin, the plaintiff alleged a series of collective and\nindividual meetings, specific plots to pursue criminal charges, and various\nflawed arrest-warrant drafts. 18\n Here, the independent-intermediary doctrine applies, but the exception\ndoesn’t.\n\n\n\n\n 12 McLin v. Ard, 866 F.3d 682, 689 (5th Cir. 2017) (quoting Deville v. Marcantel, 567\nF.3d 156, 170 (5th Cir. 2009)).\n 13 Hand v. Gary, 838 F.2d 1420, 1427 (5th Cir. 1988) (“[E]ven an officer who acted with\n\nmalice in procuring the warrant . . . will not be liable if the facts supporting the warrant . . .\nare put before an impartial intermediary such as a magistrate or a grand jury, for that\nintermediary’s independent decision breaks the causal chain and insulates the initiating\nparty.” (cleaned up)).\n 14 Buehler v. City of Austin, 824 F.3d 548, 555 (5th Cir. 2016) (applying the\n\nindependent-intermediary doctrine where the grand jury found probable cause).\n 15 Id. at 554 nn.4–5 (“Our precedents have applied [the independent intermediary\n\ndoctrine] even if the independent intermediary’s action occurred after the arrest, and even if\nthe arrestee was never convicted of any crime.”).\n 16 McLin, 866 F.3d at 689.\n 17 Id.; see also Buehler, 824 F.3d at 554–55 (“An independent intermediary’s probable\n\ncause finding does not protect law enforcement officials whose malicious motive leads them\nto withhold any relevant information, or otherwise misdirect the magistrate or the grand jury\nby omission or commission.” (cleaned up)).\n 18 Id. at 690–91.\n\n 5\n\f Case: 17-50937 Document: 00514867808 Page: 6 Date Filed: 03/11/2019\n\n\n\n No. 17-50937\n Yes, Mutz’s statement was false. 19 Contrary to the statement, Shaw was\nnot even at Falls City Elementary School on the date alleged. Still, that doesn’t\nestablish that Villanueva or Ebrom knew Mutz was lying. Nor does it show\nthat their subordinates knew Mutz was lying when they prepared the affidavit.\nAnd Shaw fails to allege any other facts that show Villanueva or Ebrom\nmisdirected Justice of the Peace Sotelo. Unlike in McLin, Shaw’s allegations\ncome up short.\n Rather, they strike us as similar to the skeletal allegations in Iqbal. 20\nThere, Iqbal alleged that Ashcroft “knew of, condoned, and willfully and\nmaliciously agreed to” violate Iqbal’s constitutional rights. 21 Iqbal also alleged\nthat Ashcroft was the “principal architect” of an invidious policy of violating\nprisoners’ constitutional rights. 22 But the Supreme Court held that, by\nthemselves, these were simply bald allegations. 23\n Consider also our unpublished opinion from this year in Curtis. 24 There,\nthe plaintiff’s taint allegations failed at the motion-to-dismiss stage, the same\nstage as here. The plaintiff never “allege[d] that the Appellees deceived the\n[intermediary] or withheld material information from it.” 25 Instead, the\nallegations were just bare assertions. And so we affirmed the district court’s\ndecision to grant qualified immunity. 26\n Shaw’s unadorned allegations are similarly conclusory. He has pleaded\nno specific facts showing that Villanueva and Ebrom misdirected Sotelo into\nissuing the arrest warrant. And so he has not established the exception to the\n\n 19 Again, we are at the motion to dismiss stage where we assume all well-pleaded facts\nare true.\n 20 556 U.S. 662 (2009).\n 21 Id. at 680.\n 22 Id.\n 23 Id. at 681.\n 24 Curtis v. Sowell, No. 18–20164, 2019 WL 654170 (5th Cir. Feb. 15, 2019).\n 25 Id. at *2.\n 26 Id. at *4.\n\n 6\n\f Case: 17-50937 Document: 00514867808 Page: 7 Date Filed: 03/11/2019\n\n\n\n No. 17-50937\nindependent-intermediary doctrine. In other words, his allegations are all\nbroth and no beans.\n Finally, Shaw contends that Deputy Phillips doctored the complaint\naffidavit because it contained two unfavorable details absent from Mutz’s\nstatement. But that’s irrelevant here. The Supreme Court held in Iqbal that\n“vicarious liability is inapplicable to Bivens and § 1983 suits.” 27 And thus in\ndeciding qualified immunity for Villanueva and Ebrom, we do not concern\nourselves with Phillips. 28 Besides, Shaw has not appealed Phillips’ qualified\nimmunity.\n In sum, the independent-intermediary doctrine applies, meaning\nVillanueva and Ebrom are entitled to qualified immunity from Shaw’s false-\narrest claim.\n B\n We next turn to Shaw’s claim that Villanueva and Ebrom violated 42\nU.S.C. § 1985 and conspired to violate 42 U.S.C. § 1983.\n For a § 1985 claim, Shaw must allege that Villanueva and Ebrom (1)\nconspired; (2) for the purpose of depriving, either directly or indirectly, Shaw\nof the equal protection of the laws, or of equal privileges and immunities under\nthe laws; and (3) took or caused action in furtherance of the conspiracy; which\n(4) injured Shaw or deprived him of his rights or privileges as a United States\ncitizen. 29\n Shaw’s threadbare assertions fall short of the sort of well-pleaded facts\nthat would allow us to draw the reasonable inference that Appellants are liable\nfor violating § 1985. As discussed above, Shaw has failed to allege facts to\n\n\n 27 Iqbal, 556 U.S. at 676.\n 28 And in any event, these allegations do not appear in Shaw’s complaint. At this stage\nof litigation, we can only consider what is in the complaint.\n 29 42 U.S.C. § 1985(3); Carpenters v. Scott, 463 U.S. 825, 828–29 (1983); Griffin v.\n\nBreckenridge, 403 U.S. 88, 102–03 (1971).\n 7\n\f Case: 17-50937 Document: 00514867808 Page: 8 Date Filed: 03/11/2019\n\n\n\n No. 17-50937\nsatisfy element four, an actual deprivation of his rights. He alleges no specific\nfacts showing that Villanueva and Ebrom themselves acted in furtherance of a\nconspiracy to violate his civil rights—though he has lots to say about what\nPhillips, Morin, and other subordinates did. In short, Shaw’s complaint, read\nin its entirety, is replete with conclusory allegations but devoid of specific facts\n(or at least devoid of specific facts that are not inextricably bound up with legal\nconclusions). Shaw thus cannot establish a § 1985 conspiracy claim.\n As for his § 1983 conspiracy claim, we explained in our 1990 case\nPfannstiel 30 that such claims are unique. The plaintiff must not only allege\nfacts that “establish (1) the existence of a conspiracy involving state action,”\nbut also “(2) a deprivation of civil rights in furtherance of the conspiracy by a\nparty to the conspiracy.” 31 No deprivation, no § 1983 conspiracy. But again,\nShaw asserts legal conclusions—that Villanueva and Ebrom deprived him of\nhis civil rights—but no well-pleaded facts supporting those conclusions. Again,\nnaked allegations or legal conclusions masquerading as something more will\nnot thwart dismissal. As pleaded, Shaw’s conspiracy-to-violate-§ 1983\nallegations, unsupported by sufficient factual content, are insufficient to state\na plausible claim for relief.\n IV\n Post-Iqbal, formulaic recitations or bare-bones allegations will not\nsurvive a motion to dismiss. Given the thinness of Shaw’s allegations,\nVillanueva and Ebrom are entitled to qualified immunity. We REVERSE.\n\n\n\n\n 30Pfannstiel v. City of Marion, 918 F.2d 1178, 1187 (5th Cir. 1990), abrogated on other\ngrounds by Martin v. Thomas, 973 F.2d 449 (5th Cir. 1992).\n 31 Id.\n\n 8\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Kyle Shaw v. Karnes County, Texas\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-11\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 17-50937 Document: 00514867808 Page: 1 Date Filed: 03/11/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n\\n No. 17-50937\\n FILED\\n March 11, 2019\\n Lyle W. Cayce\\nKYLE RAY SHAW, Clerk\\n\\n Plaintiff–Appellee,\\n\\nv.\\n\\nDWAYNE VILLANUEVA, in his Individual and Official Capacity as County\\nSheriff; ROBERT C. EBROM, JR., in his Individual and Official Capacity as\\nChief Deputy Sheriff,\\n\\n Defendants–Appellants.\\n\\n\\n Appeal from the United States District Court\\n for the Western District of Texas\\n\\n\\nBefore JONES, BARKSDALE, and WILLETT, Circuit Judges.\\nDON R. WILLETT, Circuit Judge:\\n This qualified-immunity appeal arises from a political feud in Karnes\\nCounty, Texas, ground zero for the Eagle Ford Shale oil boom. Squabbling, both\\npersonal and political, among county officials and activists led to Kyle Shaw’s\\narrest. Shaw sued, claiming that County Sheriff Dwayne Villanueva and Chief\\nDeputy Sheriff Robert Ebrom, among others, had conspired to violate his civil\\nrights.\\n The issue is simply stated: Did the district court err in denying qualified\\nimmunity to Villanueva and Ebrom? We answer yes given the bare-bones\\nnature of Shaw’s allegations. The Supreme Court is no-nonsense about\\npleading specificity requirements: “Threadbare recitals of the elements of a\\n\\f Case: 17-50937 Document: 00514867808 Page: 2 Date Filed: 03/11/2019\\n\\n\\n\\n No. 17-50937\\ncause of action, supported by mere conclusory statements, do not suffice.” 1\\nShaw complains he is entitled to relief. But Shaw’s complaint does not show it.\\n We REVERSE.\\n I\\n This legal dispute began as a political one. Kyle Shaw’s wife was elected\\nKarnes County Judge. 2 During her tenure, she voiced strong opinions about\\ncontroversial governance issues roiling the county. In response, a group of\\nsitting and former public officials and activists formed the Karnes County\\nPatriots. Their “collective mission,” Shaw asserts, “was to oust Judge\\nShaw . . . and secure the election of Sheriff Villanueva.” Then, she lost her\\nDemocratic primary and resigned.\\n A few months later, former Sheriff Bobby Mutz accused Kyle Shaw of\\nharassment. In his “Voluntary Statement,” Mutz alleged that Shaw harassed\\nhim in the pick-up line at Falls City Elementary School. Specifically, Mutz says\\nthat Shaw “roll[ed] his window down halfway,” “put his fingers in a gun,” and\\nshot at him—presumably gesticulating—several times. All while Mutz’s\\ngranddaughter was in the car.\\n Based on this, Deputy Sheriff Phillips prepared a probable-cause\\naffidavit for criminal harassment. The affidavit largely mirrored Mutz’s\\nstatement. A week later, Deputy Phillips submitted the probable-cause\\naffidavit to Justice of the Peace David Sotelo, procuring an arrest warrant for\\nShaw. Deputy Morin arrested Shaw the next week.\\n In the two weeks between Mutz’s original complaint and Shaw’s arrest,\\nno one from the Sheriff’s Department interviewed witnesses or followed up\\n\\n\\n\\n 1Ashcroft v. Iqbal, 556 U.S. 662, 678 (2009).\\n 2Often described as the chief executive officer of county government, county judges in\\nTexas wield an array of judicial and administrative powers, such as overseeing budgets and\\npresiding over commissioners courts, the county’s policymaking body.\\n 2\\n\\f Case: 17-50937 Document: 00514867808 Page: 3 Date Filed: 03/11/2019\\n\\n\\n\\n No. 17-50937\\nwith Mutz. After considering the allegations against Shaw, the Karnes County\\ngrand jury no-billed the case. The charges were dropped.\\n Shaw then brought several claims, but this appeal deals only with three:\\n§ 1985, false arrest, and conspiracy to violate § 1983. Shaw sued Karnes\\nCounty and five individual defendants:\\n • Dwayne Villanueva (Karnes County Sheriff);\\n • Robert C. Ebrom, Jr. (Karnes County Chief Deputy Sheriff);\\n • James Troy Phillips (another Karnes County Deputy Sheriff);\\n • David Morin (same); and\\n • Bobby Mutz (former Karnes County Sheriff).\\n Most Defendants moved to dismiss. 3 The magistrate judge partly agreed,\\nbelieving that Phillips and Morin were entitled to qualified immunity but not\\nVillanueva and Ebrom. The district court agreed, adopting the magistrate\\njudge’s factual findings and legal conclusions. Villanueva and Ebrom appealed,\\nasserting that qualified immunity should shield them too.\\n II\\n This appeal reaches us at the motion-to-dismiss stage. To survive a\\nmotion to dismiss, a complaint “must contain sufficient factual matter,\\naccepted as true, to ‘state a claim to relief that is plausible on its face.’” 4 In\\nreviewing, “[w]e accept all well pleaded facts as true and view them in the light\\nmost favorable to the plaintiff.” 5 But we don’t defer to the lower court’s legal\\nconclusions. Instead, a plaintiff must plead facts reasonably supporting the\\nlegal conclusions. 6\\n\\n\\n\\n\\n 3 Only Mutz, who no longer held office, did not join that motion.\\n 4 Phillips v. City of Dall., 781 F.3d 772, 775–76 (5th Cir. 2015) (quoting Iqbal, 556 U.S.\\nat 678).\\n 5 Heaney v. U.S. Veterans Admin., 756 F.2d 1215, 1217 (5th Cir. 1985).\\n 6 Gonzalez v. Kay, 577 F.3d 600, 603 (5th Cir. 2009) (quoting Iqbal, 556 U.S. at 678).\\n 3\\n\\f Case: 17-50937 Document: 00514867808 Page: 4 Date Filed: 03/11/2019\\n\\n\\n\\n No. 17-50937\\n We have interlocutory jurisdiction over qualified-immunity issues that\\nturn solely on questions of law. 7 When a defendant asserts qualified immunity,\\nthe plaintiff bears the burden of pleading facts that demonstrate liability and\\ndefeat immunity. 8 The plaintiff must show “(1) that the official violated a\\nstatutory or constitutional right, and (2) that the right was clearly established\\nat the time of the challenged conduct.” 9 And vicarious liability doesn’t apply to\\nBivens and § 1983 suits. 10 So each official must have independently violated\\nthe nonmovant’s rights. 11\\n III\\n Villanueva and Ebrom argue that since the court granted Phillips and\\nMorin qualified immunity, they should be immune too. They insist that Shaw’s\\nallegations are merely conclusory. Plus, they emphasize the magistrate’s\\nfinding that the arrest warrant wasn’t tainted.\\n In response, Shaw reiterates his allegation that Villanueva and Ebrom\\nhad him arrested purely because of their political feud with his wife. What’s\\nmore, Shaw says that Deputy Phillips added false information to the probable-\\ncause affidavit.\\n A\\n We first consider whether Villanueva and Ebrom are immune since\\nJustice of the Peace Sotelo issued an arrest warrant. Generally, if an\\nindependent intermediary, such as a justice of the peace, authorizes an arrest,\\nthen the initiating party cannot be liable for false arrest. We recently explained\\nthis in McLin: “[T]he intermediary’s decision breaks the chain of causation for\\n\\n\\n\\n 7 Iqbal, 556 U.S. at 671–72.\\n 8 Zapata v. Melson, 750 F.3d 481, 485 (5th Cir. 2014); McClendon v. City of Columbia,\\n305 F.3d 314, 323 (5th Cir. 2002) (en banc).\\n 9 Whitley v. Hanna, 726 F.3d 631, 638 (5th Cir. 2013) (cleaned up).\\n 10 Iqbal, 556 U.S. at 676.\\n 11 See id.\\n\\n 4\\n\\f Case: 17-50937 Document: 00514867808 Page: 5 Date Filed: 03/11/2019\\n\\n\\n\\n No. 17-50937\\nfalse arrest . . . .” 12 In fact, the initiating party can even be malicious. That\\nalone still won’t overcome the independent-intermediary doctrine. We held\\nthat 30-plus years ago in Hand. 13 And we reiterated it in 2016 in Buehler. 14\\nWe also elaborated in Buehler that the doctrine applies even if the arrestee\\nwas never convicted. 15\\n True, there is an exception to the doctrine. Under McLin, if the plaintiff\\nshows that the defendant tainted the intermediary’s decision-making process,\\nthe defendant can be liable. 16 But the plaintiff has to show that the defendant\\nmaliciously withheld relevant information or otherwise misdirected the\\nintermediary. 17 In McLin, the plaintiff alleged a series of collective and\\nindividual meetings, specific plots to pursue criminal charges, and various\\nflawed arrest-warrant drafts. 18\\n Here, the independent-intermediary doctrine applies, but the exception\\ndoesn’t.\\n\\n\\n\\n\\n 12 McLin v. Ard, 866 F.3d 682, 689 (5th Cir. 2017) (quoting Deville v. Marcantel, 567\\nF.3d 156, 170 (5th Cir. 2009)).\\n 13 Hand v. Gary, 838 F.2d 1420, 1427 (5th Cir. 1988) (“[E]ven an officer who acted with\\n\\nmalice in procuring the warrant . . . will not be liable if the facts supporting the warrant . . .\\nare put before an impartial intermediary such as a magistrate or a grand jury, for that\\nintermediary’s independent decision breaks the causal chain and insulates the initiating\\nparty.” (cleaned up)).\\n 14 Buehler v. City of Austin, 824 F.3d 548, 555 (5th Cir. 2016) (applying the\\n\\nindependent-intermediary doctrine where the grand jury found probable cause).\\n 15 Id. at 554 nn.4–5 (“Our precedents have applied [the independent intermediary\\n\\ndoctrine] even if the independent intermediary’s action occurred after the arrest, and even if\\nthe arrestee was never convicted of any crime.”).\\n 16 McLin, 866 F.3d at 689.\\n 17 Id.; see also Buehler, 824 F.3d at 554–55 (“An independent intermediary’s probable\\n\\ncause finding does not protect law enforcement officials whose malicious motive leads them\\nto withhold any relevant information, or otherwise misdirect the magistrate or the grand jury\\nby omission or commission.” (cleaned up)).\\n 18 Id. at 690–91.\\n\\n 5\\n\\f Case: 17-50937 Document: 00514867808 Page: 6 Date Filed: 03/11/2019\\n\\n\\n\\n No. 17-50937\\n Yes, Mutz’s statement was false. 19 Contrary to the statement, Shaw was\\nnot even at Falls City Elementary School on the date alleged. Still, that doesn’t\\nestablish that Villanueva or Ebrom knew Mutz was lying. Nor does it show\\nthat their subordinates knew Mutz was lying when they prepared the affidavit.\\nAnd Shaw fails to allege any other facts that show Villanueva or Ebrom\\nmisdirected Justice of the Peace Sotelo. Unlike in McLin, Shaw’s allegations\\ncome up short.\\n Rather, they strike us as similar to the skeletal allegations in Iqbal. 20\\nThere, Iqbal alleged that Ashcroft “knew of, condoned, and willfully and\\nmaliciously agreed to” violate Iqbal’s constitutional rights. 21 Iqbal also alleged\\nthat Ashcroft was the “principal architect” of an invidious policy of violating\\nprisoners’ constitutional rights. 22 But the Supreme Court held that, by\\nthemselves, these were simply bald allegations. 23\\n Consider also our unpublished opinion from this year in Curtis. 24 There,\\nthe plaintiff’s taint allegations failed at the motion-to-dismiss stage, the same\\nstage as here. The plaintiff never “allege[d] that the Appellees deceived the\\n[intermediary] or withheld material information from it.” 25 Instead, the\\nallegations were just bare assertions. And so we affirmed the district court’s\\ndecision to grant qualified immunity. 26\\n Shaw’s unadorned allegations are similarly conclusory. He has pleaded\\nno specific facts showing that Villanueva and Ebrom misdirected Sotelo into\\nissuing the arrest warrant. And so he has not established the exception to the\\n\\n 19 Again, we are at the motion to dismiss stage where we assume all well-pleaded facts\\nare true.\\n 20 556 U.S. 662 (2009).\\n 21 Id. at 680.\\n 22 Id.\\n 23 Id. at 681.\\n 24 Curtis v. Sowell, No. 18–20164, 2019 WL 654170 (5th Cir. Feb. 15, 2019).\\n 25 Id. at *2.\\n 26 Id. at *4.\\n\\n 6\\n\\f Case: 17-50937 Document: 00514867808 Page: 7 Date Filed: 03/11/2019\\n\\n\\n\\n No. 17-50937\\nindependent-intermediary doctrine. In other words, his allegations are all\\nbroth and no beans.\\n Finally, Shaw contends that Deputy Phillips doctored the complaint\\naffidavit because it contained two unfavorable details absent from Mutz’s\\nstatement. But that’s irrelevant here. The Supreme Court held in Iqbal that\\n“vicarious liability is inapplicable to Bivens and § 1983 suits.” 27 And thus in\\ndeciding qualified immunity for Villanueva and Ebrom, we do not concern\\nourselves with Phillips. 28 Besides, Shaw has not appealed Phillips’ qualified\\nimmunity.\\n In sum, the independent-intermediary doctrine applies, meaning\\nVillanueva and Ebrom are entitled to qualified immunity from Shaw’s false-\\narrest claim.\\n B\\n We next turn to Shaw’s claim that Villanueva and Ebrom violated 42\\nU.S.C. § 1985 and conspired to violate 42 U.S.C. § 1983.\\n For a § 1985 claim, Shaw must allege that Villanueva and Ebrom (1)\\nconspired; (2) for the purpose of depriving, either directly or indirectly, Shaw\\nof the equal protection of the laws, or of equal privileges and immunities under\\nthe laws; and (3) took or caused action in furtherance of the conspiracy; which\\n(4) injured Shaw or deprived him of his rights or privileges as a United States\\ncitizen. 29\\n Shaw’s threadbare assertions fall short of the sort of well-pleaded facts\\nthat would allow us to draw the reasonable inference that Appellants are liable\\nfor violating § 1985. As discussed above, Shaw has failed to allege facts to\\n\\n\\n 27 Iqbal, 556 U.S. at 676.\\n 28 And in any event, these allegations do not appear in Shaw’s complaint. At this stage\\nof litigation, we can only consider what is in the complaint.\\n 29 42 U.S.C. § 1985(3); Carpenters v. Scott, 463 U.S. 825, 828–29 (1983); Griffin v.\\n\\nBreckenridge, 403 U.S. 88, 102–03 (1971).\\n 7\\n\\f Case: 17-50937 Document: 00514867808 Page: 8 Date Filed: 03/11/2019\\n\\n\\n\\n No. 17-50937\\nsatisfy element four, an actual deprivation of his rights. He alleges no specific\\nfacts showing that Villanueva and Ebrom themselves acted in furtherance of a\\nconspiracy to violate his civil rights—though he has lots to say about what\\nPhillips, Morin, and other subordinates did. In short, Shaw’s complaint, read\\nin its entirety, is replete with conclusory allegations but devoid of specific facts\\n(or at least devoid of specific facts that are not inextricably bound up with legal\\nconclusions). Shaw thus cannot establish a § 1985 conspiracy claim.\\n As for his § 1983 conspiracy claim, we explained in our 1990 case\\nPfannstiel 30 that such claims are unique. The plaintiff must not only allege\\nfacts that “establish (1) the existence of a conspiracy involving state action,”\\nbut also “(2) a deprivation of civil rights in furtherance of the conspiracy by a\\nparty to the conspiracy.” 31 No deprivation, no § 1983 conspiracy. But again,\\nShaw asserts legal conclusions—that Villanueva and Ebrom deprived him of\\nhis civil rights—but no well-pleaded facts supporting those conclusions. Again,\\nnaked allegations or legal conclusions masquerading as something more will\\nnot thwart dismissal. As pleaded, Shaw’s conspiracy-to-violate-§ 1983\\nallegations, unsupported by sufficient factual content, are insufficient to state\\na plausible claim for relief.\\n IV\\n Post-Iqbal, formulaic recitations or bare-bones allegations will not\\nsurvive a motion to dismiss. Given the thinness of Shaw’s allegations,\\nVillanueva and Ebrom are entitled to qualified immunity. We REVERSE.\\n\\n\\n\\n\\n 30Pfannstiel v. City of Marion, 918 F.2d 1178, 1187 (5th Cir. 1990), abrogated on other\\ngrounds by Martin v. Thomas, 973 F.2d 449 (5th Cir. 1992).\\n 31 Id.\\n\\n 8\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1083,"cells":{"id":{"kind":"number","value":4598650,"string":"4,598,650"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"Glenn Ford v. District Attorney Caddo Parish, et a"},"decision_date":{"kind":"string","value":"2019-03-11"},"docket_number":{"kind":"string","value":"18-30126"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before SMITH, DUNCAN, and ENGELHARDT, Circuit Judges.\", \"parties\": \"\", \"opinions\": [{\"author\": \"KURT D. ENGELHARDT, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 18-30126 Document: 00514867978 Page: 1 Date Filed: 03/11/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n No. 18-30126 March 11, 2019\\n Lyle W. Cayce\\nANDREA ARMSTRONG, Executrix of the Estate of Glen Ford, Clerk\\n\\n\\n Plaintiff–Appellee\\n\\nv.\\n\\nDON ASHLEY; GARY ALDERMAN; GARY PITTMAN; EVERETT T.\\nRUSHING; BILLY LOCKWOOD, wrongly identified as Estate of Billy\\nLockwood; FRANK DATCHER; GLYNN MITCHELL; RODNEY PRICE,\\n\\n Defendants–Appellants\\n\\n\\n\\n Appeal from the United States District Court\\n for the Western District of Louisiana\\n\\n\\nBefore SMITH, DUNCAN, and ENGELHARDT, Circuit Judges.\\nKURT D. ENGELHARDT, Circuit Judge:\\n Glenn Ford was wrongly convicted of murder and spent 30 years in\\nsolitary confinement on death row before being fully exonerated, with all\\ncharges dropped. Ford sued the Defendants-Appellants 1 (as well as other\\ndefendants not included in this appeal), all of whom were law enforcement\\nofficials at the time of Ford’s wrongful conviction, alleging suppression of\\n\\n\\n\\n\\n 1Don Ashley, Gary Alderman, Gary Pittman, Everett T. Rushing, Billy Lockwood,\\nFrank Datcher, Glynn Mitchell, and Rodney Price.\\n\\f Case: 18-30126 Document: 00514867978 Page: 2 Date Filed: 03/11/2019\\n\\n\\n No. 18-30126\\n\\nevidence, fabrication of witness statements, withholding of exculpatory\\nevidence, and other violations.\\n Ford filed suit in March 2015. The operative First Amended Complaint\\nwas filed on September 8, 2015. Appellants answered the complaint on\\nDecember 3, 2015, while other defendants in the initial lawsuit chose to\\ninstead move to dismiss under Federal Rule of Civil Procedure 12(b).\\nApproximately three months later, on March 16, 2016, the Appellants filed a\\nRule 12(b)(6) motion to dismiss the case for failure to state a claim.\\nAlternatively, they moved for the Appellee to add details to the allegations\\npursuant to Federal Rule of Civil Procedure 7(a).\\n The district court denied the Rule 12(b)(6) motion for being untimely on\\nDecember 28, 2017. 2 The court also denied the alternative relief under Rule\\n7(a). The Appellants appealed the dismissal of the Rule 12(b)(6) motion on\\nJanuary 23, 2018.\\n I.\\n The first, and determinative, issue is that of appellate jurisdiction. The\\ncase comes before this court on interlocutory appeal. In deference to the district\\ncourt and to district judges’ responsibility to manage trials, interlocutory\\nappeals are only allowed in limited circumstances because they disrupt the\\nprogress of a trial. Johnson v. Jones, 515 U.S. 304, 309 (1995). Therefore,\\n“interlocutory appeals–appeals before the end of district court proceedings–are\\nthe exception, not the rule.” Id.\\n “[A] decision . . . is appealable if it falls within ‘that small class which\\nfinally determine claims of right separable from, and collateral to, rights\\nasserted in the action, too important to be denied review and too independent\\n\\n\\n\\n 2 In contrast, the district court ruled on the merits for the Rule 12(b)(6) motions filed\\nin a timely manner by the other defendants.\\n 2\\n\\f Case: 18-30126 Document: 00514867978 Page: 3 Date Filed: 03/11/2019\\n\\n\\n No. 18-30126\\n\\nof the cause itself to require that appellate consideration be deferred until the\\nwhole case is adjudicated.’” Mitchell v. Forsyth, 472 U.S. 511, 524–25 (1985)\\n(quoting Cohen v. Beneficial Indus. Loan Corp., 337 U.S. 541, 546 (1949)).\\nAccordingly, Mitchell held that “a district court’s denial of a claim of qualified\\nimmunity, to the extent that it turns on an issue of law, is an appealable ‘final\\ndecision’ within the meaning of 28 U.S.C. § 1291 notwithstanding the absence\\nof a final judgment.” Id. at 530 (emphasis added). For a decision to be\\nconsidered final, and therefore appealable, it must fulfill three conditions laid\\nout in Mitchell. Id. at 527. First, it must be “effectively unreviewable on appeal\\nfrom a final judgment.” Id. Second, it must “conclusively determine the\\ndisputed question.” Id. (citation omitted). Finally, the question at issue must\\nbe a “clai[m] of right separable from, and collateral to, rights asserted in the\\naction.” Id. (alteration in original) (citation omitted). The appellate court does\\nnot have jurisdiction to evaluate factual disputes. Winfrey v. Pikett, 872 F.3d\\n640, 643–44 (5th Cir. 2017).\\n A decision on qualified immunity can be an appealable final decision,\\n“but only to the extent that the appeal concerns the purely legal question\\nwhether the defendants are entitled to qualified immunity on the facts[.]”\\nKinney v. Weaver, 367 F.3d 337, 347 (5th Cir. 2004) (en banc). Typically, this\\ndetermination is a decision on “whether the federal right allegedly infringed\\nwas clearly established.” Behrens v. Pelletier, 516 U.S. 299, 313 (1996) (internal\\nquotation omitted). If the district court declined to rule on qualified immunity\\nwhen it was so obligated, that may also be considered an appealable final\\ndecision. See Helton v. Clements, 787 F.2d 1016, 1017 (5th Cir. 1986). However,\\n“where the district court refuses to rule on a claim of immunity because it has\\nnot been timely presented to the court, Mitchell does not provide for appellate\\njurisdiction.” Hernandez v. Brazoria Cty., No. 93-2525, 1994 WL 171620, at *2\\n\\n\\n 3\\n\\f Case: 18-30126 Document: 00514867978 Page: 4 Date Filed: 03/11/2019\\n\\n\\n No. 18-30126\\n\\n(5th Cir. Apr. 26, 1994) (per curiam) (unpublished but precedential); see also\\nEdwards v. Cass Cty., Tex., 919 F.2d 273, 275 (5th Cir. 1990).\\n II.\\n The Appellants filed a Rule 12(b)(6) motion to dismiss that included an\\nassertion of qualified immunity. The Appellants argue that in denying the Rule\\n12(b)(6) motion, the district court made an appealable final legal decision on\\nqualified immunity. The Appellants base this argument on a statement made\\nby the district court regarding a possible alternative argument that the\\ndefendants did not raise in their motion – that the Rule 12(b)(6) motion should\\ninstead be considered a Rule 12(c) motion. 3 The district court, in declining to\\nconsider the motion under Rule 12(c), stated that “there are material facts in\\ndispute and at this stage of the litigation, the Law Enforcement Defendants\\nare not entitled to a judgment as a matter of law.” Based on this statement,\\nthe Appellants aver that the district court essentially made a final legal\\ndetermination that the Appellants were not entitled to qualified immunity.\\nThis final legal determination must be appealable, Appellants maintain,\\nbecause the purpose of qualified immunity is to protect the officers from trial,\\nnot only from liability. Mitchell, 472 U.S. 511, 526-27.\\n However, the district court specifically stated that it was making the\\ndecision on procedural grounds, rather than legal grounds: “Accordingly, the\\nLaw Enforcement Defendants’ Rule 12(b)(6) Motion to Dismiss is DENIED as\\nuntimely.” The decision therefore is not based on a legal evaluation of the\\nAppellants’ entitlement to qualified immunity. We take the district court at its\\nword and decline to hold that the district court inadvertently made a final legal\\ndetermination as to whether the Appellants are entitled to qualified immunity.\\n\\n\\n 3 District courts may consider untimely Rule 12(b)(6) motions as Rule 12(c) motions\\n(indeed they are sometimes encouraged to do so). See Delhomme v. Caremark Rx Inc., 232\\nF.R.D. 573, 576 n.2 (N.D. Tex. 2005).\\n 4\\n\\f Case: 18-30126 Document: 00514867978 Page: 5 Date Filed: 03/11/2019\\n\\n\\n No. 18-30126\\n\\nAccordingly, we note that nothing in the district court’s order bars the\\nAppellants from asserting qualified immunity by appropriate, timely\\nprocedural vehicle in the future. See Kiser v. Garrett, 67 F.3d 1166, 1169 (5th\\nCir. 1995) (“It would be anomalous to conclude that a defendant waives a\\nqualified immunity defense by dismissing as moot an interlocutory appeal that\\nthe defendant was not required to take in the first place.”).\\n III.\\n Because the district court’s decision on the Rule 12(b)(6) motion was\\nbased on timing rather than a substantive legal disposition regarding qualified\\nimmunity, this court does not have jurisdiction to consider the appeal at this\\ntime. Therefore, we do not find it necessary to consider the alternative\\narguments presented by the Appellants. We DISMISS this appeal for lack of\\nappellate jurisdiction.\\n\\n\\n\\n\\n 5\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4375903/\", \"author_raw\": \"KURT D. ENGELHARDT, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"SMITH"},"judge2":{"kind":"string","value":"DUNCAN"},"judge3":{"kind":"string","value":"ENGELHARDT"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"SMITH\": \", Circuit\", \"DUNCAN\": \", Circuit\", \"ENGELHARDT\": \", Circuit\"}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4598650/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Glenn Ford v. District Attorney Caddo Parish, et a\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-11\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 18-30126 Document: 00514867978 Page: 1 Date Filed: 03/11/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\n United States Court of Appeals\n Fifth Circuit\n\n FILED\n No. 18-30126 March 11, 2019\n Lyle W. Cayce\nANDREA ARMSTRONG, Executrix of the Estate of Glen Ford, Clerk\n\n\n Plaintiff–Appellee\n\nv.\n\nDON ASHLEY; GARY ALDERMAN; GARY PITTMAN; EVERETT T.\nRUSHING; BILLY LOCKWOOD, wrongly identified as Estate of Billy\nLockwood; FRANK DATCHER; GLYNN MITCHELL; RODNEY PRICE,\n\n Defendants–Appellants\n\n\n\n Appeal from the United States District Court\n for the Western District of Louisiana\n\n\nBefore SMITH, DUNCAN, and ENGELHARDT, Circuit Judges.\nKURT D. ENGELHARDT, Circuit Judge:\n Glenn Ford was wrongly convicted of murder and spent 30 years in\nsolitary confinement on death row before being fully exonerated, with all\ncharges dropped. Ford sued the Defendants-Appellants 1 (as well as other\ndefendants not included in this appeal), all of whom were law enforcement\nofficials at the time of Ford’s wrongful conviction, alleging suppression of\n\n\n\n\n 1Don Ashley, Gary Alderman, Gary Pittman, Everett T. Rushing, Billy Lockwood,\nFrank Datcher, Glynn Mitchell, and Rodney Price.\n\f Case: 18-30126 Document: 00514867978 Page: 2 Date Filed: 03/11/2019\n\n\n No. 18-30126\n\nevidence, fabrication of witness statements, withholding of exculpatory\nevidence, and other violations.\n Ford filed suit in March 2015. The operative First Amended Complaint\nwas filed on September 8, 2015. Appellants answered the complaint on\nDecember 3, 2015, while other defendants in the initial lawsuit chose to\ninstead move to dismiss under Federal Rule of Civil Procedure 12(b).\nApproximately three months later, on March 16, 2016, the Appellants filed a\nRule 12(b)(6) motion to dismiss the case for failure to state a claim.\nAlternatively, they moved for the Appellee to add details to the allegations\npursuant to Federal Rule of Civil Procedure 7(a).\n The district court denied the Rule 12(b)(6) motion for being untimely on\nDecember 28, 2017. 2 The court also denied the alternative relief under Rule\n7(a). The Appellants appealed the dismissal of the Rule 12(b)(6) motion on\nJanuary 23, 2018.\n I.\n The first, and determinative, issue is that of appellate jurisdiction. The\ncase comes before this court on interlocutory appeal. In deference to the district\ncourt and to district judges’ responsibility to manage trials, interlocutory\nappeals are only allowed in limited circumstances because they disrupt the\nprogress of a trial. Johnson v. Jones, 515 U.S. 304, 309 (1995). Therefore,\n“interlocutory appeals–appeals before the end of district court proceedings–are\nthe exception, not the rule.” Id.\n “[A] decision . . . is appealable if it falls within ‘that small class which\nfinally determine claims of right separable from, and collateral to, rights\nasserted in the action, too important to be denied review and too independent\n\n\n\n 2 In contrast, the district court ruled on the merits for the Rule 12(b)(6) motions filed\nin a timely manner by the other defendants.\n 2\n\f Case: 18-30126 Document: 00514867978 Page: 3 Date Filed: 03/11/2019\n\n\n No. 18-30126\n\nof the cause itself to require that appellate consideration be deferred until the\nwhole case is adjudicated.’” Mitchell v. Forsyth, 472 U.S. 511, 524–25 (1985)\n(quoting Cohen v. Beneficial Indus. Loan Corp., 337 U.S. 541, 546 (1949)).\nAccordingly, Mitchell held that “a district court’s denial of a claim of qualified\nimmunity, to the extent that it turns on an issue of law, is an appealable ‘final\ndecision’ within the meaning of 28 U.S.C. § 1291 notwithstanding the absence\nof a final judgment.” Id. at 530 (emphasis added). For a decision to be\nconsidered final, and therefore appealable, it must fulfill three conditions laid\nout in Mitchell. Id. at 527. First, it must be “effectively unreviewable on appeal\nfrom a final judgment.” Id. Second, it must “conclusively determine the\ndisputed question.” Id. (citation omitted). Finally, the question at issue must\nbe a “clai[m] of right separable from, and collateral to, rights asserted in the\naction.” Id. (alteration in original) (citation omitted). The appellate court does\nnot have jurisdiction to evaluate factual disputes. Winfrey v. Pikett, 872 F.3d\n640, 643–44 (5th Cir. 2017).\n A decision on qualified immunity can be an appealable final decision,\n“but only to the extent that the appeal concerns the purely legal question\nwhether the defendants are entitled to qualified immunity on the facts[.]”\nKinney v. Weaver, 367 F.3d 337, 347 (5th Cir. 2004) (en banc). Typically, this\ndetermination is a decision on “whether the federal right allegedly infringed\nwas clearly established.” Behrens v. Pelletier, 516 U.S. 299, 313 (1996) (internal\nquotation omitted). If the district court declined to rule on qualified immunity\nwhen it was so obligated, that may also be considered an appealable final\ndecision. See Helton v. Clements, 787 F.2d 1016, 1017 (5th Cir. 1986). However,\n“where the district court refuses to rule on a claim of immunity because it has\nnot been timely presented to the court, Mitchell does not provide for appellate\njurisdiction.” Hernandez v. Brazoria Cty., No. 93-2525, 1994 WL 171620, at *2\n\n\n 3\n\f Case: 18-30126 Document: 00514867978 Page: 4 Date Filed: 03/11/2019\n\n\n No. 18-30126\n\n(5th Cir. Apr. 26, 1994) (per curiam) (unpublished but precedential); see also\nEdwards v. Cass Cty., Tex., 919 F.2d 273, 275 (5th Cir. 1990).\n II.\n The Appellants filed a Rule 12(b)(6) motion to dismiss that included an\nassertion of qualified immunity. The Appellants argue that in denying the Rule\n12(b)(6) motion, the district court made an appealable final legal decision on\nqualified immunity. The Appellants base this argument on a statement made\nby the district court regarding a possible alternative argument that the\ndefendants did not raise in their motion – that the Rule 12(b)(6) motion should\ninstead be considered a Rule 12(c) motion. 3 The district court, in declining to\nconsider the motion under Rule 12(c), stated that “there are material facts in\ndispute and at this stage of the litigation, the Law Enforcement Defendants\nare not entitled to a judgment as a matter of law.” Based on this statement,\nthe Appellants aver that the district court essentially made a final legal\ndetermination that the Appellants were not entitled to qualified immunity.\nThis final legal determination must be appealable, Appellants maintain,\nbecause the purpose of qualified immunity is to protect the officers from trial,\nnot only from liability. Mitchell, 472 U.S. 511, 526-27.\n However, the district court specifically stated that it was making the\ndecision on procedural grounds, rather than legal grounds: “Accordingly, the\nLaw Enforcement Defendants’ Rule 12(b)(6) Motion to Dismiss is DENIED as\nuntimely.” The decision therefore is not based on a legal evaluation of the\nAppellants’ entitlement to qualified immunity. We take the district court at its\nword and decline to hold that the district court inadvertently made a final legal\ndetermination as to whether the Appellants are entitled to qualified immunity.\n\n\n 3 District courts may consider untimely Rule 12(b)(6) motions as Rule 12(c) motions\n(indeed they are sometimes encouraged to do so). See Delhomme v. Caremark Rx Inc., 232\nF.R.D. 573, 576 n.2 (N.D. Tex. 2005).\n 4\n\f Case: 18-30126 Document: 00514867978 Page: 5 Date Filed: 03/11/2019\n\n\n No. 18-30126\n\nAccordingly, we note that nothing in the district court’s order bars the\nAppellants from asserting qualified immunity by appropriate, timely\nprocedural vehicle in the future. See Kiser v. Garrett, 67 F.3d 1166, 1169 (5th\nCir. 1995) (“It would be anomalous to conclude that a defendant waives a\nqualified immunity defense by dismissing as moot an interlocutory appeal that\nthe defendant was not required to take in the first place.”).\n III.\n Because the district court’s decision on the Rule 12(b)(6) motion was\nbased on timing rather than a substantive legal disposition regarding qualified\nimmunity, this court does not have jurisdiction to consider the appeal at this\ntime. Therefore, we do not find it necessary to consider the alternative\narguments presented by the Appellants. We DISMISS this appeal for lack of\nappellate jurisdiction.\n\n\n\n\n 5\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Glenn Ford v. District Attorney Caddo Parish, et a\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-11\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 18-30126 Document: 00514867978 Page: 1 Date Filed: 03/11/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n No. 18-30126 March 11, 2019\\n Lyle W. Cayce\\nANDREA ARMSTRONG, Executrix of the Estate of Glen Ford, Clerk\\n\\n\\n Plaintiff–Appellee\\n\\nv.\\n\\nDON ASHLEY; GARY ALDERMAN; GARY PITTMAN; EVERETT T.\\nRUSHING; BILLY LOCKWOOD, wrongly identified as Estate of Billy\\nLockwood; FRANK DATCHER; GLYNN MITCHELL; RODNEY PRICE,\\n\\n Defendants–Appellants\\n\\n\\n\\n Appeal from the United States District Court\\n for the Western District of Louisiana\\n\\n\\nBefore SMITH, DUNCAN, and ENGELHARDT, Circuit Judges.\\nKURT D. ENGELHARDT, Circuit Judge:\\n Glenn Ford was wrongly convicted of murder and spent 30 years in\\nsolitary confinement on death row before being fully exonerated, with all\\ncharges dropped. Ford sued the Defendants-Appellants 1 (as well as other\\ndefendants not included in this appeal), all of whom were law enforcement\\nofficials at the time of Ford’s wrongful conviction, alleging suppression of\\n\\n\\n\\n\\n 1Don Ashley, Gary Alderman, Gary Pittman, Everett T. Rushing, Billy Lockwood,\\nFrank Datcher, Glynn Mitchell, and Rodney Price.\\n\\f Case: 18-30126 Document: 00514867978 Page: 2 Date Filed: 03/11/2019\\n\\n\\n No. 18-30126\\n\\nevidence, fabrication of witness statements, withholding of exculpatory\\nevidence, and other violations.\\n Ford filed suit in March 2015. The operative First Amended Complaint\\nwas filed on September 8, 2015. Appellants answered the complaint on\\nDecember 3, 2015, while other defendants in the initial lawsuit chose to\\ninstead move to dismiss under Federal Rule of Civil Procedure 12(b).\\nApproximately three months later, on March 16, 2016, the Appellants filed a\\nRule 12(b)(6) motion to dismiss the case for failure to state a claim.\\nAlternatively, they moved for the Appellee to add details to the allegations\\npursuant to Federal Rule of Civil Procedure 7(a).\\n The district court denied the Rule 12(b)(6) motion for being untimely on\\nDecember 28, 2017. 2 The court also denied the alternative relief under Rule\\n7(a). The Appellants appealed the dismissal of the Rule 12(b)(6) motion on\\nJanuary 23, 2018.\\n I.\\n The first, and determinative, issue is that of appellate jurisdiction. The\\ncase comes before this court on interlocutory appeal. In deference to the district\\ncourt and to district judges’ responsibility to manage trials, interlocutory\\nappeals are only allowed in limited circumstances because they disrupt the\\nprogress of a trial. Johnson v. Jones, 515 U.S. 304, 309 (1995). Therefore,\\n“interlocutory appeals–appeals before the end of district court proceedings–are\\nthe exception, not the rule.” Id.\\n “[A] decision . . . is appealable if it falls within ‘that small class which\\nfinally determine claims of right separable from, and collateral to, rights\\nasserted in the action, too important to be denied review and too independent\\n\\n\\n\\n 2 In contrast, the district court ruled on the merits for the Rule 12(b)(6) motions filed\\nin a timely manner by the other defendants.\\n 2\\n\\f Case: 18-30126 Document: 00514867978 Page: 3 Date Filed: 03/11/2019\\n\\n\\n No. 18-30126\\n\\nof the cause itself to require that appellate consideration be deferred until the\\nwhole case is adjudicated.’” Mitchell v. Forsyth, 472 U.S. 511, 524–25 (1985)\\n(quoting Cohen v. Beneficial Indus. Loan Corp., 337 U.S. 541, 546 (1949)).\\nAccordingly, Mitchell held that “a district court’s denial of a claim of qualified\\nimmunity, to the extent that it turns on an issue of law, is an appealable ‘final\\ndecision’ within the meaning of 28 U.S.C. § 1291 notwithstanding the absence\\nof a final judgment.” Id. at 530 (emphasis added). For a decision to be\\nconsidered final, and therefore appealable, it must fulfill three conditions laid\\nout in Mitchell. Id. at 527. First, it must be “effectively unreviewable on appeal\\nfrom a final judgment.” Id. Second, it must “conclusively determine the\\ndisputed question.” Id. (citation omitted). Finally, the question at issue must\\nbe a “clai[m] of right separable from, and collateral to, rights asserted in the\\naction.” Id. (alteration in original) (citation omitted). The appellate court does\\nnot have jurisdiction to evaluate factual disputes. Winfrey v. Pikett, 872 F.3d\\n640, 643–44 (5th Cir. 2017).\\n A decision on qualified immunity can be an appealable final decision,\\n“but only to the extent that the appeal concerns the purely legal question\\nwhether the defendants are entitled to qualified immunity on the facts[.]”\\nKinney v. Weaver, 367 F.3d 337, 347 (5th Cir. 2004) (en banc). Typically, this\\ndetermination is a decision on “whether the federal right allegedly infringed\\nwas clearly established.” Behrens v. Pelletier, 516 U.S. 299, 313 (1996) (internal\\nquotation omitted). If the district court declined to rule on qualified immunity\\nwhen it was so obligated, that may also be considered an appealable final\\ndecision. See Helton v. Clements, 787 F.2d 1016, 1017 (5th Cir. 1986). However,\\n“where the district court refuses to rule on a claim of immunity because it has\\nnot been timely presented to the court, Mitchell does not provide for appellate\\njurisdiction.” Hernandez v. Brazoria Cty., No. 93-2525, 1994 WL 171620, at *2\\n\\n\\n 3\\n\\f Case: 18-30126 Document: 00514867978 Page: 4 Date Filed: 03/11/2019\\n\\n\\n No. 18-30126\\n\\n(5th Cir. Apr. 26, 1994) (per curiam) (unpublished but precedential); see also\\nEdwards v. Cass Cty., Tex., 919 F.2d 273, 275 (5th Cir. 1990).\\n II.\\n The Appellants filed a Rule 12(b)(6) motion to dismiss that included an\\nassertion of qualified immunity. The Appellants argue that in denying the Rule\\n12(b)(6) motion, the district court made an appealable final legal decision on\\nqualified immunity. The Appellants base this argument on a statement made\\nby the district court regarding a possible alternative argument that the\\ndefendants did not raise in their motion – that the Rule 12(b)(6) motion should\\ninstead be considered a Rule 12(c) motion. 3 The district court, in declining to\\nconsider the motion under Rule 12(c), stated that “there are material facts in\\ndispute and at this stage of the litigation, the Law Enforcement Defendants\\nare not entitled to a judgment as a matter of law.” Based on this statement,\\nthe Appellants aver that the district court essentially made a final legal\\ndetermination that the Appellants were not entitled to qualified immunity.\\nThis final legal determination must be appealable, Appellants maintain,\\nbecause the purpose of qualified immunity is to protect the officers from trial,\\nnot only from liability. Mitchell, 472 U.S. 511, 526-27.\\n However, the district court specifically stated that it was making the\\ndecision on procedural grounds, rather than legal grounds: “Accordingly, the\\nLaw Enforcement Defendants’ Rule 12(b)(6) Motion to Dismiss is DENIED as\\nuntimely.” The decision therefore is not based on a legal evaluation of the\\nAppellants’ entitlement to qualified immunity. We take the district court at its\\nword and decline to hold that the district court inadvertently made a final legal\\ndetermination as to whether the Appellants are entitled to qualified immunity.\\n\\n\\n 3 District courts may consider untimely Rule 12(b)(6) motions as Rule 12(c) motions\\n(indeed they are sometimes encouraged to do so). See Delhomme v. Caremark Rx Inc., 232\\nF.R.D. 573, 576 n.2 (N.D. Tex. 2005).\\n 4\\n\\f Case: 18-30126 Document: 00514867978 Page: 5 Date Filed: 03/11/2019\\n\\n\\n No. 18-30126\\n\\nAccordingly, we note that nothing in the district court’s order bars the\\nAppellants from asserting qualified immunity by appropriate, timely\\nprocedural vehicle in the future. See Kiser v. Garrett, 67 F.3d 1166, 1169 (5th\\nCir. 1995) (“It would be anomalous to conclude that a defendant waives a\\nqualified immunity defense by dismissing as moot an interlocutory appeal that\\nthe defendant was not required to take in the first place.”).\\n III.\\n Because the district court’s decision on the Rule 12(b)(6) motion was\\nbased on timing rather than a substantive legal disposition regarding qualified\\nimmunity, this court does not have jurisdiction to consider the appeal at this\\ntime. Therefore, we do not find it necessary to consider the alternative\\narguments presented by the Appellants. We DISMISS this appeal for lack of\\nappellate jurisdiction.\\n\\n\\n\\n\\n 5\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1084,"cells":{"id":{"kind":"number","value":8443928,"string":"8,443,928"},"name":{"kind":"string","value":"Kyle Ray SHAW v. Dwayne VILLANUEVA, in his Individual and Official Capacity as County Sheriff Robert C. Ebrom, Jr., in his Individual and Official Capacity as Chief Deputy Sheriff"},"name_abbreviation":{"kind":"string","value":"Shaw v. Villanueva"},"decision_date":{"kind":"string","value":"2019-03-11"},"docket_number":{"kind":"string","value":"No. 17-50937"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Barksdale, Jones, Willett\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"020lead\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/8415359/\", \"author_raw\": \"\"}]}"},"judge1":{"kind":"string","value":"BARKSDALE"},"judge2":{"kind":"string","value":"JONES"},"judge3":{"kind":"string","value":"WILLETT"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/8443928/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":0,"string":"0"},"020lead_count":{"kind":"number","value":1,"string":"1"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Kyle Ray SHAW v. Dwayne VILLANUEVA, in his Individual and Official Capacity as County Sheriff Robert C. Ebrom, Jr., in his Individual and Official Capacity as Chief Deputy Sheriff\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-11\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Kyle Ray SHAW v. Dwayne VILLANUEVA, in his Individual and Official Capacity as County Sheriff Robert C. Ebrom, Jr., in his Individual and Official Capacity as Chief Deputy Sheriff\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-11\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1085,"cells":{"id":{"kind":"number","value":8443929,"string":"8,443,929"},"name":{"kind":"string","value":"Andrea ARMSTRONG, of the Estate of Glen Ford v. Don ASHLEY Gary Alderman Gary Pittman Everett T. Rushing Billy Lockwood, Wrongly Identified as Estate of Billy Lockwood Frank Datcher Glynn Mitchell Rodney Price"},"name_abbreviation":{"kind":"string","value":"Armstrong v. Ashley"},"decision_date":{"kind":"string","value":"2019-03-11"},"docket_number":{"kind":"string","value":"No. 18-30126"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Duncan, Engelhardt, Smith\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"020lead\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/8415360/\", \"author_raw\": \"\"}]}"},"judge1":{"kind":"string","value":"DUNCAN"},"judge2":{"kind":"string","value":"ENGELHARDT"},"judge3":{"kind":"string","value":"SMITH"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/8443929/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":0,"string":"0"},"020lead_count":{"kind":"number","value":1,"string":"1"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Andrea ARMSTRONG, of the Estate of Glen Ford v. Don ASHLEY Gary Alderman Gary Pittman Everett T. Rushing Billy Lockwood, Wrongly Identified as Estate of Billy Lockwood Frank Datcher Glynn Mitchell Rodney Price\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-11\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Andrea ARMSTRONG, of the Estate of Glen Ford v. Don ASHLEY Gary Alderman Gary Pittman Everett T. Rushing Billy Lockwood, Wrongly Identified as Estate of Billy Lockwood Frank Datcher Glynn Mitchell Rodney Price\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-11\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1086,"cells":{"id":{"kind":"number","value":4599859,"string":"4,599,859"},"name":{"kind":"string","value":"Gustavo MONTEON-CAMARGO, Also Known as Ulysius Montillon-Camargo, Also Known as Gustavo Monteon-Camargo, Petitioner, v. William P. BARR, U.S. Attorney General, Respondent."},"name_abbreviation":{"kind":"string","value":"Gustavo Monteon-Camargo v. William Barr, U. S. Att"},"decision_date":{"kind":"string","value":"2019-03-14"},"docket_number":{"kind":"string","value":"17-60345"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Smith, Duncan, Engelhardt\", \"parties\": \"\", \"opinions\": [{\"author\": \"JERRY E. SMITH, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 17-60345 Document: 00514872705 Page: 1 Date Filed: 03/14/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n No. 17-60345 FILED\\n March 14, 2019\\n Lyle W. Cayce\\n Clerk\\n\\nGUSTAVO MONTEON-CAMARGO,\\nAlso Known as Ulysius Montillon-Camargo,\\nAlso Known as Gustavo Monteon Camargo,\\n\\n Petitioner,\\n\\nversus\\n\\nWILLIAM P. BARR, U.S. Attorney General,\\n\\n Respondent.\\n\\n\\n\\n\\n Petitions for Review of an Order of\\n the Board of Immigration Appeals\\n\\n\\n\\n\\nBefore SMITH, DUNCAN, and ENGELHARDT, Circuit Judges.\\nJERRY E. SMITH, Circuit Judge:\\n\\n Gustavo Monteon-Camargo, a native and citizen of Mexico, petitions for\\nreview of a final order of removal by the Board of Immigration Appeals (“BIA”\\nor “Board”). The BIA determined that Monteon-Camargo was ineligible for\\ncancellation of removal because his 2007 conviction of attempted theft from a\\nperson under Texas law counts as a crime involving moral turpitude (“CIMT”)\\n\\f Case: 17-60345 Document: 00514872705 Page: 2 Date Filed: 03/14/2019\\n\\n\\n\\n No. 17-60345\\nunder a 2016 BIA decision. We grant the petition and reverse and remand\\nbecause that retroactive application was error.\\n\\n I.\\n Monteon-Camargo first entered the United States in 1998 on a non-\\nimmigrant visa but was arrested and administratively returned to Mexico in\\n2004. He reentered on an unknown date and was arrested by the Department\\nof Homeland Security (“DHS”) in 2010. DHS served him with a Notice to\\nAppear, charging him with inadmissibility as an alien present in the United\\nStates without being admitted or paroled, in violation of 8 U.S.C.\\n§ 1182(a)(6)(A)(i).\\n\\n During removal proceedings, Monteon-Camargo submitted an “Applica-\\ntion for Cancellation of Removal and Adjustment of Status for Certain Non-\\npermanent Residents.” DHS submitted a judgment showing that in 2007,\\nMonteon-Camargo had pleaded guilty of attempted theft from a person in vio-\\nlation of Texas Penal Code § 31.03. 1 Deciding that that offense was a CIMT\\nand that Monteon-Camargo thus had failed to establish one of the\\nprerequisites for eligibility for cancellation of removal—that his conviction was\\nnot a CIMT—the immigration judge (“IJ”) found Monteon-Camargo removable\\n\\n\\n\\n\\n 1 Texas Penal Code § 31.03(a)–(b) provides as follows:\\n (a) A person commits an offense if he unlawfully appropriates property with intent to\\n deprive the owner of property.\\n (b) Appropriation of property is unlawful if:\\n (1) it is without the owner’s effective consent;\\n (2) the property is stolen and the actor appropriates the property knowing it\\n was stolen by another; or\\n (3) property in the custody of any law enforcement agency was explicitly repre-\\n sented by any law enforcement agent to the actor as being stolen and the actor\\n appropriates the property believing it was stolen by another.\\n 2\\n\\f Case: 17-60345 Document: 00514872705 Page: 3 Date Filed: 03/14/2019\\n\\n\\n\\n No. 17-60345\\nas charged. 2\\n\\n Monteon-Camargo appealed to the BIA, contending that the IJ erred in\\nfailing to apply the modified categorical approach to determine whether the\\nattempted-theft conviction was a CIMT. He asked the BIA to remand to allow\\nhim to supplement the record with his conviction records so he could show that\\nhis conviction was not a CIMT. 3\\n\\n The BIA dismissed the appeal. It agreed with the IJ that attempted theft\\nfrom a person under § 31.03 is categorically a CIMT and that Monteon-\\nCamargo was therefore statutorily ineligible for cancellation of removal. The\\nBoard based its decision on In re Diaz-Lizarraga, 26 I. & N. Dec. 847, 848 (BIA\\n2016), which announced that a theft offense is a CIMT if it involves a taking\\nor exercise of control over another’s property without consent and with an\\nintent to deprive the owner of his property either permanently or under cir-\\ncumstances in which the owner’s property rights are substantially eroded. A\\ndefendant could not be convicted of violating § 31.03, the BIA continued, unless\\nhis conduct met the definition in Diaz-Lizarraga. The BIA also noted that\\nTexas caselaw confirms “that a theft conviction may not lawfully be entered\\nabsent proof beyond a reasonable doubt that the accused intended\\npermanently to deprive the victim of the value of his property.” Consequently,\\n\\n\\n 2 The IJ also denied Monteon-Camargo’s request for a continuance to apply for other\\nforms of relief, explaining that a continuance would be futile because Monteon-Camargo was\\nstatutorily ineligible for adjustment of status and could not cure his ineligibility with a\\nwaiver. The IJ further declined to continue proceedings to allow Monteon-Camargo to apply\\nfor withholding of removal because Monteon-Camargo had not shown the requisite good\\ncause. The IJ noted that proceedings had been ongoing for approximately two years, yet\\nMonteon-Camargo had not sought a withholding of removal until other forms of relief were\\nforeclosed.\\n 3 Monteon-Camargo also challenged the IJ’s denial of a continuance, explaining that\\nhe had not “proceeded on his application for withholding of removal” because he believed he\\nhad a strong case for cancellation of removal. He further averred that he needed a continu-\\nance to file for asylum under the United Nations Convention Against Torture.\\n 3\\n\\f Case: 17-60345 Document: 00514872705 Page: 4 Date Filed: 03/14/2019\\n\\n\\n\\n No. 17-60345\\nthe Board concluded, Monteon-Camargo’s conviction is a CIMT. 4\\n\\n While his petition for review to this court was pending, Monteon-\\nCamargo moved the Board to reopen and reconsider its decision dismissing his\\noriginal appeal of the IJ’s decision. The BIA denied that motion, whereupon\\nMonteon-Camargo filed a second petition for review in this court. We consoli-\\ndated the two petitions, and the parties filed supplemental briefing.\\n\\n After that, several of our sister circuits held that the Board may not\\nretroactively apply Diaz-Lizarraga’s definition of CIMTs to predicate offenses\\ncommitted before that decision. 5 Monteon-Camargo and the government have\\nsubmitted several supplemental letters addressing those cases.\\n\\n II.\\n We review the BIA’s rulings of law de novo, “giv[ing] Chevron defer-\\nence[ 6] to the BIA’s interpretation of the term ‘moral turpitude’ and its guid-\\nance on the general categories of offenses which constitute CIMTs.” Laryea v.\\nSessions, 871 F.3d 337, 341 (5th Cir. 2017) (internal alterations and citation\\nomitted). Because the BIA agreed with the IJ’s rulings, we review the decisions\\nof both the BIA and the IJ. See Zhu v. Gonzales, 493 F.3d 588, 593 (5th Cir.\\n2007).\\n\\n An alien is eligible for cancellation of removal if, among other things, he\\n\\n\\n\\n\\n 4 Regarding the request for a continuance, the BIA observed that Monteon-Camargo\\nhad received multiple continuances over the past two years, had “designated Mexico as the\\ncountry of removal” and expressed no fear of returning there, “ha[d] not proffered an applica-\\ntion [for asylum] on appeal,” and had “established [neither] prima facie eligibility for [asylum\\nnor prejudice].”\\n 5Garcia-Martinez v. Sessions, 886 F.3d 1291 (9th Cir. 2018); Obeya v. Sessions,\\n884 F.3d 442 (2d Cir. 2018); Lucio-Rayos v. Sessions, 875 F.3d 573 (10th Cir. 2017).\\n 6 See Chevron, U.S.A., Inc. v. Nat. Res. Def. Council, 467 U.S. 837, 842–43 (1984).\\n 4\\n\\f Case: 17-60345 Document: 00514872705 Page: 5 Date Filed: 03/14/2019\\n\\n\\n\\n No. 17-60345\\n“has not been convicted of an offense under section 1182(a)(2)” 7—that is, “a\\n[CIMT].” 8 U.S.C. § 1182(a)(2)(A)(i)(I). The alien has the burden to establish\\neligibility for cancellation of removal. Id. § 1229a(c)(4)(A). Put differently, the\\nalien must prove that his conviction was not a CIMT.\\n\\n Congress did not define “moral turpitude” in the Immigration and\\nNationality Act but “left the interpretation of this provision to the BIA and\\ninterpretation of its application to state and federal laws to the federal courts.”\\nRodriguez-Castro v. Gonzales, 427 F.3d 316, 319−20 (5th Cir. 2005). The BIA\\nhas long maintained that “theft [is] . . . a [CIMT],” Okoro v. INS, 125 F.3d 920,\\n926 (5th Cir. 1997), and this court has consistently deferred to that holding.\\nSee id.\\n\\n Historically, the BIA has held that a theft offense is categorically a CIMT\\nonly if it was “committed with the intent to permanently deprive an owner of\\nproperty.” 8 But the BIA altered its position in 2016. In Diaz-Lizarraga, a for-\\nmal adjudication, the BIA opined that “lawmakers and judges across the coun-\\ntry have come to recognize that many temporary takings are as culpable as\\npermanent ones.” Diaz-Lizarraga, 26 I. & N. Dec. at 851. The Board thus\\nrevised its interpretation of which theft crimes constitute CIMTs, holding “that\\na taking or exercise of control over another’s property without consent . . . is a\\n[CIMT] if it involves an intent to deprive the owner of his property either\\npermanently or under circumstances where the owner’s property rights are\\nsubstantially eroded.” Id. at 852–53 (some emphasis added).\\n\\n The BIA applied that new standard to classify Monteon-Camargo’s\\nconviction as a CIMT. Monteon-Camargo contends that the BIA’s retroactive\\n\\n\\n 7 8 U.S.C. § 1229b(b)(1)(C).\\n 8Diaz-Lizarraga, 26 I. & N. Dec. at 849; see also, e.g., In re Grazley, 14 I. & N. Dec.\\n330, 333 (BIA 1973).\\n 5\\n\\f Case: 17-60345 Document: 00514872705 Page: 6 Date Filed: 03/14/2019\\n\\n\\n\\n No. 17-60345\\napplication of Diaz-Lizarraga violates due process. But before we reach the\\nmerits of that argument, we must decide two threshold questions: whether he\\nwaived the issue and whether we have jurisdiction.\\n\\n A.\\n “Generally speaking, a [party] waives an issue if he fails to adequately\\nbrief it.” United States v. Martinez, 263 F.3d 436, 438 (5th Cir. 2001). That\\n“rule is a prudential construct that requires the exercise of discretion.” Id.\\n(internal quotation marks and citation omitted). Federal Rule of Appellate\\nProcedure 28(a)(8)(A) instructs a party to brief his “contentions and the rea-\\nsons for them, with citations to the authorities and parts of the record on which\\nthe [party] relies.” Still, this court has the discretion to consider inadequately\\nbriefed claims and has done so. See, e.g., Martinez, 263 F.3d at 438.\\n\\n Monteon-Camargo first contended that the BIA erred in retroactively\\napplying Diaz-Lizarraga in his supplemental brief, devoting just over a page\\nto the theory and citing no authorities. But both parties have filed supple-\\nmental letters addressing the issue and providing authorities.\\n\\n Despite the sparse briefing, we exercise our discretion to consider\\nMonteon-Camargo’s retroactivity claim. Three of our sister circuits have held\\nthat the BIA’s revised CIMT definition may not be retroactively applied to\\npredicate offenses committed before Diaz-Lizarraga was issued. 9 And the\\ngovernment has apparently adopted that position, as well, based on a response\\n\\n\\n 9 Garcia-Martinez v. Sessions, 886 F.3d 1291 (9th Cir. 2018); Obeya v. Sessions,\\n884 F.3d 442 (2d Cir. 2018); Lucio-Rayos v. Sessions, 875 F.3d 573 (10th Cir. 2017). In Lucio-\\nRayos, the Tenth Circuit explained that “after the BIA’s decision in this case, the BIA updated\\nits definition of theft offenses that qualify as a CIMT.” Lucio-Rayos, 875 F.3d at 578 (internal\\nquotation marks and citation omitted). But “[t]hat new definition . . . does not apply retroac-\\ntively here . . . because a revised rule adopted by the BIA in the exercise of its delegated\\nlegislative policymaking authority is presumed to apply prospectively only to cases initiated\\nafter its issuance.” Id.\\n 6\\n\\f Case: 17-60345 Document: 00514872705 Page: 7 Date Filed: 03/14/2019\\n\\n\\n\\n No. 17-60345\\nto a certiorari petition filed November 9, 2018. 10 We are also satisfied that the\\nparties have adequately presented their positions in the supplemental letters,\\nmaking it appropriate to decide the issue.\\n\\n B.\\n The government contends that we do not have jurisdiction to decide\\nMonteon-Camargo’s retroactivity claim, averring that judicial review is un-\\navailable under § 1252(d)(1) because Monteon-Camargo did not present that\\nclaim to the BIA. 11 “Judicial review of a final removal order is only available\\nif ‘the alien has exhausted all administrative remedies available to the alien\\nas of right.’” Vazquez v. Sessions, 885 F.3d 862, 868 (5th Cir. 2018) (quoting\\n8 U.S.C. § 1252(d)(1)). That exhaustion requirement is “mandatory and juris-\\ndictional.” Omari v. Holder, 562 F.3d 314, 324 (5th Cir. 2009) (emphasis omit-\\nted). “An alien fails to exhaust his administrative remedies with respect to an\\nissue when the issue is not raised in the first instance before the BIA.” Vaz-\\nquez, 885 F.3d at 868 (internal quotation marks, alteration, and citation omit-\\nted). “[T]o satisfy the exhaustion requirement . . . a petitioner must ‘raise,’\\n‘present,’ or ‘mention’ an issue to the BIA” in his brief to the Board. Id. (citing\\nOmari, 562 F.3d at 321).\\n\\n Due process claims, however, are generally exempt from the exhaustion\\ndoctrine because they are not within the purview of the BIA. Anwar v. INS,\\n\\n\\n\\n 10 Br. for the Resp’t in Opp’n at 2–3, Lucio-Rayos v. Whitaker (No. 18-64), 2018 WL\\n5920369 (internal quotation marks and citation omitted) (observing that for “removal pro-\\nceedings [that] were initiated” before Diaz-Lizarraga, “theft offense[s] constituted” CIMTs\\nonly if they “required the defendant to act with the intent to permanently deprive an owner\\nof property”).\\n 11 The government’s only response to Monteon-Camargo’s retroactivity claim has been\\nthat this court lacks jurisdiction. The government posits that Monteon-Camargo “did not\\npresent that argument to the agency and this Court lacks jurisdiction to review that argu-\\nment in the first instance” under 8 U.S.C. § 1252(d)(1).\\n 7\\n\\f Case: 17-60345 Document: 00514872705 Page: 8 Date Filed: 03/14/2019\\n\\n\\n\\n No. 17-60345\\n116 F.3d 140, 144 n.4 (5th Cir. 1997) (citations omitted). “[W]hen a petitioner’s\\ndue process claim does not assert a procedural error correctable by the BIA, it\\nis not subject to an exhaustion requirement.” Lopez De Jesus v. INS, 312 F.3d\\n155, 162 n.47 (5th Cir. 2002).\\n\\n Monteon-Camargo raises a due process challenge to the BIA’s decision,\\ncontending that Diaz-Lizarraga cannot apply retroactively because of “the due\\nprocess interests of fair notice.” The government counters that retroactivity\\nclaims are not per se constitutional due process claims that the BIA is unable\\nto correct. And Monteon-Camargo, the government suggests, is alleging “pro-\\ncedural error,” Falek v. Gonzales, 475 F.3d 285, 289−90 (5th Cir. 2007) (inter-\\nnal quotation marks and citation omitted), because his “supplemental brief\\ndoes not mention the [C]onstitution, let alone establish that [his retroactivity\\nclaim] is the type of argument that the Board is unable to review.” The gov-\\nernment concludes that under Falek, Monteon-Camargo needed to exhaust his\\nretroactivity claim before the Board.\\n\\n But unlike in Falek, id., Monteon-Camargo presses a constitutional\\nclaim, contending that retroactively applying Diaz-Lizarraga compromises his\\n“‘due process interests in fair notice, reasonable reliance, and settled expec-\\ntations’” (quoting De Niz Robles v. Lynch, 803 F.3d 1165, 1169 (10th Cir. 2015)\\n(Gorsuch, J.)). 12 Accordingly, his retroactivity claim “is not subject to an ex-\\nhaustion requirement,” Lopez De Jesus, 312 F.3d at 162 n.47, and we have\\njurisdiction to consider it.\\n\\n\\n\\n\\n 12 Compare Lopez De Jesus, 312 F.3d at 162 (recognizing an exception to the exhaus-\\ntion requirement where a BIA decision applied a statutory amendment retroactively, thus\\nrendering an alien ineligible for a waiver of inadmissibility, and the alien challenged the\\nretroactive application as a violation of “his constitutional rights to fair notice and due\\nprocess”).\\n 8\\n\\f Case: 17-60345 Document: 00514872705 Page: 9 Date Filed: 03/14/2019\\n\\n\\n\\n No. 17-60345\\n C.\\n That takes us to the merits. “[T]he leading case on administrative\\nretroactivity” instructs that any disadvantages from the “‘retroactive effect[s]’”\\nof deciding a “‘case of first impression . . . must be balanced against the mis-\\nchief of producing a result which is contrary to a statutory design or to legal\\nand equitable principles.’” Microcomputer Tech. Inst. v. Riley, 139 F.3d 1044,\\n1050 (5th Cir. 1998) (quoting SEC v. Chenery Corp., 332 U.S. 194, 203 (1947)).\\nTo apply that instruction, this court “balance[s] the ills of retroactivity against\\nthe disadvantages of prospectivity.” Id. 13 “If that mischief [of prospectivity] is\\ngreater than the ill effect of the retroactive application of a new standard, it is\\nnot the type of retroactivity which is condemned by law.” Chenery, 332 U.S.\\nat 203. We must thus balance the ills of applying the BIA’s new interpretation\\nof which thefts constitute CIMTs against the disadvantages of applying the\\nchange solely to predicate offenses adjudicated after Diaz-Lizarraga.\\n\\n Because the retroactivity issue was first raised in the supplemental\\nbriefing, the various briefs say little about the disadvantages of retroactivity\\nversus prospectivity. There are, however, some obvious disadvantages. Crim-\\ninal defendants may have pleaded guilty of crimes that they rightly thought,\\nbased on the Board’s prior position, did not constitute CIMTs. Accordingly,\\nthey may have entered pleas believing that they would not suffer adverse im-\\nmigration consequences as a result. Retroactively applying Diaz-Lizarraga\\nthus would compromise the “familiar [due process] considerations of fair\\nnotice, reasonable reliance, and settled expectations.” Landgraf v. USI Film\\n\\n\\n\\n 13 Other circuits, by contrast, apply “variously articulated factors,” usually “the five\\nfactors articulated in Retail, Wholesale & Dep’t Store Union v. NLRB, 466 F.2d 380, 390 (D.C.\\nCir. 1972),” to “measure [the] unfairness to the parties against the ‘mischief’ of allowing the\\nprevious . . . interpretation to stand.” Microcomputer Tech. Inst., 139 F.3d at 1050 (quoting\\nRetail, Wholesale & Dep’t Store Union, 466 F.2d at 390).\\n 9\\n\\f Case: 17-60345 Document: 00514872705 Page: 10 Date Filed: 03/14/2019\\n\\n\\n\\n No. 17-60345\\nProds., 511 U.S. 244, 270 (1994).\\n\\n The change in the Board’s guidance, moreover, was significant: It added\\nan entirely new category of theft offenses to those considered CIMTs. In Diaz-\\nLizarraga, the Board recognized that it was drastically changing the land-\\nscape, observing that it was “updat[ing]” what had been its position “[f]rom\\n[its] earliest days.” Diaz-Lizarraga, 26 I. & N. Dec. at 849, 852. Applying such\\na broad “new rule[] of general applicability” to prior conduct contravenes basic\\npresumptions about our legislative system. De Niz Robles, 803 F.3d at 1169.\\nA “presumption of prospectivity attaches to Congress’s own work,” and it\\nshould generally attach when an agency “exercise[s] delegated legislative\\n. . . authority.” Id. at 1171−72.\\n\\n Though there are multiple disadvantages to applying it retroactively, the\\ngovernment has not identified a single disadvantage of applying Diaz-\\nLizarraga only prospectively. We conclude that the definition of CIMTs an-\\nnounced in Diaz-Lizarraga may be applied only to crimes committed after that\\ndecision issued. The BIA erred in applying its new definition to Monteon-\\nCamargo’s conviction of attempted theft.\\n\\n The petition for review is GRANTED. The order is REVERSED and\\nREMANDED for further proceedings. 14\\n\\n\\n\\n\\n 14 We DENY, as moot, Monteon-Camargo’s petition for review of the BIA’s denial of\\nhis motion to reopen and reconsider. See Arce-Vences v. Mukasey, 512 F.3d 167, 173 n.1 (5th\\nCir. 2007) (denying as moot a petition for review of the BIA’s denial of a motion to reopen\\nwhere the court granted the petition for review of the original removal order).\\n 10\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4377112/\", \"author_raw\": \"JERRY E. SMITH, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"SMITH"},"judge2":{"kind":"string","value":"DUNCAN"},"judge3":{"kind":"string","value":"ENGELHARDT"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4599859/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Gustavo MONTEON-CAMARGO, Also Known as Ulysius Montillon-Camargo, Also Known as Gustavo Monteon-Camargo, Petitioner, v. William P. BARR, U.S. Attorney General, Respondent.\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-14\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 17-60345 Document: 00514872705 Page: 1 Date Filed: 03/14/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\n United States Court of Appeals\n Fifth Circuit\n\n No. 17-60345 FILED\n March 14, 2019\n Lyle W. Cayce\n Clerk\n\nGUSTAVO MONTEON-CAMARGO,\nAlso Known as Ulysius Montillon-Camargo,\nAlso Known as Gustavo Monteon Camargo,\n\n Petitioner,\n\nversus\n\nWILLIAM P. BARR, U.S. Attorney General,\n\n Respondent.\n\n\n\n\n Petitions for Review of an Order of\n the Board of Immigration Appeals\n\n\n\n\nBefore SMITH, DUNCAN, and ENGELHARDT, Circuit Judges.\nJERRY E. SMITH, Circuit Judge:\n\n Gustavo Monteon-Camargo, a native and citizen of Mexico, petitions for\nreview of a final order of removal by the Board of Immigration Appeals (“BIA”\nor “Board”). The BIA determined that Monteon-Camargo was ineligible for\ncancellation of removal because his 2007 conviction of attempted theft from a\nperson under Texas law counts as a crime involving moral turpitude (“CIMT”)\n\f Case: 17-60345 Document: 00514872705 Page: 2 Date Filed: 03/14/2019\n\n\n\n No. 17-60345\nunder a 2016 BIA decision. We grant the petition and reverse and remand\nbecause that retroactive application was error.\n\n I.\n Monteon-Camargo first entered the United States in 1998 on a non-\nimmigrant visa but was arrested and administratively returned to Mexico in\n2004. He reentered on an unknown date and was arrested by the Department\nof Homeland Security (“DHS”) in 2010. DHS served him with a Notice to\nAppear, charging him with inadmissibility as an alien present in the United\nStates without being admitted or paroled, in violation of 8 U.S.C.\n§ 1182(a)(6)(A)(i).\n\n During removal proceedings, Monteon-Camargo submitted an “Applica-\ntion for Cancellation of Removal and Adjustment of Status for Certain Non-\npermanent Residents.” DHS submitted a judgment showing that in 2007,\nMonteon-Camargo had pleaded guilty of attempted theft from a person in vio-\nlation of Texas Penal Code § 31.03. 1 Deciding that that offense was a CIMT\nand that Monteon-Camargo thus had failed to establish one of the\nprerequisites for eligibility for cancellation of removal—that his conviction was\nnot a CIMT—the immigration judge (“IJ”) found Monteon-Camargo removable\n\n\n\n\n 1 Texas Penal Code § 31.03(a)–(b) provides as follows:\n (a) A person commits an offense if he unlawfully appropriates property with intent to\n deprive the owner of property.\n (b) Appropriation of property is unlawful if:\n (1) it is without the owner’s effective consent;\n (2) the property is stolen and the actor appropriates the property knowing it\n was stolen by another; or\n (3) property in the custody of any law enforcement agency was explicitly repre-\n sented by any law enforcement agent to the actor as being stolen and the actor\n appropriates the property believing it was stolen by another.\n 2\n\f Case: 17-60345 Document: 00514872705 Page: 3 Date Filed: 03/14/2019\n\n\n\n No. 17-60345\nas charged. 2\n\n Monteon-Camargo appealed to the BIA, contending that the IJ erred in\nfailing to apply the modified categorical approach to determine whether the\nattempted-theft conviction was a CIMT. He asked the BIA to remand to allow\nhim to supplement the record with his conviction records so he could show that\nhis conviction was not a CIMT. 3\n\n The BIA dismissed the appeal. It agreed with the IJ that attempted theft\nfrom a person under § 31.03 is categorically a CIMT and that Monteon-\nCamargo was therefore statutorily ineligible for cancellation of removal. The\nBoard based its decision on In re Diaz-Lizarraga, 26 I. & N. Dec. 847, 848 (BIA\n2016), which announced that a theft offense is a CIMT if it involves a taking\nor exercise of control over another’s property without consent and with an\nintent to deprive the owner of his property either permanently or under cir-\ncumstances in which the owner’s property rights are substantially eroded. A\ndefendant could not be convicted of violating § 31.03, the BIA continued, unless\nhis conduct met the definition in Diaz-Lizarraga. The BIA also noted that\nTexas caselaw confirms “that a theft conviction may not lawfully be entered\nabsent proof beyond a reasonable doubt that the accused intended\npermanently to deprive the victim of the value of his property.” Consequently,\n\n\n 2 The IJ also denied Monteon-Camargo’s request for a continuance to apply for other\nforms of relief, explaining that a continuance would be futile because Monteon-Camargo was\nstatutorily ineligible for adjustment of status and could not cure his ineligibility with a\nwaiver. The IJ further declined to continue proceedings to allow Monteon-Camargo to apply\nfor withholding of removal because Monteon-Camargo had not shown the requisite good\ncause. The IJ noted that proceedings had been ongoing for approximately two years, yet\nMonteon-Camargo had not sought a withholding of removal until other forms of relief were\nforeclosed.\n 3 Monteon-Camargo also challenged the IJ’s denial of a continuance, explaining that\nhe had not “proceeded on his application for withholding of removal” because he believed he\nhad a strong case for cancellation of removal. He further averred that he needed a continu-\nance to file for asylum under the United Nations Convention Against Torture.\n 3\n\f Case: 17-60345 Document: 00514872705 Page: 4 Date Filed: 03/14/2019\n\n\n\n No. 17-60345\nthe Board concluded, Monteon-Camargo’s conviction is a CIMT. 4\n\n While his petition for review to this court was pending, Monteon-\nCamargo moved the Board to reopen and reconsider its decision dismissing his\noriginal appeal of the IJ’s decision. The BIA denied that motion, whereupon\nMonteon-Camargo filed a second petition for review in this court. We consoli-\ndated the two petitions, and the parties filed supplemental briefing.\n\n After that, several of our sister circuits held that the Board may not\nretroactively apply Diaz-Lizarraga’s definition of CIMTs to predicate offenses\ncommitted before that decision. 5 Monteon-Camargo and the government have\nsubmitted several supplemental letters addressing those cases.\n\n II.\n We review the BIA’s rulings of law de novo, “giv[ing] Chevron defer-\nence[ 6] to the BIA’s interpretation of the term ‘moral turpitude’ and its guid-\nance on the general categories of offenses which constitute CIMTs.” Laryea v.\nSessions, 871 F.3d 337, 341 (5th Cir. 2017) (internal alterations and citation\nomitted). Because the BIA agreed with the IJ’s rulings, we review the decisions\nof both the BIA and the IJ. See Zhu v. Gonzales, 493 F.3d 588, 593 (5th Cir.\n2007).\n\n An alien is eligible for cancellation of removal if, among other things, he\n\n\n\n\n 4 Regarding the request for a continuance, the BIA observed that Monteon-Camargo\nhad received multiple continuances over the past two years, had “designated Mexico as the\ncountry of removal” and expressed no fear of returning there, “ha[d] not proffered an applica-\ntion [for asylum] on appeal,” and had “established [neither] prima facie eligibility for [asylum\nnor prejudice].”\n 5Garcia-Martinez v. Sessions, 886 F.3d 1291 (9th Cir. 2018); Obeya v. Sessions,\n884 F.3d 442 (2d Cir. 2018); Lucio-Rayos v. Sessions, 875 F.3d 573 (10th Cir. 2017).\n 6 See Chevron, U.S.A., Inc. v. Nat. Res. Def. Council, 467 U.S. 837, 842–43 (1984).\n 4\n\f Case: 17-60345 Document: 00514872705 Page: 5 Date Filed: 03/14/2019\n\n\n\n No. 17-60345\n“has not been convicted of an offense under section 1182(a)(2)” 7—that is, “a\n[CIMT].” 8 U.S.C. § 1182(a)(2)(A)(i)(I). The alien has the burden to establish\neligibility for cancellation of removal. Id. § 1229a(c)(4)(A). Put differently, the\nalien must prove that his conviction was not a CIMT.\n\n Congress did not define “moral turpitude” in the Immigration and\nNationality Act but “left the interpretation of this provision to the BIA and\ninterpretation of its application to state and federal laws to the federal courts.”\nRodriguez-Castro v. Gonzales, 427 F.3d 316, 319−20 (5th Cir. 2005). The BIA\nhas long maintained that “theft [is] . . . a [CIMT],” Okoro v. INS, 125 F.3d 920,\n926 (5th Cir. 1997), and this court has consistently deferred to that holding.\nSee id.\n\n Historically, the BIA has held that a theft offense is categorically a CIMT\nonly if it was “committed with the intent to permanently deprive an owner of\nproperty.” 8 But the BIA altered its position in 2016. In Diaz-Lizarraga, a for-\nmal adjudication, the BIA opined that “lawmakers and judges across the coun-\ntry have come to recognize that many temporary takings are as culpable as\npermanent ones.” Diaz-Lizarraga, 26 I. & N. Dec. at 851. The Board thus\nrevised its interpretation of which theft crimes constitute CIMTs, holding “that\na taking or exercise of control over another’s property without consent . . . is a\n[CIMT] if it involves an intent to deprive the owner of his property either\npermanently or under circumstances where the owner’s property rights are\nsubstantially eroded.” Id. at 852–53 (some emphasis added).\n\n The BIA applied that new standard to classify Monteon-Camargo’s\nconviction as a CIMT. Monteon-Camargo contends that the BIA’s retroactive\n\n\n 7 8 U.S.C. § 1229b(b)(1)(C).\n 8Diaz-Lizarraga, 26 I. & N. Dec. at 849; see also, e.g., In re Grazley, 14 I. & N. Dec.\n330, 333 (BIA 1973).\n 5\n\f Case: 17-60345 Document: 00514872705 Page: 6 Date Filed: 03/14/2019\n\n\n\n No. 17-60345\napplication of Diaz-Lizarraga violates due process. But before we reach the\nmerits of that argument, we must decide two threshold questions: whether he\nwaived the issue and whether we have jurisdiction.\n\n A.\n “Generally speaking, a [party] waives an issue if he fails to adequately\nbrief it.” United States v. Martinez, 263 F.3d 436, 438 (5th Cir. 2001). That\n“rule is a prudential construct that requires the exercise of discretion.” Id.\n(internal quotation marks and citation omitted). Federal Rule of Appellate\nProcedure 28(a)(8)(A) instructs a party to brief his “contentions and the rea-\nsons for them, with citations to the authorities and parts of the record on which\nthe [party] relies.” Still, this court has the discretion to consider inadequately\nbriefed claims and has done so. See, e.g., Martinez, 263 F.3d at 438.\n\n Monteon-Camargo first contended that the BIA erred in retroactively\napplying Diaz-Lizarraga in his supplemental brief, devoting just over a page\nto the theory and citing no authorities. But both parties have filed supple-\nmental letters addressing the issue and providing authorities.\n\n Despite the sparse briefing, we exercise our discretion to consider\nMonteon-Camargo’s retroactivity claim. Three of our sister circuits have held\nthat the BIA’s revised CIMT definition may not be retroactively applied to\npredicate offenses committed before Diaz-Lizarraga was issued. 9 And the\ngovernment has apparently adopted that position, as well, based on a response\n\n\n 9 Garcia-Martinez v. Sessions, 886 F.3d 1291 (9th Cir. 2018); Obeya v. Sessions,\n884 F.3d 442 (2d Cir. 2018); Lucio-Rayos v. Sessions, 875 F.3d 573 (10th Cir. 2017). In Lucio-\nRayos, the Tenth Circuit explained that “after the BIA’s decision in this case, the BIA updated\nits definition of theft offenses that qualify as a CIMT.” Lucio-Rayos, 875 F.3d at 578 (internal\nquotation marks and citation omitted). But “[t]hat new definition . . . does not apply retroac-\ntively here . . . because a revised rule adopted by the BIA in the exercise of its delegated\nlegislative policymaking authority is presumed to apply prospectively only to cases initiated\nafter its issuance.” Id.\n 6\n\f Case: 17-60345 Document: 00514872705 Page: 7 Date Filed: 03/14/2019\n\n\n\n No. 17-60345\nto a certiorari petition filed November 9, 2018. 10 We are also satisfied that the\nparties have adequately presented their positions in the supplemental letters,\nmaking it appropriate to decide the issue.\n\n B.\n The government contends that we do not have jurisdiction to decide\nMonteon-Camargo’s retroactivity claim, averring that judicial review is un-\navailable under § 1252(d)(1) because Monteon-Camargo did not present that\nclaim to the BIA. 11 “Judicial review of a final removal order is only available\nif ‘the alien has exhausted all administrative remedies available to the alien\nas of right.’” Vazquez v. Sessions, 885 F.3d 862, 868 (5th Cir. 2018) (quoting\n8 U.S.C. § 1252(d)(1)). That exhaustion requirement is “mandatory and juris-\ndictional.” Omari v. Holder, 562 F.3d 314, 324 (5th Cir. 2009) (emphasis omit-\nted). “An alien fails to exhaust his administrative remedies with respect to an\nissue when the issue is not raised in the first instance before the BIA.” Vaz-\nquez, 885 F.3d at 868 (internal quotation marks, alteration, and citation omit-\nted). “[T]o satisfy the exhaustion requirement . . . a petitioner must ‘raise,’\n‘present,’ or ‘mention’ an issue to the BIA” in his brief to the Board. Id. (citing\nOmari, 562 F.3d at 321).\n\n Due process claims, however, are generally exempt from the exhaustion\ndoctrine because they are not within the purview of the BIA. Anwar v. INS,\n\n\n\n 10 Br. for the Resp’t in Opp’n at 2–3, Lucio-Rayos v. Whitaker (No. 18-64), 2018 WL\n5920369 (internal quotation marks and citation omitted) (observing that for “removal pro-\nceedings [that] were initiated” before Diaz-Lizarraga, “theft offense[s] constituted” CIMTs\nonly if they “required the defendant to act with the intent to permanently deprive an owner\nof property”).\n 11 The government’s only response to Monteon-Camargo’s retroactivity claim has been\nthat this court lacks jurisdiction. The government posits that Monteon-Camargo “did not\npresent that argument to the agency and this Court lacks jurisdiction to review that argu-\nment in the first instance” under 8 U.S.C. § 1252(d)(1).\n 7\n\f Case: 17-60345 Document: 00514872705 Page: 8 Date Filed: 03/14/2019\n\n\n\n No. 17-60345\n116 F.3d 140, 144 n.4 (5th Cir. 1997) (citations omitted). “[W]hen a petitioner’s\ndue process claim does not assert a procedural error correctable by the BIA, it\nis not subject to an exhaustion requirement.” Lopez De Jesus v. INS, 312 F.3d\n155, 162 n.47 (5th Cir. 2002).\n\n Monteon-Camargo raises a due process challenge to the BIA’s decision,\ncontending that Diaz-Lizarraga cannot apply retroactively because of “the due\nprocess interests of fair notice.” The government counters that retroactivity\nclaims are not per se constitutional due process claims that the BIA is unable\nto correct. And Monteon-Camargo, the government suggests, is alleging “pro-\ncedural error,” Falek v. Gonzales, 475 F.3d 285, 289−90 (5th Cir. 2007) (inter-\nnal quotation marks and citation omitted), because his “supplemental brief\ndoes not mention the [C]onstitution, let alone establish that [his retroactivity\nclaim] is the type of argument that the Board is unable to review.” The gov-\nernment concludes that under Falek, Monteon-Camargo needed to exhaust his\nretroactivity claim before the Board.\n\n But unlike in Falek, id., Monteon-Camargo presses a constitutional\nclaim, contending that retroactively applying Diaz-Lizarraga compromises his\n“‘due process interests in fair notice, reasonable reliance, and settled expec-\ntations’” (quoting De Niz Robles v. Lynch, 803 F.3d 1165, 1169 (10th Cir. 2015)\n(Gorsuch, J.)). 12 Accordingly, his retroactivity claim “is not subject to an ex-\nhaustion requirement,” Lopez De Jesus, 312 F.3d at 162 n.47, and we have\njurisdiction to consider it.\n\n\n\n\n 12 Compare Lopez De Jesus, 312 F.3d at 162 (recognizing an exception to the exhaus-\ntion requirement where a BIA decision applied a statutory amendment retroactively, thus\nrendering an alien ineligible for a waiver of inadmissibility, and the alien challenged the\nretroactive application as a violation of “his constitutional rights to fair notice and due\nprocess”).\n 8\n\f Case: 17-60345 Document: 00514872705 Page: 9 Date Filed: 03/14/2019\n\n\n\n No. 17-60345\n C.\n That takes us to the merits. “[T]he leading case on administrative\nretroactivity” instructs that any disadvantages from the “‘retroactive effect[s]’”\nof deciding a “‘case of first impression . . . must be balanced against the mis-\nchief of producing a result which is contrary to a statutory design or to legal\nand equitable principles.’” Microcomputer Tech. Inst. v. Riley, 139 F.3d 1044,\n1050 (5th Cir. 1998) (quoting SEC v. Chenery Corp., 332 U.S. 194, 203 (1947)).\nTo apply that instruction, this court “balance[s] the ills of retroactivity against\nthe disadvantages of prospectivity.” Id. 13 “If that mischief [of prospectivity] is\ngreater than the ill effect of the retroactive application of a new standard, it is\nnot the type of retroactivity which is condemned by law.” Chenery, 332 U.S.\nat 203. We must thus balance the ills of applying the BIA’s new interpretation\nof which thefts constitute CIMTs against the disadvantages of applying the\nchange solely to predicate offenses adjudicated after Diaz-Lizarraga.\n\n Because the retroactivity issue was first raised in the supplemental\nbriefing, the various briefs say little about the disadvantages of retroactivity\nversus prospectivity. There are, however, some obvious disadvantages. Crim-\ninal defendants may have pleaded guilty of crimes that they rightly thought,\nbased on the Board’s prior position, did not constitute CIMTs. Accordingly,\nthey may have entered pleas believing that they would not suffer adverse im-\nmigration consequences as a result. Retroactively applying Diaz-Lizarraga\nthus would compromise the “familiar [due process] considerations of fair\nnotice, reasonable reliance, and settled expectations.” Landgraf v. USI Film\n\n\n\n 13 Other circuits, by contrast, apply “variously articulated factors,” usually “the five\nfactors articulated in Retail, Wholesale & Dep’t Store Union v. NLRB, 466 F.2d 380, 390 (D.C.\nCir. 1972),” to “measure [the] unfairness to the parties against the ‘mischief’ of allowing the\nprevious . . . interpretation to stand.” Microcomputer Tech. Inst., 139 F.3d at 1050 (quoting\nRetail, Wholesale & Dep’t Store Union, 466 F.2d at 390).\n 9\n\f Case: 17-60345 Document: 00514872705 Page: 10 Date Filed: 03/14/2019\n\n\n\n No. 17-60345\nProds., 511 U.S. 244, 270 (1994).\n\n The change in the Board’s guidance, moreover, was significant: It added\nan entirely new category of theft offenses to those considered CIMTs. In Diaz-\nLizarraga, the Board recognized that it was drastically changing the land-\nscape, observing that it was “updat[ing]” what had been its position “[f]rom\n[its] earliest days.” Diaz-Lizarraga, 26 I. & N. Dec. at 849, 852. Applying such\na broad “new rule[] of general applicability” to prior conduct contravenes basic\npresumptions about our legislative system. De Niz Robles, 803 F.3d at 1169.\nA “presumption of prospectivity attaches to Congress’s own work,” and it\nshould generally attach when an agency “exercise[s] delegated legislative\n. . . authority.” Id. at 1171−72.\n\n Though there are multiple disadvantages to applying it retroactively, the\ngovernment has not identified a single disadvantage of applying Diaz-\nLizarraga only prospectively. We conclude that the definition of CIMTs an-\nnounced in Diaz-Lizarraga may be applied only to crimes committed after that\ndecision issued. The BIA erred in applying its new definition to Monteon-\nCamargo’s conviction of attempted theft.\n\n The petition for review is GRANTED. The order is REVERSED and\nREMANDED for further proceedings. 14\n\n\n\n\n 14 We DENY, as moot, Monteon-Camargo’s petition for review of the BIA’s denial of\nhis motion to reopen and reconsider. See Arce-Vences v. Mukasey, 512 F.3d 167, 173 n.1 (5th\nCir. 2007) (denying as moot a petition for review of the BIA’s denial of a motion to reopen\nwhere the court granted the petition for review of the original removal order).\n 10\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Gustavo MONTEON-CAMARGO, Also Known as Ulysius Montillon-Camargo, Also Known as Gustavo Monteon-Camargo, Petitioner, v. William P. BARR, U.S. Attorney General, Respondent.\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-14\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 17-60345 Document: 00514872705 Page: 1 Date Filed: 03/14/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n No. 17-60345 FILED\\n March 14, 2019\\n Lyle W. Cayce\\n Clerk\\n\\nGUSTAVO MONTEON-CAMARGO,\\nAlso Known as Ulysius Montillon-Camargo,\\nAlso Known as Gustavo Monteon Camargo,\\n\\n Petitioner,\\n\\nversus\\n\\nWILLIAM P. BARR, U.S. Attorney General,\\n\\n Respondent.\\n\\n\\n\\n\\n Petitions for Review of an Order of\\n the Board of Immigration Appeals\\n\\n\\n\\n\\nBefore SMITH, DUNCAN, and ENGELHARDT, Circuit Judges.\\nJERRY E. SMITH, Circuit Judge:\\n\\n Gustavo Monteon-Camargo, a native and citizen of Mexico, petitions for\\nreview of a final order of removal by the Board of Immigration Appeals (“BIA”\\nor “Board”). The BIA determined that Monteon-Camargo was ineligible for\\ncancellation of removal because his 2007 conviction of attempted theft from a\\nperson under Texas law counts as a crime involving moral turpitude (“CIMT”)\\n\\f Case: 17-60345 Document: 00514872705 Page: 2 Date Filed: 03/14/2019\\n\\n\\n\\n No. 17-60345\\nunder a 2016 BIA decision. We grant the petition and reverse and remand\\nbecause that retroactive application was error.\\n\\n I.\\n Monteon-Camargo first entered the United States in 1998 on a non-\\nimmigrant visa but was arrested and administratively returned to Mexico in\\n2004. He reentered on an unknown date and was arrested by the Department\\nof Homeland Security (“DHS”) in 2010. DHS served him with a Notice to\\nAppear, charging him with inadmissibility as an alien present in the United\\nStates without being admitted or paroled, in violation of 8 U.S.C.\\n§ 1182(a)(6)(A)(i).\\n\\n During removal proceedings, Monteon-Camargo submitted an “Applica-\\ntion for Cancellation of Removal and Adjustment of Status for Certain Non-\\npermanent Residents.” DHS submitted a judgment showing that in 2007,\\nMonteon-Camargo had pleaded guilty of attempted theft from a person in vio-\\nlation of Texas Penal Code § 31.03. 1 Deciding that that offense was a CIMT\\nand that Monteon-Camargo thus had failed to establish one of the\\nprerequisites for eligibility for cancellation of removal—that his conviction was\\nnot a CIMT—the immigration judge (“IJ”) found Monteon-Camargo removable\\n\\n\\n\\n\\n 1 Texas Penal Code § 31.03(a)–(b) provides as follows:\\n (a) A person commits an offense if he unlawfully appropriates property with intent to\\n deprive the owner of property.\\n (b) Appropriation of property is unlawful if:\\n (1) it is without the owner’s effective consent;\\n (2) the property is stolen and the actor appropriates the property knowing it\\n was stolen by another; or\\n (3) property in the custody of any law enforcement agency was explicitly repre-\\n sented by any law enforcement agent to the actor as being stolen and the actor\\n appropriates the property believing it was stolen by another.\\n 2\\n\\f Case: 17-60345 Document: 00514872705 Page: 3 Date Filed: 03/14/2019\\n\\n\\n\\n No. 17-60345\\nas charged. 2\\n\\n Monteon-Camargo appealed to the BIA, contending that the IJ erred in\\nfailing to apply the modified categorical approach to determine whether the\\nattempted-theft conviction was a CIMT. He asked the BIA to remand to allow\\nhim to supplement the record with his conviction records so he could show that\\nhis conviction was not a CIMT. 3\\n\\n The BIA dismissed the appeal. It agreed with the IJ that attempted theft\\nfrom a person under § 31.03 is categorically a CIMT and that Monteon-\\nCamargo was therefore statutorily ineligible for cancellation of removal. The\\nBoard based its decision on In re Diaz-Lizarraga, 26 I. & N. Dec. 847, 848 (BIA\\n2016), which announced that a theft offense is a CIMT if it involves a taking\\nor exercise of control over another’s property without consent and with an\\nintent to deprive the owner of his property either permanently or under cir-\\ncumstances in which the owner’s property rights are substantially eroded. A\\ndefendant could not be convicted of violating § 31.03, the BIA continued, unless\\nhis conduct met the definition in Diaz-Lizarraga. The BIA also noted that\\nTexas caselaw confirms “that a theft conviction may not lawfully be entered\\nabsent proof beyond a reasonable doubt that the accused intended\\npermanently to deprive the victim of the value of his property.” Consequently,\\n\\n\\n 2 The IJ also denied Monteon-Camargo’s request for a continuance to apply for other\\nforms of relief, explaining that a continuance would be futile because Monteon-Camargo was\\nstatutorily ineligible for adjustment of status and could not cure his ineligibility with a\\nwaiver. The IJ further declined to continue proceedings to allow Monteon-Camargo to apply\\nfor withholding of removal because Monteon-Camargo had not shown the requisite good\\ncause. The IJ noted that proceedings had been ongoing for approximately two years, yet\\nMonteon-Camargo had not sought a withholding of removal until other forms of relief were\\nforeclosed.\\n 3 Monteon-Camargo also challenged the IJ’s denial of a continuance, explaining that\\nhe had not “proceeded on his application for withholding of removal” because he believed he\\nhad a strong case for cancellation of removal. He further averred that he needed a continu-\\nance to file for asylum under the United Nations Convention Against Torture.\\n 3\\n\\f Case: 17-60345 Document: 00514872705 Page: 4 Date Filed: 03/14/2019\\n\\n\\n\\n No. 17-60345\\nthe Board concluded, Monteon-Camargo’s conviction is a CIMT. 4\\n\\n While his petition for review to this court was pending, Monteon-\\nCamargo moved the Board to reopen and reconsider its decision dismissing his\\noriginal appeal of the IJ’s decision. The BIA denied that motion, whereupon\\nMonteon-Camargo filed a second petition for review in this court. We consoli-\\ndated the two petitions, and the parties filed supplemental briefing.\\n\\n After that, several of our sister circuits held that the Board may not\\nretroactively apply Diaz-Lizarraga’s definition of CIMTs to predicate offenses\\ncommitted before that decision. 5 Monteon-Camargo and the government have\\nsubmitted several supplemental letters addressing those cases.\\n\\n II.\\n We review the BIA’s rulings of law de novo, “giv[ing] Chevron defer-\\nence[ 6] to the BIA’s interpretation of the term ‘moral turpitude’ and its guid-\\nance on the general categories of offenses which constitute CIMTs.” Laryea v.\\nSessions, 871 F.3d 337, 341 (5th Cir. 2017) (internal alterations and citation\\nomitted). Because the BIA agreed with the IJ’s rulings, we review the decisions\\nof both the BIA and the IJ. See Zhu v. Gonzales, 493 F.3d 588, 593 (5th Cir.\\n2007).\\n\\n An alien is eligible for cancellation of removal if, among other things, he\\n\\n\\n\\n\\n 4 Regarding the request for a continuance, the BIA observed that Monteon-Camargo\\nhad received multiple continuances over the past two years, had “designated Mexico as the\\ncountry of removal” and expressed no fear of returning there, “ha[d] not proffered an applica-\\ntion [for asylum] on appeal,” and had “established [neither] prima facie eligibility for [asylum\\nnor prejudice].”\\n 5Garcia-Martinez v. Sessions, 886 F.3d 1291 (9th Cir. 2018); Obeya v. Sessions,\\n884 F.3d 442 (2d Cir. 2018); Lucio-Rayos v. Sessions, 875 F.3d 573 (10th Cir. 2017).\\n 6 See Chevron, U.S.A., Inc. v. Nat. Res. Def. Council, 467 U.S. 837, 842–43 (1984).\\n 4\\n\\f Case: 17-60345 Document: 00514872705 Page: 5 Date Filed: 03/14/2019\\n\\n\\n\\n No. 17-60345\\n“has not been convicted of an offense under section 1182(a)(2)” 7—that is, “a\\n[CIMT].” 8 U.S.C. § 1182(a)(2)(A)(i)(I). The alien has the burden to establish\\neligibility for cancellation of removal. Id. § 1229a(c)(4)(A). Put differently, the\\nalien must prove that his conviction was not a CIMT.\\n\\n Congress did not define “moral turpitude” in the Immigration and\\nNationality Act but “left the interpretation of this provision to the BIA and\\ninterpretation of its application to state and federal laws to the federal courts.”\\nRodriguez-Castro v. Gonzales, 427 F.3d 316, 319−20 (5th Cir. 2005). The BIA\\nhas long maintained that “theft [is] . . . a [CIMT],” Okoro v. INS, 125 F.3d 920,\\n926 (5th Cir. 1997), and this court has consistently deferred to that holding.\\nSee id.\\n\\n Historically, the BIA has held that a theft offense is categorically a CIMT\\nonly if it was “committed with the intent to permanently deprive an owner of\\nproperty.” 8 But the BIA altered its position in 2016. In Diaz-Lizarraga, a for-\\nmal adjudication, the BIA opined that “lawmakers and judges across the coun-\\ntry have come to recognize that many temporary takings are as culpable as\\npermanent ones.” Diaz-Lizarraga, 26 I. & N. Dec. at 851. The Board thus\\nrevised its interpretation of which theft crimes constitute CIMTs, holding “that\\na taking or exercise of control over another’s property without consent . . . is a\\n[CIMT] if it involves an intent to deprive the owner of his property either\\npermanently or under circumstances where the owner’s property rights are\\nsubstantially eroded.” Id. at 852–53 (some emphasis added).\\n\\n The BIA applied that new standard to classify Monteon-Camargo’s\\nconviction as a CIMT. Monteon-Camargo contends that the BIA’s retroactive\\n\\n\\n 7 8 U.S.C. § 1229b(b)(1)(C).\\n 8Diaz-Lizarraga, 26 I. & N. Dec. at 849; see also, e.g., In re Grazley, 14 I. & N. Dec.\\n330, 333 (BIA 1973).\\n 5\\n\\f Case: 17-60345 Document: 00514872705 Page: 6 Date Filed: 03/14/2019\\n\\n\\n\\n No. 17-60345\\napplication of Diaz-Lizarraga violates due process. But before we reach the\\nmerits of that argument, we must decide two threshold questions: whether he\\nwaived the issue and whether we have jurisdiction.\\n\\n A.\\n “Generally speaking, a [party] waives an issue if he fails to adequately\\nbrief it.” United States v. Martinez, 263 F.3d 436, 438 (5th Cir. 2001). That\\n“rule is a prudential construct that requires the exercise of discretion.” Id.\\n(internal quotation marks and citation omitted). Federal Rule of Appellate\\nProcedure 28(a)(8)(A) instructs a party to brief his “contentions and the rea-\\nsons for them, with citations to the authorities and parts of the record on which\\nthe [party] relies.” Still, this court has the discretion to consider inadequately\\nbriefed claims and has done so. See, e.g., Martinez, 263 F.3d at 438.\\n\\n Monteon-Camargo first contended that the BIA erred in retroactively\\napplying Diaz-Lizarraga in his supplemental brief, devoting just over a page\\nto the theory and citing no authorities. But both parties have filed supple-\\nmental letters addressing the issue and providing authorities.\\n\\n Despite the sparse briefing, we exercise our discretion to consider\\nMonteon-Camargo’s retroactivity claim. Three of our sister circuits have held\\nthat the BIA’s revised CIMT definition may not be retroactively applied to\\npredicate offenses committed before Diaz-Lizarraga was issued. 9 And the\\ngovernment has apparently adopted that position, as well, based on a response\\n\\n\\n 9 Garcia-Martinez v. Sessions, 886 F.3d 1291 (9th Cir. 2018); Obeya v. Sessions,\\n884 F.3d 442 (2d Cir. 2018); Lucio-Rayos v. Sessions, 875 F.3d 573 (10th Cir. 2017). In Lucio-\\nRayos, the Tenth Circuit explained that “after the BIA’s decision in this case, the BIA updated\\nits definition of theft offenses that qualify as a CIMT.” Lucio-Rayos, 875 F.3d at 578 (internal\\nquotation marks and citation omitted). But “[t]hat new definition . . . does not apply retroac-\\ntively here . . . because a revised rule adopted by the BIA in the exercise of its delegated\\nlegislative policymaking authority is presumed to apply prospectively only to cases initiated\\nafter its issuance.” Id.\\n 6\\n\\f Case: 17-60345 Document: 00514872705 Page: 7 Date Filed: 03/14/2019\\n\\n\\n\\n No. 17-60345\\nto a certiorari petition filed November 9, 2018. 10 We are also satisfied that the\\nparties have adequately presented their positions in the supplemental letters,\\nmaking it appropriate to decide the issue.\\n\\n B.\\n The government contends that we do not have jurisdiction to decide\\nMonteon-Camargo’s retroactivity claim, averring that judicial review is un-\\navailable under § 1252(d)(1) because Monteon-Camargo did not present that\\nclaim to the BIA. 11 “Judicial review of a final removal order is only available\\nif ‘the alien has exhausted all administrative remedies available to the alien\\nas of right.’” Vazquez v. Sessions, 885 F.3d 862, 868 (5th Cir. 2018) (quoting\\n8 U.S.C. § 1252(d)(1)). That exhaustion requirement is “mandatory and juris-\\ndictional.” Omari v. Holder, 562 F.3d 314, 324 (5th Cir. 2009) (emphasis omit-\\nted). “An alien fails to exhaust his administrative remedies with respect to an\\nissue when the issue is not raised in the first instance before the BIA.” Vaz-\\nquez, 885 F.3d at 868 (internal quotation marks, alteration, and citation omit-\\nted). “[T]o satisfy the exhaustion requirement . . . a petitioner must ‘raise,’\\n‘present,’ or ‘mention’ an issue to the BIA” in his brief to the Board. Id. (citing\\nOmari, 562 F.3d at 321).\\n\\n Due process claims, however, are generally exempt from the exhaustion\\ndoctrine because they are not within the purview of the BIA. Anwar v. INS,\\n\\n\\n\\n 10 Br. for the Resp’t in Opp’n at 2–3, Lucio-Rayos v. Whitaker (No. 18-64), 2018 WL\\n5920369 (internal quotation marks and citation omitted) (observing that for “removal pro-\\nceedings [that] were initiated” before Diaz-Lizarraga, “theft offense[s] constituted” CIMTs\\nonly if they “required the defendant to act with the intent to permanently deprive an owner\\nof property”).\\n 11 The government’s only response to Monteon-Camargo’s retroactivity claim has been\\nthat this court lacks jurisdiction. The government posits that Monteon-Camargo “did not\\npresent that argument to the agency and this Court lacks jurisdiction to review that argu-\\nment in the first instance” under 8 U.S.C. § 1252(d)(1).\\n 7\\n\\f Case: 17-60345 Document: 00514872705 Page: 8 Date Filed: 03/14/2019\\n\\n\\n\\n No. 17-60345\\n116 F.3d 140, 144 n.4 (5th Cir. 1997) (citations omitted). “[W]hen a petitioner’s\\ndue process claim does not assert a procedural error correctable by the BIA, it\\nis not subject to an exhaustion requirement.” Lopez De Jesus v. INS, 312 F.3d\\n155, 162 n.47 (5th Cir. 2002).\\n\\n Monteon-Camargo raises a due process challenge to the BIA’s decision,\\ncontending that Diaz-Lizarraga cannot apply retroactively because of “the due\\nprocess interests of fair notice.” The government counters that retroactivity\\nclaims are not per se constitutional due process claims that the BIA is unable\\nto correct. And Monteon-Camargo, the government suggests, is alleging “pro-\\ncedural error,” Falek v. Gonzales, 475 F.3d 285, 289−90 (5th Cir. 2007) (inter-\\nnal quotation marks and citation omitted), because his “supplemental brief\\ndoes not mention the [C]onstitution, let alone establish that [his retroactivity\\nclaim] is the type of argument that the Board is unable to review.” The gov-\\nernment concludes that under Falek, Monteon-Camargo needed to exhaust his\\nretroactivity claim before the Board.\\n\\n But unlike in Falek, id., Monteon-Camargo presses a constitutional\\nclaim, contending that retroactively applying Diaz-Lizarraga compromises his\\n“‘due process interests in fair notice, reasonable reliance, and settled expec-\\ntations’” (quoting De Niz Robles v. Lynch, 803 F.3d 1165, 1169 (10th Cir. 2015)\\n(Gorsuch, J.)). 12 Accordingly, his retroactivity claim “is not subject to an ex-\\nhaustion requirement,” Lopez De Jesus, 312 F.3d at 162 n.47, and we have\\njurisdiction to consider it.\\n\\n\\n\\n\\n 12 Compare Lopez De Jesus, 312 F.3d at 162 (recognizing an exception to the exhaus-\\ntion requirement where a BIA decision applied a statutory amendment retroactively, thus\\nrendering an alien ineligible for a waiver of inadmissibility, and the alien challenged the\\nretroactive application as a violation of “his constitutional rights to fair notice and due\\nprocess”).\\n 8\\n\\f Case: 17-60345 Document: 00514872705 Page: 9 Date Filed: 03/14/2019\\n\\n\\n\\n No. 17-60345\\n C.\\n That takes us to the merits. “[T]he leading case on administrative\\nretroactivity” instructs that any disadvantages from the “‘retroactive effect[s]’”\\nof deciding a “‘case of first impression . . . must be balanced against the mis-\\nchief of producing a result which is contrary to a statutory design or to legal\\nand equitable principles.’” Microcomputer Tech. Inst. v. Riley, 139 F.3d 1044,\\n1050 (5th Cir. 1998) (quoting SEC v. Chenery Corp., 332 U.S. 194, 203 (1947)).\\nTo apply that instruction, this court “balance[s] the ills of retroactivity against\\nthe disadvantages of prospectivity.” Id. 13 “If that mischief [of prospectivity] is\\ngreater than the ill effect of the retroactive application of a new standard, it is\\nnot the type of retroactivity which is condemned by law.” Chenery, 332 U.S.\\nat 203. We must thus balance the ills of applying the BIA’s new interpretation\\nof which thefts constitute CIMTs against the disadvantages of applying the\\nchange solely to predicate offenses adjudicated after Diaz-Lizarraga.\\n\\n Because the retroactivity issue was first raised in the supplemental\\nbriefing, the various briefs say little about the disadvantages of retroactivity\\nversus prospectivity. There are, however, some obvious disadvantages. Crim-\\ninal defendants may have pleaded guilty of crimes that they rightly thought,\\nbased on the Board’s prior position, did not constitute CIMTs. Accordingly,\\nthey may have entered pleas believing that they would not suffer adverse im-\\nmigration consequences as a result. Retroactively applying Diaz-Lizarraga\\nthus would compromise the “familiar [due process] considerations of fair\\nnotice, reasonable reliance, and settled expectations.” Landgraf v. USI Film\\n\\n\\n\\n 13 Other circuits, by contrast, apply “variously articulated factors,” usually “the five\\nfactors articulated in Retail, Wholesale & Dep’t Store Union v. NLRB, 466 F.2d 380, 390 (D.C.\\nCir. 1972),” to “measure [the] unfairness to the parties against the ‘mischief’ of allowing the\\nprevious . . . interpretation to stand.” Microcomputer Tech. Inst., 139 F.3d at 1050 (quoting\\nRetail, Wholesale & Dep’t Store Union, 466 F.2d at 390).\\n 9\\n\\f Case: 17-60345 Document: 00514872705 Page: 10 Date Filed: 03/14/2019\\n\\n\\n\\n No. 17-60345\\nProds., 511 U.S. 244, 270 (1994).\\n\\n The change in the Board’s guidance, moreover, was significant: It added\\nan entirely new category of theft offenses to those considered CIMTs. In Diaz-\\nLizarraga, the Board recognized that it was drastically changing the land-\\nscape, observing that it was “updat[ing]” what had been its position “[f]rom\\n[its] earliest days.” Diaz-Lizarraga, 26 I. & N. Dec. at 849, 852. Applying such\\na broad “new rule[] of general applicability” to prior conduct contravenes basic\\npresumptions about our legislative system. De Niz Robles, 803 F.3d at 1169.\\nA “presumption of prospectivity attaches to Congress’s own work,” and it\\nshould generally attach when an agency “exercise[s] delegated legislative\\n. . . authority.” Id. at 1171−72.\\n\\n Though there are multiple disadvantages to applying it retroactively, the\\ngovernment has not identified a single disadvantage of applying Diaz-\\nLizarraga only prospectively. We conclude that the definition of CIMTs an-\\nnounced in Diaz-Lizarraga may be applied only to crimes committed after that\\ndecision issued. The BIA erred in applying its new definition to Monteon-\\nCamargo’s conviction of attempted theft.\\n\\n The petition for review is GRANTED. The order is REVERSED and\\nREMANDED for further proceedings. 14\\n\\n\\n\\n\\n 14 We DENY, as moot, Monteon-Camargo’s petition for review of the BIA’s denial of\\nhis motion to reopen and reconsider. See Arce-Vences v. Mukasey, 512 F.3d 167, 173 n.1 (5th\\nCir. 2007) (denying as moot a petition for review of the BIA’s denial of a motion to reopen\\nwhere the court granted the petition for review of the original removal order).\\n 10\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1087,"cells":{"id":{"kind":"number","value":4599961,"string":"4,599,961"},"name":{"kind":"string","value":"State of TEXAS, Plaintiff-Appellee, v. ALABAMA-COUSHATTA TRIBE OF TEXAS, Defendant-Appellant."},"name_abbreviation":{"kind":"string","value":"State of Texas v. Alabama-Coushatta Tribe of TX"},"decision_date":{"kind":"string","value":"2019-03-14"},"docket_number":{"kind":"string","value":"18-40116"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Smith, Duncan, Engelhardt\", \"parties\": \"\", \"opinions\": [{\"author\": \"JERRY E. SMITH, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 18-40116 Document: 00514873577 Page: 1 Date Filed: 03/14/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n No. 18-40116 March 14, 2019\\n Lyle W. Cayce\\n Clerk\\n\\n\\nSTATE OF TEXAS,\\n\\n Plaintiff−Appellee,\\n\\nversus\\n\\nALABAMA-COUSHATTA TRIBE OF TEXAS,\\n\\n Defendant−Appellant.\\n\\n\\n\\n\\n Appeal from the United States District Court\\n for the Eastern District of Texas\\n\\n\\n\\n\\nBefore SMITH, DUNCAN, and ENGELHARDT, Circuit Judges.\\nJERRY E. SMITH, Circuit Judge:\\n\\n For almost thirty years, the State of Texas and one of its Indian tribes,\\nthe Alabama-Coushatta Tribe (the “Tribe”), have disputed the impact of two\\nfederal statutes on the Tribe’s ability to conduct gaming on the Tribe’s reser-\\nvation. The first statute, the Ysleta del Sur Pueblo and Alabama and\\n\\f Case: 18-40116 Document: 00514873577 Page: 2 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\nCoushatta Indian Tribes of Texas Restoration Act 1 (the “Restoration Act”),\\nrestored the Tribe’s status as a federally-recognized tribe and limited its gam-\\ning operations according to state law. The second, the Indian Gaming Regula-\\ntory Act (“IGRA”), 25 U.S.C. §§ 2701–2721, broadly “establish[ed] . . . Federal\\nstandards for gaming on Indian lands.” Id. § 2702(3).\\n\\n Soon after IGRA was enacted, this court determined that the Restoration\\nAct and IGRA conflict and that the Restoration Act governs the Tribe’s gaming\\nactivities. See Ysleta del sur Pueblo v. Texas (“Ysleta I”), 36 F.3d 1325, 1335\\n(5th Cir. 1994). Several years later, when the Tribe was conducting gaming\\noperations in violation of Texas law, the district court permanently enjoined\\nthat activity as a violation of the Restoration Act.\\n\\n The Supreme Court then decided National Cable & Telecommunications\\nAss’n v. Brand X Internet Services, 545 U.S. 967 (2005), and City of Arlington\\nv. FCC, 569 U.S. 290 (2013). And the National Indian Gaming Commission\\n(“NIGC”), which administers IGRA, held, contrary to Ysleta I, that IGRA gov-\\nerns the Tribe’s gaming activity. Citing those changes in the law, the Tribe\\nasked the district court to dissolve the permanent injunction. The district\\ncourt refused, the Tribe appeals, and we affirm.\\n\\n I.\\n A.\\n In 1987, Congress passed the Restoration Act to restore “the Federal\\nrecognition of” both the Ysleta del Sur Pueblo (the “Pueblo,” an Indian tribe in\\nfar west Texas) and the Tribe. Pub. L. No. 100-89, §§ 103(a), 203(a), 101 Stat.\\n\\n\\n\\n 1 Pub. L. No. 100-89, §§ 201–07, 101 Stat. 666 (Aug. 18, 1987). The U.S. Code was\\nupdated while this case was pending in district court and now omits the Restoration Act,\\nwhich was previously codified at 25 U.S.C. § 731 et seq. Though no longer codified, the\\nRestoration Act is still in effect.\\n 2\\n\\f Case: 18-40116 Document: 00514873577 Page: 3 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\nat 667, 670. 2 The Restoration Act’s final section regulates gaming on the\\nTribe’s reservation and lands. It provides that “[a]ll gaming activities which\\nare prohibited by the laws of the State of Texas are hereby prohibited on the\\nreservation and on the lands of the tribe.” Id. § 207(a), 101 Stat. at 672. 3 It\\nbars Texas from asserting regulatory control over otherwise legal gaming on\\nthe Tribe’s reservation and lands. Id. § 207(b), 101 Stat. at 672. It also gives\\n“the courts of the United States . . . exclusive jurisdiction over any offense in\\nviolation” of its gaming restriction and limits Texas to “bringing an action in\\nthe courts of the United States to enjoin violations of the provisions of this\\nsection.” Id. § 207(c), 101 Stat. at 672.\\n\\n Congress enacted IGRA the following year. Finding that “existing Fed-\\neral law d[id] not provide clear standards or regulations for the conduct of gam-\\ning on Indian lands,” 25 U.S.C. § 2701(3), Congress established “Federal stan-\\ndards for gaming on Indian lands, and . . . a National Indian Gaming Commis-\\nsion . . . to protect such gaming as a means of generating tribal revenue.” Id.\\n§ 2702(3). Though its stated purpose is broad, IGRA does not specifically\\n\\n\\n\\n 2Though the Pueblo has extensively litigated the same questions the Tribe raises, the\\nPueblo is not a party to this appeal but appears as amicus curiae.\\n 3That subsection concludes by explaining that the “provisions of this subsection are\\nenacted in accordance with the tribe’s request in Tribal Resolution No. T.C.-86-07.” Restor-\\nation Act § 207(a), 101 Stat. at 672. That resolution, in turn, was purportedly passed out of\\nconcern that the Restoration Act would not be enacted “unless the bill was amended to\\nprovide for direct application of state laws governing gaming and bingo on the [Tribe’s]\\nReservation.” The resolution “respectfully request[ed] [the Tribe’s] representatives” in Con-\\ngress amend the Restoration Act to “provide that all gaming, gambling, lottery, or bingo, as\\ndefined by the laws and administrative regulations of the state of Texas, shall be prohibited\\non the Tribe’s reservation or on Tribal land.”\\n The significance of the Restoration Act’s reference to the Tribe’s resolution is disputed.\\nThe state contends that the resolution represents a quid pro quo in which the Tribe agreed\\nto foreswear gaming for all time in exchange for passage of the Restoration Act. The Tribe\\nexamines the evolution of drafts of the Restoration Act and emphasizes that strong prohibi-\\ntory language was ultimately deleted. In any event, the stringent prohibition proposed by\\nthe resolution was not included.\\n 3\\n\\f Case: 18-40116 Document: 00514873577 Page: 4 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\npreempt the field of Indian gaming law.\\n\\n IGRA defines three classes of gaming that federally recognized tribes\\nmay offer and regulates each differently. Tribes have “exclusive jurisdiction”\\nover “class I gaming,” which consists of “social games solely for prizes of mini-\\nmal value or traditional forms of Indian gaming” associated with “tribal cere-\\nmonies or celebrations.” Id. §§ 2703(6), 2710(a)(1). “Class II gaming” includes\\n“the game of chance commonly known as bingo,” id. § 2703(7)(A)(i), and certain\\n“card games” either “explicitly authorized” or “not explicitly prohibited” by\\nstate law. Id. § 2703(7)(A)(ii)(I)–(II). Tribes have the authority to regulate\\nclass II gaming, provided that a tribe issues a self-regulatory ordinance\\nmeeting statutory criteria and the NIGC approves that ordinance. Id.\\n§ 2710(b)(1)–(2). “Class III gaming” includes all forms of gaming that are not\\nin class I or II. Class III gaming is lawful on Indian lands only if tribes secure\\nfederal administrative and state approval. Id. § 2703(8); see id. § 2710(d).\\nIGRA created the NIGC to administer its provisions, instructing the NIGC to\\n“promulgate such regulations and guidelines as it deems appropriate to\\nimplement the provisions of this chapter.” Id. § 2706(b)(10).\\n\\n B.\\n Notwithstanding the Restoration Act, Texas, the Tribe, and the Pueblo\\nhave long disputed whether IGRA applies to the Tribe and the Pueblo. Texas\\navers that IGRA’s permissive gaming structure is inconsistent with Sections\\n107(a) and 207(a) of the Restoration Act, which prohibit gaming that violates\\nTexas law on the Pueblo’s and Tribe’s lands, respectively. The Tribe maintains\\nthat IGRA permits it to conduct gaming operations according to IGRA’s three-\\nclass structure.\\n\\n This court first considered the relationship between the Restoration Act\\nand IGRA in Ysleta I. Under IGRA, the Pueblo had tried to negotiate a\\n 4\\n\\f Case: 18-40116 Document: 00514873577 Page: 5 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\ncompact with Texas to permit class III gaming. Texas refused, citing the Res-\\ntoration Act and insisting that state law prohibited the proposed games. The\\nPueblo sued to compel Texas to negotiate, and the district court granted sum-\\nmary judgment for the Pueblo.\\n\\n This court reversed, holding that “(1) the Restoration Act and IGRA\\nestablish different regulatory regimes with regard to gaming” and that “(2) the\\nRestoration Act prevails over IGRA when gaming activities proposed by the\\nYsleta del Sur Pueblo are at issue.” Ysleta I, 36 F.3d at 1332. With respect to\\nthe first ruling, this court found it “significant” that “the Restoration Act estab-\\nlishes a procedure for enforcement of § 107(a) which is fundamentally at odds\\nwith the concepts of IGRA.” Id. at 1334. Based on that finding, we had to\\ndetermine “which statute [to] appl[y].” Id. The Pueblo urged “that, to the\\nextent that a conflict between the two exists, IGRA impliedly repeals the\\nRestoration Act.” Id. at 1334–35. We rejected that theory, noting that implied\\nrepeals are disfavored and that generally “a specific statute will not be con-\\ntrolled or nullified by a general one.” Id. at 1335 (cleaned up). And “[w]ith\\nregard to gaming,” we continued, “the Restoration Act clearly is a specific\\nstatute, whereas IGRA is a general one.” Id. 4\\n\\n This court thus concluded “that [the Restoration Act]—and not IGRA—\\nwould govern the determination of whether gaming activities proposed by the\\nYsleta del Sur Pueblo are allowed under Texas law, which functions as sur-\\nrogate federal law.” Id. “If the [Pueblo] wishe[d] to vitiate [the restrictive\\ngaming provisions] of the Restoration Act,” we declared, “it will have to petition\\nCongress to amend or repeal the Restoration Act rather than merely comply\\n\\n\\n\\n\\n 4 “The former applies to two specifically named Indian tribes located in one particular\\nstate, and the latter applies to all tribes nationwide.” Ysleta I, 36 F.3d at 1335.\\n 5\\n\\f Case: 18-40116 Document: 00514873577 Page: 6 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\nwith the procedures of IGRA.” Id. 5\\n\\n C.\\n The Tribe was not a party in Ysleta I, but, “particularly with regard to\\nthe sections concerning gaming,” its Restoration Act is almost identical to the\\nPueblo’s. Id. at 1329 n.3. We thus suggested in Ysleta I that the Restoration\\nAct—and not IGRA—would govern the legality of any gaming operations of the\\nTribe. Despite the Restoration Act’s restrictions, the Tribe maintained a casino\\non its reservation after Ysleta I. And in 2001, the Tribe sued Texas, seeking\\ndeclaratory relief that its gaming was lawful under IGRA. See Alabama-\\nCoushatta Tribes of Tex. v. Texas, 208 F. Supp. 2d 670, 672 (E.D. Tex. 2002).\\nTexas counterclaimed, asking the district court permanently to enjoin the\\nTribe’s gaming activities based on Section 207 of the Restoration Act. Id.\\n\\n Relying on Ysleta I, the district court held that the Restoration Act gov-\\nerned the legality of the Tribe’s gaming activities. Id. at 677–78. And because\\nthose activities violated Texas law, the court permanently enjoined them in\\n2002. Id. at 681. This court affirmed, explaining that it was “bound by the\\ndetermination [in Ysleta I] that the Restoration Act precludes [the Tribe] from\\nconducting all gaming activities prohibited by Texas law on tribal lands.” Ala-\\nbama Coushatta Tribe of Tex. v. Texas, No. 02-41030, 2003 WL 21017542, at *1\\n(5th Cir. Apr. 16, 2003) (per curiam) (unpublished). 6\\n\\n\\n\\n\\n 5 Though Ysleta I arose in the context of the Pueblo’s trying to conduct IGRA class III\\ngaming, Ysleta I does not suggest that the conflict between the Restoration Act and IGRA is\\nlimited to class III gaming.\\n 6 We further ruled that Ysleta I’s holding that “the tribe was precluded from seeking\\nrelief under the IGRA” was binding, contrary to the Tribe’s assertion that it was dictum.\\nAlabama Coushatta Tribe of Tex., 2003 WL 21017542, at *1. We explained that the Ysleta I\\npanel was required to decide that question “because the Restoration Act placed greater limits\\non the tribe’s ability to conduct gaming operations” than did IGRA. Id.\\n 6\\n\\f Case: 18-40116 Document: 00514873577 Page: 7 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\n D.\\n The Tribe ceased all gaming for twelve years. But in 2015, it started the\\nprocess outlined by IGRA to secure NIGC’s approval to offer class II gaming.\\nAs IGRA requires, see 25 U.S.C. § 2710, the Tribe adopted an ordinance au-\\nthorizing class II bingo gaming—which Texas law permits in several forms 7—\\nand submitted it to NIGC’s Chairman for approval. 8 The Tribe concedes that\\nby seeking that approval, the Tribe was requesting NIGC’s formal administra-\\ntive determination of whether, contrary to Ysleta I, the tribe fell within IGRA’s\\nambit.\\n\\n The Chairman approved the ordinance via letter, explaining that “[n]oth-\\ning in the IGRA’s language or its legislative history indicates that the Tribe is\\noutside the scope of NIGC’s jurisdiction.” 9 He then determined that the Tribe’s\\nreservation—established through the Restoration Act—counts as “Indian\\nlands” under IGRA. Those findings, the Chairman continued, demonstrate\\nthat the Tribe’s “lands are eligible for gaming under IGRA.” The Chairman\\nthus concluded that the Tribe’s ordinance was “consistent with the require-\\nments of IGRA and NIGC regulations” and approved it. 10\\n\\n Despite initially observing that the Restoration Act and IGRA poten-\\ntially overlap, 11 the Chairman did not carefully consider whether the Restora-\\ntion Act limited the jurisdictional reach of IGRA. He opined, instead, that “the\\n\\n\\n 7 See, e.g., 16 Tex. Admin. Code §§ 402.100−.709.\\n 8 See 29 U.S.C. § 2710(b)(1)(B).\\n 9 Letter from Jonodev O. Chaudhuri, Chairman, Nat’l Indian Gaming Comm’n, to Nita\\nBattise, Chairperson, Alabama-Coushatta Tribe of Tex. (Oct. 8, 2015).\\n 10Id. The Chairman noted that the Department of the Interior interpreted IGRA as\\nimpliedly repealing the Restoration Act, but the Chairman did not adopt that conclusion.\\n 11See id. (noting that the Restoration Act “applies state gaming laws to the Tribe’s\\nlands, with a qualification,” thus raising the question “how to interpret the interface between\\nIGRA and the Restoration Act”).\\n 7\\n\\f Case: 18-40116 Document: 00514873577 Page: 8 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\nTribe possesses sufficient legal jurisdiction over its Restoration Act lands” for\\nIGRA to apply. In other words, the Chairman determined that the Restoration\\nAct does not constitute a “Federal law” that is a “specific[] prohibit[ion]” on the\\nTribe’s proposed gaming. 25 U.S.C. § 2710(b)(1)(A).\\n\\n With NIGC’s approval in hand, the Tribe began to develop Naskila\\nEntertainment Center (“Naskila”), a class II gaming facility offering electronic\\nbingo. Before it opened, the Tribe and Texas forged a prelitigation agreement\\nspecifying that the Tribe could operate Naskila pending a state inspection.\\nTexas committed to “advise the Tribe . . . whether the gambling operation\\nmeets the requirements of Texas law federalized in the Restoration Act” and\\nreserved the right to seek various forms of relief if it did not.\\n\\n Upon inspection, the state determined that the electronic bingo at Nas-\\nkila violated various provisions of Texas gaming law. Then the state revived\\nthe decades-old case—in which the district court had permanently enjoined the\\nTribe’s gaming activities that had violated the Restoration Act—by filing a\\nmotion for contempt, averring that the gaming at Naskila violated the 2002\\ninjunction. 12 Texas also sought a declaration “that IGRA does not apply to the\\nTribe because IGRA did not repeal the Restoration Act, and, accordingly,” the\\nTribe “may not conduct Class II IGRA gaming on its lands.” The Tribe, in turn,\\nmoved for relief from the 2002 injunction, contending that the “[NIGC’s]\\nauthoritative interpretation” of the Restoration Act and IGRA “both consti-\\ntutes a change in law and eliminates the sole legal basis for the injunction.”\\n\\n Texas moved for summary judgment on issues related to its motion for\\ncontempt, and the Tribe sought partial summary judgment on whether its\\n\\n\\n 12 The Tribe was the plaintiff (as it had sought a declaratory judgment that its gaming\\nactivities were lawful under IGRA), and Texas was the defendant. When Texas reopened the\\ncase, the court granted its motion to realign the parties, making Texas the plaintiff.\\n 8\\n\\f Case: 18-40116 Document: 00514873577 Page: 9 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\nbingo operations are class II gaming under IGRA. The district court granted\\nTexas’s motion “with respect to the State’s request for a declaration . . . that\\nthe Restoration Act, and consequently, Texas law, applies to the Tribe’s gam-\\ning activities.” The court refused to extend Chevron deference 13 to the NIGC’s\\nletter concluding that IGRA applied, and it denied the Tribe’s motion for relief\\nfrom the permanent injunction.\\n\\n The Tribe appeals, asking us to decide whether the district court abused\\nits discretion by refusing to defer to the NIGC’s determination that IGRA\\napplies to the Tribe’s gaming. The district court stayed its ruling pending\\nappeal. 14\\n\\n II.\\n District courts may “relieve a party . . . from a final judgment, order, or\\nproceeding” if “applying it prospectively is no longer equitable.” FED. R. CIV. P.\\n60(b), 60(b)(5). Where, as here, “the relief sought is dissolution or modification\\nof an injunction, the district court may grant a Rule 60(b)(5) motion when the\\nparty seeking relief can show a significant change in statutory or decisional\\nlaw.” Cooper v. Tex. Alcoholic Beverage Comm’n, 820 F.3d 730, 741 (5th Cir.\\n2016) (cleaned up). The “significant change” in this case, according to the\\nTribe, is the NIGC’s determination that the Tribe’s lands are eligible for\\ngaming under IGRA, combined with Brand X and City of Arlington.\\n\\n We review for abuse of discretion the denial of a Rule 60(b)(5) motion for\\nrelief from judgment. Moore v. Tangipahoa Par. Sch. Bd., 864 F.3d 401, 405\\n(5th Cir. 2017). “A district court abuses its discretion if it: (1) relies on clearly\\n\\n\\n\\n 13 See Chevron, U.S.A., Inc. v. Nat. Res. Def. Council, Inc., 567 U.S. 837 (1984).\\n 14 We have jurisdiction under 28 U.S.C. § 1292(a)(1), which allows for immediate\\nappeal of interlocutory orders “refusing to dissolve or modify injunctions.”\\n 9\\n\\f Case: 18-40116 Document: 00514873577 Page: 10 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\nerroneous factual findings; (2) relies on erroneous conclusions of law; or\\n(3) misapplies the law to the facts.” In re Volkswagen of Am., Inc., 545 F.3d\\n304, 310 (5th Cir. 2008) (en banc) (citation omitted). “It is not enough that\\ngranting the motion may have been permissible; instead, denial of relief must\\nhave been so unwarranted as to constitute an abuse of discretion.” Moore,\\n864 F.3d at 405 (internal quotation marks and citation omitted). While review\\nis highly deferential, “we review de novo any questions of law underlying the\\ndistrict court’s decision.” Frew v. Janek, 780 F.3d 320, 326 (5th Cir. 2015)\\n(internal quotation marks and citation omitted).\\n\\n III.\\n This case turns on whether a judicial precedent—holding that the\\nRestoration Act and IGRA conflict and that the former, not the latter, applies\\nto the Tribe’s gaming activity—or a later contrary agency interpretation should\\ncontrol. Brand X supplied the framework: “A court’s prior judicial construction\\nof a statute trumps an agency construction otherwise entitled to Chevron\\ndeference only if the prior court decision holds that its construction follows\\nfrom the unambiguous terms of the statute and thus leaves no room for agency\\ndiscretion.” Brand X, 545 U.S. at 982 (emphasis added). We must thus decide\\nwhether Ysleta I is “a judicial precedent holding that the statute unambigu-\\nously forecloses the agency’s interpretation.” Id. at 982–83.\\n\\n A.\\n Brand X’s rule that only a prior judicial interpretation adhering to the\\nunambiguous terms of the statute trumps an agency construction “follows from\\nChevron itself.” Id. at 982. “Chevron’s premise is that it is for agencies, not\\ncourts, to fill statutory gaps.” Id. (citation omitted). So to be faithful to that\\nprinciple, “judicial interpretations contained in precedents” must be held “to\\nthe same demanding Chevron step one standard that applies if the court is\\n 10\\n\\f Case: 18-40116 Document: 00514873577 Page: 11 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\nreviewing the agency’s construction on a blank slate.” Id. That means that a\\njudicial interpretation should prevail over a later conflicting agency interpre-\\ntation if the “court, employing traditional tools of statutory construction, as-\\ncertain[ed] that Congress had an intention on the precise question at issue.”\\nChevron, 467 U.S. at 843 n.9. 15\\n\\n Consequently, a prior judicial decision need not “say in so many magic\\nwords that its holding is the only permissible interpretation of the statute in\\norder for that holding to be binding on an agency.” Exelon Wind 1, L.L.C. v.\\nNelson, 766 F.3d 380, 398 (5th Cir. 2014) (quoting Fernandez v. Keisler,\\n502 F.3d 337, 347 (4th Cir. 2007)). 16 To the contrary, where “the exercise of\\nstatutory interpretation makes clear the court’s view that the plain language\\nof the statute was controlling and that there existed no room for contrary\\nagency interpretation,” the court’s interpretation should prevail. Id. (quoting\\nFernandez, 502 F.3d at 347–48). 17\\n\\n Instead of requiring the prior decision to have called the relevant statute\\n“unambiguous,” reviewing courts have looked for the contrary—whether the\\ndecision called the statute “ambiguous.” For example, this court recently held\\nthat an agency’s interpretation could prevail over a prior judicial interpreta-\\ntion because the latter had “expressly recognized that the court decided to come\\n\\n\\n 15Brand X, 545 U.S. at 985, offers the rule of lenity as an example of a “rule of con-\\nstruction” that a court might have applied which “requir[ed] it to conclude that the statute\\nwas unambiguous to reach its judgment.”\\n 16 See also Silva-Trevino v. Holder, 742 F.3d 197, 201–03 (5th Cir. 2014) (upholding a\\nprior judicial interpretation in the face of a conflicting agency interpretation even though the\\nprior decision did not say that the statute was “unambiguous” because the first court was\\n“confident” that “Congress ha[d] spoken directly to the statutory question at hand” based on\\nthe text of the statute and Congress’s use of the language in other statutes).\\n 17 See also Council for Urological Interests v. Burwell, 790 F.3d 212, 221 (D.C. Cir.\\n2015) (citation omitted) (“[A] statute may foreclose an agency's preferred interpretation\\ndespite such textual ambiguities if its structure, legislative history, or purpose makes clear\\nwhat its text leaves opaque.”).\\n 11\\n\\f Case: 18-40116 Document: 00514873577 Page: 12 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\ndown on one side of a complex debate.” 18 And where other circuits have de-\\nferred to an agency’s interpretation under Brand X, those courts have “empha-\\nsize[d] that their prior decisions also noted ambiguity in the text at issue.” See\\nExelon Wind 1, 766 F.3d at 398 (collecting citations). 19\\n\\n B.\\n Ysleta I did not find “ambiguity in the text at issue.” Id. Instead, after\\napplying canons of construction and legislative history to § 107(a) and (c) of the\\nPueblo’s Restoration Act—which corresponds to § 207(a) and (c) in the\\nTribe’s—this court concluded that “the Restoration Act and IGRA establish\\n. . . fundamentally different regimes.” Ysleta I, 36 F.3d at 1334. Indeed, this\\ncourt was left with “the unmistakable conclusion that Congress—and the\\nTribe—intended for Texas’ gaming laws and regulations to operate as surro-\\ngate federal law on the Tribe’s reservation in Texas.” Id. In other words, this\\ncourt summarized, “(1) the Restoration Act and IGRA establish different regu-\\nlatory regimes with regard to gaming, [and] (2) the Restoration Act prevails\\nover IGRA when gaming activities proposed by [the Pueblo or Tribe] are at\\nissue.” Id. at 1332.\\n\\n Additionally, we cited evidence that Congress did not intend for IGRA to\\napply to all Indian gaming. 20 Moreover, we specifically rejected the theory that\\n\\n\\n 18 Acosta v. Hensel Phelps Constr. Co., 909 F.3d 723, 738 (5th Cir. 2018) (internal\\nquotation marks omitted) (quoting Melerine v. Avondale Shipyards, Inc., 659 F.2d 706, 710\\n(5th Cir. Unit A Oct. 1981) (discussing the “complex dispute” among courts)).\\n 19A plurality of the Supreme Court has likewise held that, under Brand X, a court\\nneed not have said that the statute it was interpreting was “unambiguous.” Instead, “[i]f a\\ncourt, employing traditional tools of statutory construction, ascertains that Congress had an\\nintention on the precise question at issue, that intention is the law and must be given effect.”\\nUnited States v. Home Concrete & Supply, LLC, 566 U.S. 478, 488 (2012) (plurality opinion)\\n(quoting Chevron, 467 U.S. at 843 n.9).\\n 20 See Ysleta I, 36 F.3d at 1335 (citing later enactments expressly excluding certain\\ntribes from IGRA’s coverage as evidence of “a clear intention on Congress’ part that IGRA is\\n 12\\n\\f Case: 18-40116 Document: 00514873577 Page: 13 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\n“to the extent that a conflict between the two exists, IGRA impliedly repeals\\nthe Restoration Act.” Ysleta I, 36 F.3d at 1335. Repudiating that interpreta-\\ntion, we cited (1) the presumption against implied repeals and (2) the canon\\nthat a specific statute controls over a general statute. Id. With respect to the\\nsecond, we noted that the Restoration Act was “clearly” the specific statute,\\n“whereas IGRA is a general one.” Id.\\n\\n The Tribe counters that, for two reasons, Ysleta I does not foreclose the\\nNIGC’s determination that IGRA applies to the Tribe. First, the Tribe empha-\\nsizes that Ysleta I’s holding “was based on nontextual cues from legislative\\nhistory and canons of construction” and thus could not have “follow[ed] from\\nthe unambiguous terms of the statute.” Brand X, 545 U.S. at 982. That rea-\\nsoning disregards the fact that the Brand X inquiry stems from Chevron step\\none and requires the reviewing court to apply “traditional tools of statutory\\ninterpretation”—like the canons and legislative history—to determine whether\\nCongress has spoken to the precise issue. See Chevron, 467 U.S. at 843 n.9.\\nAnd when “the canons supply an answer, Chevron leaves the stage.” Epic Sys.\\nCorp. v. Lewis, 138 S. Ct. 1612, 1630 (2018) (internal quotation marks and\\ncitation omitted).\\n\\n Second, the Tribe asserts that Ysleta I “never had occasion to determine\\nwhether the Restoration Act constitutes a federal law that specifically prohib-\\nits [c]lass II gaming on Indian lands under IGRA.” That misses what Ysleta I\\ndid hold—that the Restoration Act’s gaming provisions, and not IGRA, provide\\nthe framework for deciding the legality of any and all gaming by the Pueblo\\nand the Tribe on their Restoration Act lands. Ysleta I, 36 F.3d at 1332. 21\\n\\n\\n\\nnot to be the one and only statute addressing the subject of gaming on Indian lands”).\\n The Tribe suggests that the Restoration Act’s application of Texas laws to the Tribe’s\\n 21\\n\\ngambling is somewhat empty because Texas does not “prohibit” gaming as defined in\\n 13\\n\\f Case: 18-40116 Document: 00514873577 Page: 14 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\n In sum, Brand X teaches that a court should not defer to an agency’s\\ninterpretation of a statute if a “judicial precedent hold[s] that the statute un-\\nambiguously forecloses the agency’s interpretation.” Brand X, 545 U.S.\\nat 982–83. That requires us to apply Chevron step one to a prior judicial inter-\\npretation and to determine whether that court employed traditional tools of\\nstatutory interpretation and found that Congress spoke to the precise issue.\\nThat is what Ysleta I did in holding that “the Restoration Act prevails over\\nIGRA when gaming activities proposed by [the Pueblo or Tribe] are at issue.”\\nYsleta I, 36 F.3d at 1332. Consequently, the NIGC’s decision that IGRA applies\\nto the Tribe does not displace Ysleta I. We thus reaffirm that the Restoration\\nAct and the Texas law it invokes—and not IGRA—govern the permissibility of\\ngaming operations on the Tribe’s lands. 22 IGRA does not apply to the Tribe,\\nand the NIGC does not have jurisdiction over the Tribe.\\n\\n The district court did not abuse its discretion in denying relief from the\\npermanent injunction. The order denying the motion for relief from judgment\\nis AFFIRMED.\\n\\n\\n\\n\\nCalifornia v. Cabazon Band of Mission Indians, 480 U.S. 202 (1987). This court expressly\\nrejected that theory in Ysleta I, 36 F.3d at 1333−34, holding that “Congress did not enact the\\nRestoration Act with an eye toward Cabazon Band.” Instead, we were “left with the unmis-\\ntakable conclusion that Congress—and the [Pueblo]—intended for Texas’ gaming laws and\\nregulations to operate as surrogate federal law on the [Pueblo’s] reservation in Texas.” Id.\\nat 1334.\\n 22The Tribe alternatively contends that Ysleta I should be overruled. The rule of\\norderliness forbids us from reaching that issue. See Jacobs v. Nat’l Drug Intelligence Ctr.,\\n548 F.3d 375, 378 (5th Cir. 2008) (citations omitted) (“[O]ne panel of [this] court may not\\noverturn another panel’s decision, absent an intervening change in the law, such as by a\\nstatutory amendment, or the Supreme Court, or [the] en banc court.”).\\n 14\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4377214/\", \"author_raw\": \"JERRY E. SMITH, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"SMITH"},"judge2":{"kind":"string","value":"DUNCAN"},"judge3":{"kind":"string","value":"ENGELHARDT"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4599961/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: State of TEXAS, Plaintiff-Appellee, v. ALABAMA-COUSHATTA TRIBE OF TEXAS, Defendant-Appellant.\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-14\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 18-40116 Document: 00514873577 Page: 1 Date Filed: 03/14/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\n United States Court of Appeals\n Fifth Circuit\n\n FILED\n No. 18-40116 March 14, 2019\n Lyle W. Cayce\n Clerk\n\n\nSTATE OF TEXAS,\n\n Plaintiff−Appellee,\n\nversus\n\nALABAMA-COUSHATTA TRIBE OF TEXAS,\n\n Defendant−Appellant.\n\n\n\n\n Appeal from the United States District Court\n for the Eastern District of Texas\n\n\n\n\nBefore SMITH, DUNCAN, and ENGELHARDT, Circuit Judges.\nJERRY E. SMITH, Circuit Judge:\n\n For almost thirty years, the State of Texas and one of its Indian tribes,\nthe Alabama-Coushatta Tribe (the “Tribe”), have disputed the impact of two\nfederal statutes on the Tribe’s ability to conduct gaming on the Tribe’s reser-\nvation. The first statute, the Ysleta del Sur Pueblo and Alabama and\n\f Case: 18-40116 Document: 00514873577 Page: 2 Date Filed: 03/14/2019\n\n\n\n No. 18-40116\nCoushatta Indian Tribes of Texas Restoration Act 1 (the “Restoration Act”),\nrestored the Tribe’s status as a federally-recognized tribe and limited its gam-\ning operations according to state law. The second, the Indian Gaming Regula-\ntory Act (“IGRA”), 25 U.S.C. §§ 2701–2721, broadly “establish[ed] . . . Federal\nstandards for gaming on Indian lands.” Id. § 2702(3).\n\n Soon after IGRA was enacted, this court determined that the Restoration\nAct and IGRA conflict and that the Restoration Act governs the Tribe’s gaming\nactivities. See Ysleta del sur Pueblo v. Texas (“Ysleta I”), 36 F.3d 1325, 1335\n(5th Cir. 1994). Several years later, when the Tribe was conducting gaming\noperations in violation of Texas law, the district court permanently enjoined\nthat activity as a violation of the Restoration Act.\n\n The Supreme Court then decided National Cable & Telecommunications\nAss’n v. Brand X Internet Services, 545 U.S. 967 (2005), and City of Arlington\nv. FCC, 569 U.S. 290 (2013). And the National Indian Gaming Commission\n(“NIGC”), which administers IGRA, held, contrary to Ysleta I, that IGRA gov-\nerns the Tribe’s gaming activity. Citing those changes in the law, the Tribe\nasked the district court to dissolve the permanent injunction. The district\ncourt refused, the Tribe appeals, and we affirm.\n\n I.\n A.\n In 1987, Congress passed the Restoration Act to restore “the Federal\nrecognition of” both the Ysleta del Sur Pueblo (the “Pueblo,” an Indian tribe in\nfar west Texas) and the Tribe. Pub. L. No. 100-89, §§ 103(a), 203(a), 101 Stat.\n\n\n\n 1 Pub. L. No. 100-89, §§ 201–07, 101 Stat. 666 (Aug. 18, 1987). The U.S. Code was\nupdated while this case was pending in district court and now omits the Restoration Act,\nwhich was previously codified at 25 U.S.C. § 731 et seq. Though no longer codified, the\nRestoration Act is still in effect.\n 2\n\f Case: 18-40116 Document: 00514873577 Page: 3 Date Filed: 03/14/2019\n\n\n\n No. 18-40116\nat 667, 670. 2 The Restoration Act’s final section regulates gaming on the\nTribe’s reservation and lands. It provides that “[a]ll gaming activities which\nare prohibited by the laws of the State of Texas are hereby prohibited on the\nreservation and on the lands of the tribe.” Id. § 207(a), 101 Stat. at 672. 3 It\nbars Texas from asserting regulatory control over otherwise legal gaming on\nthe Tribe’s reservation and lands. Id. § 207(b), 101 Stat. at 672. It also gives\n“the courts of the United States . . . exclusive jurisdiction over any offense in\nviolation” of its gaming restriction and limits Texas to “bringing an action in\nthe courts of the United States to enjoin violations of the provisions of this\nsection.” Id. § 207(c), 101 Stat. at 672.\n\n Congress enacted IGRA the following year. Finding that “existing Fed-\neral law d[id] not provide clear standards or regulations for the conduct of gam-\ning on Indian lands,” 25 U.S.C. § 2701(3), Congress established “Federal stan-\ndards for gaming on Indian lands, and . . . a National Indian Gaming Commis-\nsion . . . to protect such gaming as a means of generating tribal revenue.” Id.\n§ 2702(3). Though its stated purpose is broad, IGRA does not specifically\n\n\n\n 2Though the Pueblo has extensively litigated the same questions the Tribe raises, the\nPueblo is not a party to this appeal but appears as amicus curiae.\n 3That subsection concludes by explaining that the “provisions of this subsection are\nenacted in accordance with the tribe’s request in Tribal Resolution No. T.C.-86-07.” Restor-\nation Act § 207(a), 101 Stat. at 672. That resolution, in turn, was purportedly passed out of\nconcern that the Restoration Act would not be enacted “unless the bill was amended to\nprovide for direct application of state laws governing gaming and bingo on the [Tribe’s]\nReservation.” The resolution “respectfully request[ed] [the Tribe’s] representatives” in Con-\ngress amend the Restoration Act to “provide that all gaming, gambling, lottery, or bingo, as\ndefined by the laws and administrative regulations of the state of Texas, shall be prohibited\non the Tribe’s reservation or on Tribal land.”\n The significance of the Restoration Act’s reference to the Tribe’s resolution is disputed.\nThe state contends that the resolution represents a quid pro quo in which the Tribe agreed\nto foreswear gaming for all time in exchange for passage of the Restoration Act. The Tribe\nexamines the evolution of drafts of the Restoration Act and emphasizes that strong prohibi-\ntory language was ultimately deleted. In any event, the stringent prohibition proposed by\nthe resolution was not included.\n 3\n\f Case: 18-40116 Document: 00514873577 Page: 4 Date Filed: 03/14/2019\n\n\n\n No. 18-40116\npreempt the field of Indian gaming law.\n\n IGRA defines three classes of gaming that federally recognized tribes\nmay offer and regulates each differently. Tribes have “exclusive jurisdiction”\nover “class I gaming,” which consists of “social games solely for prizes of mini-\nmal value or traditional forms of Indian gaming” associated with “tribal cere-\nmonies or celebrations.” Id. §§ 2703(6), 2710(a)(1). “Class II gaming” includes\n“the game of chance commonly known as bingo,” id. § 2703(7)(A)(i), and certain\n“card games” either “explicitly authorized” or “not explicitly prohibited” by\nstate law. Id. § 2703(7)(A)(ii)(I)–(II). Tribes have the authority to regulate\nclass II gaming, provided that a tribe issues a self-regulatory ordinance\nmeeting statutory criteria and the NIGC approves that ordinance. Id.\n§ 2710(b)(1)–(2). “Class III gaming” includes all forms of gaming that are not\nin class I or II. Class III gaming is lawful on Indian lands only if tribes secure\nfederal administrative and state approval. Id. § 2703(8); see id. § 2710(d).\nIGRA created the NIGC to administer its provisions, instructing the NIGC to\n“promulgate such regulations and guidelines as it deems appropriate to\nimplement the provisions of this chapter.” Id. § 2706(b)(10).\n\n B.\n Notwithstanding the Restoration Act, Texas, the Tribe, and the Pueblo\nhave long disputed whether IGRA applies to the Tribe and the Pueblo. Texas\navers that IGRA’s permissive gaming structure is inconsistent with Sections\n107(a) and 207(a) of the Restoration Act, which prohibit gaming that violates\nTexas law on the Pueblo’s and Tribe’s lands, respectively. The Tribe maintains\nthat IGRA permits it to conduct gaming operations according to IGRA’s three-\nclass structure.\n\n This court first considered the relationship between the Restoration Act\nand IGRA in Ysleta I. Under IGRA, the Pueblo had tried to negotiate a\n 4\n\f Case: 18-40116 Document: 00514873577 Page: 5 Date Filed: 03/14/2019\n\n\n\n No. 18-40116\ncompact with Texas to permit class III gaming. Texas refused, citing the Res-\ntoration Act and insisting that state law prohibited the proposed games. The\nPueblo sued to compel Texas to negotiate, and the district court granted sum-\nmary judgment for the Pueblo.\n\n This court reversed, holding that “(1) the Restoration Act and IGRA\nestablish different regulatory regimes with regard to gaming” and that “(2) the\nRestoration Act prevails over IGRA when gaming activities proposed by the\nYsleta del Sur Pueblo are at issue.” Ysleta I, 36 F.3d at 1332. With respect to\nthe first ruling, this court found it “significant” that “the Restoration Act estab-\nlishes a procedure for enforcement of § 107(a) which is fundamentally at odds\nwith the concepts of IGRA.” Id. at 1334. Based on that finding, we had to\ndetermine “which statute [to] appl[y].” Id. The Pueblo urged “that, to the\nextent that a conflict between the two exists, IGRA impliedly repeals the\nRestoration Act.” Id. at 1334–35. We rejected that theory, noting that implied\nrepeals are disfavored and that generally “a specific statute will not be con-\ntrolled or nullified by a general one.” Id. at 1335 (cleaned up). And “[w]ith\nregard to gaming,” we continued, “the Restoration Act clearly is a specific\nstatute, whereas IGRA is a general one.” Id. 4\n\n This court thus concluded “that [the Restoration Act]—and not IGRA—\nwould govern the determination of whether gaming activities proposed by the\nYsleta del Sur Pueblo are allowed under Texas law, which functions as sur-\nrogate federal law.” Id. “If the [Pueblo] wishe[d] to vitiate [the restrictive\ngaming provisions] of the Restoration Act,” we declared, “it will have to petition\nCongress to amend or repeal the Restoration Act rather than merely comply\n\n\n\n\n 4 “The former applies to two specifically named Indian tribes located in one particular\nstate, and the latter applies to all tribes nationwide.” Ysleta I, 36 F.3d at 1335.\n 5\n\f Case: 18-40116 Document: 00514873577 Page: 6 Date Filed: 03/14/2019\n\n\n\n No. 18-40116\nwith the procedures of IGRA.” Id. 5\n\n C.\n The Tribe was not a party in Ysleta I, but, “particularly with regard to\nthe sections concerning gaming,” its Restoration Act is almost identical to the\nPueblo’s. Id. at 1329 n.3. We thus suggested in Ysleta I that the Restoration\nAct—and not IGRA—would govern the legality of any gaming operations of the\nTribe. Despite the Restoration Act’s restrictions, the Tribe maintained a casino\non its reservation after Ysleta I. And in 2001, the Tribe sued Texas, seeking\ndeclaratory relief that its gaming was lawful under IGRA. See Alabama-\nCoushatta Tribes of Tex. v. Texas, 208 F. Supp. 2d 670, 672 (E.D. Tex. 2002).\nTexas counterclaimed, asking the district court permanently to enjoin the\nTribe’s gaming activities based on Section 207 of the Restoration Act. Id.\n\n Relying on Ysleta I, the district court held that the Restoration Act gov-\nerned the legality of the Tribe’s gaming activities. Id. at 677–78. And because\nthose activities violated Texas law, the court permanently enjoined them in\n2002. Id. at 681. This court affirmed, explaining that it was “bound by the\ndetermination [in Ysleta I] that the Restoration Act precludes [the Tribe] from\nconducting all gaming activities prohibited by Texas law on tribal lands.” Ala-\nbama Coushatta Tribe of Tex. v. Texas, No. 02-41030, 2003 WL 21017542, at *1\n(5th Cir. Apr. 16, 2003) (per curiam) (unpublished). 6\n\n\n\n\n 5 Though Ysleta I arose in the context of the Pueblo’s trying to conduct IGRA class III\ngaming, Ysleta I does not suggest that the conflict between the Restoration Act and IGRA is\nlimited to class III gaming.\n 6 We further ruled that Ysleta I’s holding that “the tribe was precluded from seeking\nrelief under the IGRA” was binding, contrary to the Tribe’s assertion that it was dictum.\nAlabama Coushatta Tribe of Tex., 2003 WL 21017542, at *1. We explained that the Ysleta I\npanel was required to decide that question “because the Restoration Act placed greater limits\non the tribe’s ability to conduct gaming operations” than did IGRA. Id.\n 6\n\f Case: 18-40116 Document: 00514873577 Page: 7 Date Filed: 03/14/2019\n\n\n\n No. 18-40116\n D.\n The Tribe ceased all gaming for twelve years. But in 2015, it started the\nprocess outlined by IGRA to secure NIGC’s approval to offer class II gaming.\nAs IGRA requires, see 25 U.S.C. § 2710, the Tribe adopted an ordinance au-\nthorizing class II bingo gaming—which Texas law permits in several forms 7—\nand submitted it to NIGC’s Chairman for approval. 8 The Tribe concedes that\nby seeking that approval, the Tribe was requesting NIGC’s formal administra-\ntive determination of whether, contrary to Ysleta I, the tribe fell within IGRA’s\nambit.\n\n The Chairman approved the ordinance via letter, explaining that “[n]oth-\ning in the IGRA’s language or its legislative history indicates that the Tribe is\noutside the scope of NIGC’s jurisdiction.” 9 He then determined that the Tribe’s\nreservation—established through the Restoration Act—counts as “Indian\nlands” under IGRA. Those findings, the Chairman continued, demonstrate\nthat the Tribe’s “lands are eligible for gaming under IGRA.” The Chairman\nthus concluded that the Tribe’s ordinance was “consistent with the require-\nments of IGRA and NIGC regulations” and approved it. 10\n\n Despite initially observing that the Restoration Act and IGRA poten-\ntially overlap, 11 the Chairman did not carefully consider whether the Restora-\ntion Act limited the jurisdictional reach of IGRA. He opined, instead, that “the\n\n\n 7 See, e.g., 16 Tex. Admin. Code §§ 402.100−.709.\n 8 See 29 U.S.C. § 2710(b)(1)(B).\n 9 Letter from Jonodev O. Chaudhuri, Chairman, Nat’l Indian Gaming Comm’n, to Nita\nBattise, Chairperson, Alabama-Coushatta Tribe of Tex. (Oct. 8, 2015).\n 10Id. The Chairman noted that the Department of the Interior interpreted IGRA as\nimpliedly repealing the Restoration Act, but the Chairman did not adopt that conclusion.\n 11See id. (noting that the Restoration Act “applies state gaming laws to the Tribe’s\nlands, with a qualification,” thus raising the question “how to interpret the interface between\nIGRA and the Restoration Act”).\n 7\n\f Case: 18-40116 Document: 00514873577 Page: 8 Date Filed: 03/14/2019\n\n\n\n No. 18-40116\nTribe possesses sufficient legal jurisdiction over its Restoration Act lands” for\nIGRA to apply. In other words, the Chairman determined that the Restoration\nAct does not constitute a “Federal law” that is a “specific[] prohibit[ion]” on the\nTribe’s proposed gaming. 25 U.S.C. § 2710(b)(1)(A).\n\n With NIGC’s approval in hand, the Tribe began to develop Naskila\nEntertainment Center (“Naskila”), a class II gaming facility offering electronic\nbingo. Before it opened, the Tribe and Texas forged a prelitigation agreement\nspecifying that the Tribe could operate Naskila pending a state inspection.\nTexas committed to “advise the Tribe . . . whether the gambling operation\nmeets the requirements of Texas law federalized in the Restoration Act” and\nreserved the right to seek various forms of relief if it did not.\n\n Upon inspection, the state determined that the electronic bingo at Nas-\nkila violated various provisions of Texas gaming law. Then the state revived\nthe decades-old case—in which the district court had permanently enjoined the\nTribe’s gaming activities that had violated the Restoration Act—by filing a\nmotion for contempt, averring that the gaming at Naskila violated the 2002\ninjunction. 12 Texas also sought a declaration “that IGRA does not apply to the\nTribe because IGRA did not repeal the Restoration Act, and, accordingly,” the\nTribe “may not conduct Class II IGRA gaming on its lands.” The Tribe, in turn,\nmoved for relief from the 2002 injunction, contending that the “[NIGC’s]\nauthoritative interpretation” of the Restoration Act and IGRA “both consti-\ntutes a change in law and eliminates the sole legal basis for the injunction.”\n\n Texas moved for summary judgment on issues related to its motion for\ncontempt, and the Tribe sought partial summary judgment on whether its\n\n\n 12 The Tribe was the plaintiff (as it had sought a declaratory judgment that its gaming\nactivities were lawful under IGRA), and Texas was the defendant. When Texas reopened the\ncase, the court granted its motion to realign the parties, making Texas the plaintiff.\n 8\n\f Case: 18-40116 Document: 00514873577 Page: 9 Date Filed: 03/14/2019\n\n\n\n No. 18-40116\nbingo operations are class II gaming under IGRA. The district court granted\nTexas’s motion “with respect to the State’s request for a declaration . . . that\nthe Restoration Act, and consequently, Texas law, applies to the Tribe’s gam-\ning activities.” The court refused to extend Chevron deference 13 to the NIGC’s\nletter concluding that IGRA applied, and it denied the Tribe’s motion for relief\nfrom the permanent injunction.\n\n The Tribe appeals, asking us to decide whether the district court abused\nits discretion by refusing to defer to the NIGC’s determination that IGRA\napplies to the Tribe’s gaming. The district court stayed its ruling pending\nappeal. 14\n\n II.\n District courts may “relieve a party . . . from a final judgment, order, or\nproceeding” if “applying it prospectively is no longer equitable.” FED. R. CIV. P.\n60(b), 60(b)(5). Where, as here, “the relief sought is dissolution or modification\nof an injunction, the district court may grant a Rule 60(b)(5) motion when the\nparty seeking relief can show a significant change in statutory or decisional\nlaw.” Cooper v. Tex. Alcoholic Beverage Comm’n, 820 F.3d 730, 741 (5th Cir.\n2016) (cleaned up). The “significant change” in this case, according to the\nTribe, is the NIGC’s determination that the Tribe’s lands are eligible for\ngaming under IGRA, combined with Brand X and City of Arlington.\n\n We review for abuse of discretion the denial of a Rule 60(b)(5) motion for\nrelief from judgment. Moore v. Tangipahoa Par. Sch. Bd., 864 F.3d 401, 405\n(5th Cir. 2017). “A district court abuses its discretion if it: (1) relies on clearly\n\n\n\n 13 See Chevron, U.S.A., Inc. v. Nat. Res. Def. Council, Inc., 567 U.S. 837 (1984).\n 14 We have jurisdiction under 28 U.S.C. § 1292(a)(1), which allows for immediate\nappeal of interlocutory orders “refusing to dissolve or modify injunctions.”\n 9\n\f Case: 18-40116 Document: 00514873577 Page: 10 Date Filed: 03/14/2019\n\n\n\n No. 18-40116\nerroneous factual findings; (2) relies on erroneous conclusions of law; or\n(3) misapplies the law to the facts.” In re Volkswagen of Am., Inc., 545 F.3d\n304, 310 (5th Cir. 2008) (en banc) (citation omitted). “It is not enough that\ngranting the motion may have been permissible; instead, denial of relief must\nhave been so unwarranted as to constitute an abuse of discretion.” Moore,\n864 F.3d at 405 (internal quotation marks and citation omitted). While review\nis highly deferential, “we review de novo any questions of law underlying the\ndistrict court’s decision.” Frew v. Janek, 780 F.3d 320, 326 (5th Cir. 2015)\n(internal quotation marks and citation omitted).\n\n III.\n This case turns on whether a judicial precedent—holding that the\nRestoration Act and IGRA conflict and that the former, not the latter, applies\nto the Tribe’s gaming activity—or a later contrary agency interpretation should\ncontrol. Brand X supplied the framework: “A court’s prior judicial construction\nof a statute trumps an agency construction otherwise entitled to Chevron\ndeference only if the prior court decision holds that its construction follows\nfrom the unambiguous terms of the statute and thus leaves no room for agency\ndiscretion.” Brand X, 545 U.S. at 982 (emphasis added). We must thus decide\nwhether Ysleta I is “a judicial precedent holding that the statute unambigu-\nously forecloses the agency’s interpretation.” Id. at 982–83.\n\n A.\n Brand X’s rule that only a prior judicial interpretation adhering to the\nunambiguous terms of the statute trumps an agency construction “follows from\nChevron itself.” Id. at 982. “Chevron’s premise is that it is for agencies, not\ncourts, to fill statutory gaps.” Id. (citation omitted). So to be faithful to that\nprinciple, “judicial interpretations contained in precedents” must be held “to\nthe same demanding Chevron step one standard that applies if the court is\n 10\n\f Case: 18-40116 Document: 00514873577 Page: 11 Date Filed: 03/14/2019\n\n\n\n No. 18-40116\nreviewing the agency’s construction on a blank slate.” Id. That means that a\njudicial interpretation should prevail over a later conflicting agency interpre-\ntation if the “court, employing traditional tools of statutory construction, as-\ncertain[ed] that Congress had an intention on the precise question at issue.”\nChevron, 467 U.S. at 843 n.9. 15\n\n Consequently, a prior judicial decision need not “say in so many magic\nwords that its holding is the only permissible interpretation of the statute in\norder for that holding to be binding on an agency.” Exelon Wind 1, L.L.C. v.\nNelson, 766 F.3d 380, 398 (5th Cir. 2014) (quoting Fernandez v. Keisler,\n502 F.3d 337, 347 (4th Cir. 2007)). 16 To the contrary, where “the exercise of\nstatutory interpretation makes clear the court’s view that the plain language\nof the statute was controlling and that there existed no room for contrary\nagency interpretation,” the court’s interpretation should prevail. Id. (quoting\nFernandez, 502 F.3d at 347–48). 17\n\n Instead of requiring the prior decision to have called the relevant statute\n“unambiguous,” reviewing courts have looked for the contrary—whether the\ndecision called the statute “ambiguous.” For example, this court recently held\nthat an agency’s interpretation could prevail over a prior judicial interpreta-\ntion because the latter had “expressly recognized that the court decided to come\n\n\n 15Brand X, 545 U.S. at 985, offers the rule of lenity as an example of a “rule of con-\nstruction” that a court might have applied which “requir[ed] it to conclude that the statute\nwas unambiguous to reach its judgment.”\n 16 See also Silva-Trevino v. Holder, 742 F.3d 197, 201–03 (5th Cir. 2014) (upholding a\nprior judicial interpretation in the face of a conflicting agency interpretation even though the\nprior decision did not say that the statute was “unambiguous” because the first court was\n“confident” that “Congress ha[d] spoken directly to the statutory question at hand” based on\nthe text of the statute and Congress’s use of the language in other statutes).\n 17 See also Council for Urological Interests v. Burwell, 790 F.3d 212, 221 (D.C. Cir.\n2015) (citation omitted) (“[A] statute may foreclose an agency's preferred interpretation\ndespite such textual ambiguities if its structure, legislative history, or purpose makes clear\nwhat its text leaves opaque.”).\n 11\n\f Case: 18-40116 Document: 00514873577 Page: 12 Date Filed: 03/14/2019\n\n\n\n No. 18-40116\ndown on one side of a complex debate.” 18 And where other circuits have de-\nferred to an agency’s interpretation under Brand X, those courts have “empha-\nsize[d] that their prior decisions also noted ambiguity in the text at issue.” See\nExelon Wind 1, 766 F.3d at 398 (collecting citations). 19\n\n B.\n Ysleta I did not find “ambiguity in the text at issue.” Id. Instead, after\napplying canons of construction and legislative history to § 107(a) and (c) of the\nPueblo’s Restoration Act—which corresponds to § 207(a) and (c) in the\nTribe’s—this court concluded that “the Restoration Act and IGRA establish\n. . . fundamentally different regimes.” Ysleta I, 36 F.3d at 1334. Indeed, this\ncourt was left with “the unmistakable conclusion that Congress—and the\nTribe—intended for Texas’ gaming laws and regulations to operate as surro-\ngate federal law on the Tribe’s reservation in Texas.” Id. In other words, this\ncourt summarized, “(1) the Restoration Act and IGRA establish different regu-\nlatory regimes with regard to gaming, [and] (2) the Restoration Act prevails\nover IGRA when gaming activities proposed by [the Pueblo or Tribe] are at\nissue.” Id. at 1332.\n\n Additionally, we cited evidence that Congress did not intend for IGRA to\napply to all Indian gaming. 20 Moreover, we specifically rejected the theory that\n\n\n 18 Acosta v. Hensel Phelps Constr. Co., 909 F.3d 723, 738 (5th Cir. 2018) (internal\nquotation marks omitted) (quoting Melerine v. Avondale Shipyards, Inc., 659 F.2d 706, 710\n(5th Cir. Unit A Oct. 1981) (discussing the “complex dispute” among courts)).\n 19A plurality of the Supreme Court has likewise held that, under Brand X, a court\nneed not have said that the statute it was interpreting was “unambiguous.” Instead, “[i]f a\ncourt, employing traditional tools of statutory construction, ascertains that Congress had an\nintention on the precise question at issue, that intention is the law and must be given effect.”\nUnited States v. Home Concrete & Supply, LLC, 566 U.S. 478, 488 (2012) (plurality opinion)\n(quoting Chevron, 467 U.S. at 843 n.9).\n 20 See Ysleta I, 36 F.3d at 1335 (citing later enactments expressly excluding certain\ntribes from IGRA’s coverage as evidence of “a clear intention on Congress’ part that IGRA is\n 12\n\f Case: 18-40116 Document: 00514873577 Page: 13 Date Filed: 03/14/2019\n\n\n\n No. 18-40116\n“to the extent that a conflict between the two exists, IGRA impliedly repeals\nthe Restoration Act.” Ysleta I, 36 F.3d at 1335. Repudiating that interpreta-\ntion, we cited (1) the presumption against implied repeals and (2) the canon\nthat a specific statute controls over a general statute. Id. With respect to the\nsecond, we noted that the Restoration Act was “clearly” the specific statute,\n“whereas IGRA is a general one.” Id.\n\n The Tribe counters that, for two reasons, Ysleta I does not foreclose the\nNIGC’s determination that IGRA applies to the Tribe. First, the Tribe empha-\nsizes that Ysleta I’s holding “was based on nontextual cues from legislative\nhistory and canons of construction” and thus could not have “follow[ed] from\nthe unambiguous terms of the statute.” Brand X, 545 U.S. at 982. That rea-\nsoning disregards the fact that the Brand X inquiry stems from Chevron step\none and requires the reviewing court to apply “traditional tools of statutory\ninterpretation”—like the canons and legislative history—to determine whether\nCongress has spoken to the precise issue. See Chevron, 467 U.S. at 843 n.9.\nAnd when “the canons supply an answer, Chevron leaves the stage.” Epic Sys.\nCorp. v. Lewis, 138 S. Ct. 1612, 1630 (2018) (internal quotation marks and\ncitation omitted).\n\n Second, the Tribe asserts that Ysleta I “never had occasion to determine\nwhether the Restoration Act constitutes a federal law that specifically prohib-\nits [c]lass II gaming on Indian lands under IGRA.” That misses what Ysleta I\ndid hold—that the Restoration Act’s gaming provisions, and not IGRA, provide\nthe framework for deciding the legality of any and all gaming by the Pueblo\nand the Tribe on their Restoration Act lands. Ysleta I, 36 F.3d at 1332. 21\n\n\n\nnot to be the one and only statute addressing the subject of gaming on Indian lands”).\n The Tribe suggests that the Restoration Act’s application of Texas laws to the Tribe’s\n 21\n\ngambling is somewhat empty because Texas does not “prohibit” gaming as defined in\n 13\n\f Case: 18-40116 Document: 00514873577 Page: 14 Date Filed: 03/14/2019\n\n\n\n No. 18-40116\n In sum, Brand X teaches that a court should not defer to an agency’s\ninterpretation of a statute if a “judicial precedent hold[s] that the statute un-\nambiguously forecloses the agency’s interpretation.” Brand X, 545 U.S.\nat 982–83. That requires us to apply Chevron step one to a prior judicial inter-\npretation and to determine whether that court employed traditional tools of\nstatutory interpretation and found that Congress spoke to the precise issue.\nThat is what Ysleta I did in holding that “the Restoration Act prevails over\nIGRA when gaming activities proposed by [the Pueblo or Tribe] are at issue.”\nYsleta I, 36 F.3d at 1332. Consequently, the NIGC’s decision that IGRA applies\nto the Tribe does not displace Ysleta I. We thus reaffirm that the Restoration\nAct and the Texas law it invokes—and not IGRA—govern the permissibility of\ngaming operations on the Tribe’s lands. 22 IGRA does not apply to the Tribe,\nand the NIGC does not have jurisdiction over the Tribe.\n\n The district court did not abuse its discretion in denying relief from the\npermanent injunction. The order denying the motion for relief from judgment\nis AFFIRMED.\n\n\n\n\nCalifornia v. Cabazon Band of Mission Indians, 480 U.S. 202 (1987). This court expressly\nrejected that theory in Ysleta I, 36 F.3d at 1333−34, holding that “Congress did not enact the\nRestoration Act with an eye toward Cabazon Band.” Instead, we were “left with the unmis-\ntakable conclusion that Congress—and the [Pueblo]—intended for Texas’ gaming laws and\nregulations to operate as surrogate federal law on the [Pueblo’s] reservation in Texas.” Id.\nat 1334.\n 22The Tribe alternatively contends that Ysleta I should be overruled. The rule of\norderliness forbids us from reaching that issue. See Jacobs v. Nat’l Drug Intelligence Ctr.,\n548 F.3d 375, 378 (5th Cir. 2008) (citations omitted) (“[O]ne panel of [this] court may not\noverturn another panel’s decision, absent an intervening change in the law, such as by a\nstatutory amendment, or the Supreme Court, or [the] en banc court.”).\n 14\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: State of TEXAS, Plaintiff-Appellee, v. ALABAMA-COUSHATTA TRIBE OF TEXAS, Defendant-Appellant.\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-14\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 18-40116 Document: 00514873577 Page: 1 Date Filed: 03/14/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n No. 18-40116 March 14, 2019\\n Lyle W. Cayce\\n Clerk\\n\\n\\nSTATE OF TEXAS,\\n\\n Plaintiff−Appellee,\\n\\nversus\\n\\nALABAMA-COUSHATTA TRIBE OF TEXAS,\\n\\n Defendant−Appellant.\\n\\n\\n\\n\\n Appeal from the United States District Court\\n for the Eastern District of Texas\\n\\n\\n\\n\\nBefore SMITH, DUNCAN, and ENGELHARDT, Circuit Judges.\\nJERRY E. SMITH, Circuit Judge:\\n\\n For almost thirty years, the State of Texas and one of its Indian tribes,\\nthe Alabama-Coushatta Tribe (the “Tribe”), have disputed the impact of two\\nfederal statutes on the Tribe’s ability to conduct gaming on the Tribe’s reser-\\nvation. The first statute, the Ysleta del Sur Pueblo and Alabama and\\n\\f Case: 18-40116 Document: 00514873577 Page: 2 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\nCoushatta Indian Tribes of Texas Restoration Act 1 (the “Restoration Act”),\\nrestored the Tribe’s status as a federally-recognized tribe and limited its gam-\\ning operations according to state law. The second, the Indian Gaming Regula-\\ntory Act (“IGRA”), 25 U.S.C. §§ 2701–2721, broadly “establish[ed] . . . Federal\\nstandards for gaming on Indian lands.” Id. § 2702(3).\\n\\n Soon after IGRA was enacted, this court determined that the Restoration\\nAct and IGRA conflict and that the Restoration Act governs the Tribe’s gaming\\nactivities. See Ysleta del sur Pueblo v. Texas (“Ysleta I”), 36 F.3d 1325, 1335\\n(5th Cir. 1994). Several years later, when the Tribe was conducting gaming\\noperations in violation of Texas law, the district court permanently enjoined\\nthat activity as a violation of the Restoration Act.\\n\\n The Supreme Court then decided National Cable & Telecommunications\\nAss’n v. Brand X Internet Services, 545 U.S. 967 (2005), and City of Arlington\\nv. FCC, 569 U.S. 290 (2013). And the National Indian Gaming Commission\\n(“NIGC”), which administers IGRA, held, contrary to Ysleta I, that IGRA gov-\\nerns the Tribe’s gaming activity. Citing those changes in the law, the Tribe\\nasked the district court to dissolve the permanent injunction. The district\\ncourt refused, the Tribe appeals, and we affirm.\\n\\n I.\\n A.\\n In 1987, Congress passed the Restoration Act to restore “the Federal\\nrecognition of” both the Ysleta del Sur Pueblo (the “Pueblo,” an Indian tribe in\\nfar west Texas) and the Tribe. Pub. L. No. 100-89, §§ 103(a), 203(a), 101 Stat.\\n\\n\\n\\n 1 Pub. L. No. 100-89, §§ 201–07, 101 Stat. 666 (Aug. 18, 1987). The U.S. Code was\\nupdated while this case was pending in district court and now omits the Restoration Act,\\nwhich was previously codified at 25 U.S.C. § 731 et seq. Though no longer codified, the\\nRestoration Act is still in effect.\\n 2\\n\\f Case: 18-40116 Document: 00514873577 Page: 3 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\nat 667, 670. 2 The Restoration Act’s final section regulates gaming on the\\nTribe’s reservation and lands. It provides that “[a]ll gaming activities which\\nare prohibited by the laws of the State of Texas are hereby prohibited on the\\nreservation and on the lands of the tribe.” Id. § 207(a), 101 Stat. at 672. 3 It\\nbars Texas from asserting regulatory control over otherwise legal gaming on\\nthe Tribe’s reservation and lands. Id. § 207(b), 101 Stat. at 672. It also gives\\n“the courts of the United States . . . exclusive jurisdiction over any offense in\\nviolation” of its gaming restriction and limits Texas to “bringing an action in\\nthe courts of the United States to enjoin violations of the provisions of this\\nsection.” Id. § 207(c), 101 Stat. at 672.\\n\\n Congress enacted IGRA the following year. Finding that “existing Fed-\\neral law d[id] not provide clear standards or regulations for the conduct of gam-\\ning on Indian lands,” 25 U.S.C. § 2701(3), Congress established “Federal stan-\\ndards for gaming on Indian lands, and . . . a National Indian Gaming Commis-\\nsion . . . to protect such gaming as a means of generating tribal revenue.” Id.\\n§ 2702(3). Though its stated purpose is broad, IGRA does not specifically\\n\\n\\n\\n 2Though the Pueblo has extensively litigated the same questions the Tribe raises, the\\nPueblo is not a party to this appeal but appears as amicus curiae.\\n 3That subsection concludes by explaining that the “provisions of this subsection are\\nenacted in accordance with the tribe’s request in Tribal Resolution No. T.C.-86-07.” Restor-\\nation Act § 207(a), 101 Stat. at 672. That resolution, in turn, was purportedly passed out of\\nconcern that the Restoration Act would not be enacted “unless the bill was amended to\\nprovide for direct application of state laws governing gaming and bingo on the [Tribe’s]\\nReservation.” The resolution “respectfully request[ed] [the Tribe’s] representatives” in Con-\\ngress amend the Restoration Act to “provide that all gaming, gambling, lottery, or bingo, as\\ndefined by the laws and administrative regulations of the state of Texas, shall be prohibited\\non the Tribe’s reservation or on Tribal land.”\\n The significance of the Restoration Act’s reference to the Tribe’s resolution is disputed.\\nThe state contends that the resolution represents a quid pro quo in which the Tribe agreed\\nto foreswear gaming for all time in exchange for passage of the Restoration Act. The Tribe\\nexamines the evolution of drafts of the Restoration Act and emphasizes that strong prohibi-\\ntory language was ultimately deleted. In any event, the stringent prohibition proposed by\\nthe resolution was not included.\\n 3\\n\\f Case: 18-40116 Document: 00514873577 Page: 4 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\npreempt the field of Indian gaming law.\\n\\n IGRA defines three classes of gaming that federally recognized tribes\\nmay offer and regulates each differently. Tribes have “exclusive jurisdiction”\\nover “class I gaming,” which consists of “social games solely for prizes of mini-\\nmal value or traditional forms of Indian gaming” associated with “tribal cere-\\nmonies or celebrations.” Id. §§ 2703(6), 2710(a)(1). “Class II gaming” includes\\n“the game of chance commonly known as bingo,” id. § 2703(7)(A)(i), and certain\\n“card games” either “explicitly authorized” or “not explicitly prohibited” by\\nstate law. Id. § 2703(7)(A)(ii)(I)–(II). Tribes have the authority to regulate\\nclass II gaming, provided that a tribe issues a self-regulatory ordinance\\nmeeting statutory criteria and the NIGC approves that ordinance. Id.\\n§ 2710(b)(1)–(2). “Class III gaming” includes all forms of gaming that are not\\nin class I or II. Class III gaming is lawful on Indian lands only if tribes secure\\nfederal administrative and state approval. Id. § 2703(8); see id. § 2710(d).\\nIGRA created the NIGC to administer its provisions, instructing the NIGC to\\n“promulgate such regulations and guidelines as it deems appropriate to\\nimplement the provisions of this chapter.” Id. § 2706(b)(10).\\n\\n B.\\n Notwithstanding the Restoration Act, Texas, the Tribe, and the Pueblo\\nhave long disputed whether IGRA applies to the Tribe and the Pueblo. Texas\\navers that IGRA’s permissive gaming structure is inconsistent with Sections\\n107(a) and 207(a) of the Restoration Act, which prohibit gaming that violates\\nTexas law on the Pueblo’s and Tribe’s lands, respectively. The Tribe maintains\\nthat IGRA permits it to conduct gaming operations according to IGRA’s three-\\nclass structure.\\n\\n This court first considered the relationship between the Restoration Act\\nand IGRA in Ysleta I. Under IGRA, the Pueblo had tried to negotiate a\\n 4\\n\\f Case: 18-40116 Document: 00514873577 Page: 5 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\ncompact with Texas to permit class III gaming. Texas refused, citing the Res-\\ntoration Act and insisting that state law prohibited the proposed games. The\\nPueblo sued to compel Texas to negotiate, and the district court granted sum-\\nmary judgment for the Pueblo.\\n\\n This court reversed, holding that “(1) the Restoration Act and IGRA\\nestablish different regulatory regimes with regard to gaming” and that “(2) the\\nRestoration Act prevails over IGRA when gaming activities proposed by the\\nYsleta del Sur Pueblo are at issue.” Ysleta I, 36 F.3d at 1332. With respect to\\nthe first ruling, this court found it “significant” that “the Restoration Act estab-\\nlishes a procedure for enforcement of § 107(a) which is fundamentally at odds\\nwith the concepts of IGRA.” Id. at 1334. Based on that finding, we had to\\ndetermine “which statute [to] appl[y].” Id. The Pueblo urged “that, to the\\nextent that a conflict between the two exists, IGRA impliedly repeals the\\nRestoration Act.” Id. at 1334–35. We rejected that theory, noting that implied\\nrepeals are disfavored and that generally “a specific statute will not be con-\\ntrolled or nullified by a general one.” Id. at 1335 (cleaned up). And “[w]ith\\nregard to gaming,” we continued, “the Restoration Act clearly is a specific\\nstatute, whereas IGRA is a general one.” Id. 4\\n\\n This court thus concluded “that [the Restoration Act]—and not IGRA—\\nwould govern the determination of whether gaming activities proposed by the\\nYsleta del Sur Pueblo are allowed under Texas law, which functions as sur-\\nrogate federal law.” Id. “If the [Pueblo] wishe[d] to vitiate [the restrictive\\ngaming provisions] of the Restoration Act,” we declared, “it will have to petition\\nCongress to amend or repeal the Restoration Act rather than merely comply\\n\\n\\n\\n\\n 4 “The former applies to two specifically named Indian tribes located in one particular\\nstate, and the latter applies to all tribes nationwide.” Ysleta I, 36 F.3d at 1335.\\n 5\\n\\f Case: 18-40116 Document: 00514873577 Page: 6 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\nwith the procedures of IGRA.” Id. 5\\n\\n C.\\n The Tribe was not a party in Ysleta I, but, “particularly with regard to\\nthe sections concerning gaming,” its Restoration Act is almost identical to the\\nPueblo’s. Id. at 1329 n.3. We thus suggested in Ysleta I that the Restoration\\nAct—and not IGRA—would govern the legality of any gaming operations of the\\nTribe. Despite the Restoration Act’s restrictions, the Tribe maintained a casino\\non its reservation after Ysleta I. And in 2001, the Tribe sued Texas, seeking\\ndeclaratory relief that its gaming was lawful under IGRA. See Alabama-\\nCoushatta Tribes of Tex. v. Texas, 208 F. Supp. 2d 670, 672 (E.D. Tex. 2002).\\nTexas counterclaimed, asking the district court permanently to enjoin the\\nTribe’s gaming activities based on Section 207 of the Restoration Act. Id.\\n\\n Relying on Ysleta I, the district court held that the Restoration Act gov-\\nerned the legality of the Tribe’s gaming activities. Id. at 677–78. And because\\nthose activities violated Texas law, the court permanently enjoined them in\\n2002. Id. at 681. This court affirmed, explaining that it was “bound by the\\ndetermination [in Ysleta I] that the Restoration Act precludes [the Tribe] from\\nconducting all gaming activities prohibited by Texas law on tribal lands.” Ala-\\nbama Coushatta Tribe of Tex. v. Texas, No. 02-41030, 2003 WL 21017542, at *1\\n(5th Cir. Apr. 16, 2003) (per curiam) (unpublished). 6\\n\\n\\n\\n\\n 5 Though Ysleta I arose in the context of the Pueblo’s trying to conduct IGRA class III\\ngaming, Ysleta I does not suggest that the conflict between the Restoration Act and IGRA is\\nlimited to class III gaming.\\n 6 We further ruled that Ysleta I’s holding that “the tribe was precluded from seeking\\nrelief under the IGRA” was binding, contrary to the Tribe’s assertion that it was dictum.\\nAlabama Coushatta Tribe of Tex., 2003 WL 21017542, at *1. We explained that the Ysleta I\\npanel was required to decide that question “because the Restoration Act placed greater limits\\non the tribe’s ability to conduct gaming operations” than did IGRA. Id.\\n 6\\n\\f Case: 18-40116 Document: 00514873577 Page: 7 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\n D.\\n The Tribe ceased all gaming for twelve years. But in 2015, it started the\\nprocess outlined by IGRA to secure NIGC’s approval to offer class II gaming.\\nAs IGRA requires, see 25 U.S.C. § 2710, the Tribe adopted an ordinance au-\\nthorizing class II bingo gaming—which Texas law permits in several forms 7—\\nand submitted it to NIGC’s Chairman for approval. 8 The Tribe concedes that\\nby seeking that approval, the Tribe was requesting NIGC’s formal administra-\\ntive determination of whether, contrary to Ysleta I, the tribe fell within IGRA’s\\nambit.\\n\\n The Chairman approved the ordinance via letter, explaining that “[n]oth-\\ning in the IGRA’s language or its legislative history indicates that the Tribe is\\noutside the scope of NIGC’s jurisdiction.” 9 He then determined that the Tribe’s\\nreservation—established through the Restoration Act—counts as “Indian\\nlands” under IGRA. Those findings, the Chairman continued, demonstrate\\nthat the Tribe’s “lands are eligible for gaming under IGRA.” The Chairman\\nthus concluded that the Tribe’s ordinance was “consistent with the require-\\nments of IGRA and NIGC regulations” and approved it. 10\\n\\n Despite initially observing that the Restoration Act and IGRA poten-\\ntially overlap, 11 the Chairman did not carefully consider whether the Restora-\\ntion Act limited the jurisdictional reach of IGRA. He opined, instead, that “the\\n\\n\\n 7 See, e.g., 16 Tex. Admin. Code §§ 402.100−.709.\\n 8 See 29 U.S.C. § 2710(b)(1)(B).\\n 9 Letter from Jonodev O. Chaudhuri, Chairman, Nat’l Indian Gaming Comm’n, to Nita\\nBattise, Chairperson, Alabama-Coushatta Tribe of Tex. (Oct. 8, 2015).\\n 10Id. The Chairman noted that the Department of the Interior interpreted IGRA as\\nimpliedly repealing the Restoration Act, but the Chairman did not adopt that conclusion.\\n 11See id. (noting that the Restoration Act “applies state gaming laws to the Tribe’s\\nlands, with a qualification,” thus raising the question “how to interpret the interface between\\nIGRA and the Restoration Act”).\\n 7\\n\\f Case: 18-40116 Document: 00514873577 Page: 8 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\nTribe possesses sufficient legal jurisdiction over its Restoration Act lands” for\\nIGRA to apply. In other words, the Chairman determined that the Restoration\\nAct does not constitute a “Federal law” that is a “specific[] prohibit[ion]” on the\\nTribe’s proposed gaming. 25 U.S.C. § 2710(b)(1)(A).\\n\\n With NIGC’s approval in hand, the Tribe began to develop Naskila\\nEntertainment Center (“Naskila”), a class II gaming facility offering electronic\\nbingo. Before it opened, the Tribe and Texas forged a prelitigation agreement\\nspecifying that the Tribe could operate Naskila pending a state inspection.\\nTexas committed to “advise the Tribe . . . whether the gambling operation\\nmeets the requirements of Texas law federalized in the Restoration Act” and\\nreserved the right to seek various forms of relief if it did not.\\n\\n Upon inspection, the state determined that the electronic bingo at Nas-\\nkila violated various provisions of Texas gaming law. Then the state revived\\nthe decades-old case—in which the district court had permanently enjoined the\\nTribe’s gaming activities that had violated the Restoration Act—by filing a\\nmotion for contempt, averring that the gaming at Naskila violated the 2002\\ninjunction. 12 Texas also sought a declaration “that IGRA does not apply to the\\nTribe because IGRA did not repeal the Restoration Act, and, accordingly,” the\\nTribe “may not conduct Class II IGRA gaming on its lands.” The Tribe, in turn,\\nmoved for relief from the 2002 injunction, contending that the “[NIGC’s]\\nauthoritative interpretation” of the Restoration Act and IGRA “both consti-\\ntutes a change in law and eliminates the sole legal basis for the injunction.”\\n\\n Texas moved for summary judgment on issues related to its motion for\\ncontempt, and the Tribe sought partial summary judgment on whether its\\n\\n\\n 12 The Tribe was the plaintiff (as it had sought a declaratory judgment that its gaming\\nactivities were lawful under IGRA), and Texas was the defendant. When Texas reopened the\\ncase, the court granted its motion to realign the parties, making Texas the plaintiff.\\n 8\\n\\f Case: 18-40116 Document: 00514873577 Page: 9 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\nbingo operations are class II gaming under IGRA. The district court granted\\nTexas’s motion “with respect to the State’s request for a declaration . . . that\\nthe Restoration Act, and consequently, Texas law, applies to the Tribe’s gam-\\ning activities.” The court refused to extend Chevron deference 13 to the NIGC’s\\nletter concluding that IGRA applied, and it denied the Tribe’s motion for relief\\nfrom the permanent injunction.\\n\\n The Tribe appeals, asking us to decide whether the district court abused\\nits discretion by refusing to defer to the NIGC’s determination that IGRA\\napplies to the Tribe’s gaming. The district court stayed its ruling pending\\nappeal. 14\\n\\n II.\\n District courts may “relieve a party . . . from a final judgment, order, or\\nproceeding” if “applying it prospectively is no longer equitable.” FED. R. CIV. P.\\n60(b), 60(b)(5). Where, as here, “the relief sought is dissolution or modification\\nof an injunction, the district court may grant a Rule 60(b)(5) motion when the\\nparty seeking relief can show a significant change in statutory or decisional\\nlaw.” Cooper v. Tex. Alcoholic Beverage Comm’n, 820 F.3d 730, 741 (5th Cir.\\n2016) (cleaned up). The “significant change” in this case, according to the\\nTribe, is the NIGC’s determination that the Tribe’s lands are eligible for\\ngaming under IGRA, combined with Brand X and City of Arlington.\\n\\n We review for abuse of discretion the denial of a Rule 60(b)(5) motion for\\nrelief from judgment. Moore v. Tangipahoa Par. Sch. Bd., 864 F.3d 401, 405\\n(5th Cir. 2017). “A district court abuses its discretion if it: (1) relies on clearly\\n\\n\\n\\n 13 See Chevron, U.S.A., Inc. v. Nat. Res. Def. Council, Inc., 567 U.S. 837 (1984).\\n 14 We have jurisdiction under 28 U.S.C. § 1292(a)(1), which allows for immediate\\nappeal of interlocutory orders “refusing to dissolve or modify injunctions.”\\n 9\\n\\f Case: 18-40116 Document: 00514873577 Page: 10 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\nerroneous factual findings; (2) relies on erroneous conclusions of law; or\\n(3) misapplies the law to the facts.” In re Volkswagen of Am., Inc., 545 F.3d\\n304, 310 (5th Cir. 2008) (en banc) (citation omitted). “It is not enough that\\ngranting the motion may have been permissible; instead, denial of relief must\\nhave been so unwarranted as to constitute an abuse of discretion.” Moore,\\n864 F.3d at 405 (internal quotation marks and citation omitted). While review\\nis highly deferential, “we review de novo any questions of law underlying the\\ndistrict court’s decision.” Frew v. Janek, 780 F.3d 320, 326 (5th Cir. 2015)\\n(internal quotation marks and citation omitted).\\n\\n III.\\n This case turns on whether a judicial precedent—holding that the\\nRestoration Act and IGRA conflict and that the former, not the latter, applies\\nto the Tribe’s gaming activity—or a later contrary agency interpretation should\\ncontrol. Brand X supplied the framework: “A court’s prior judicial construction\\nof a statute trumps an agency construction otherwise entitled to Chevron\\ndeference only if the prior court decision holds that its construction follows\\nfrom the unambiguous terms of the statute and thus leaves no room for agency\\ndiscretion.” Brand X, 545 U.S. at 982 (emphasis added). We must thus decide\\nwhether Ysleta I is “a judicial precedent holding that the statute unambigu-\\nously forecloses the agency’s interpretation.” Id. at 982–83.\\n\\n A.\\n Brand X’s rule that only a prior judicial interpretation adhering to the\\nunambiguous terms of the statute trumps an agency construction “follows from\\nChevron itself.” Id. at 982. “Chevron’s premise is that it is for agencies, not\\ncourts, to fill statutory gaps.” Id. (citation omitted). So to be faithful to that\\nprinciple, “judicial interpretations contained in precedents” must be held “to\\nthe same demanding Chevron step one standard that applies if the court is\\n 10\\n\\f Case: 18-40116 Document: 00514873577 Page: 11 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\nreviewing the agency’s construction on a blank slate.” Id. That means that a\\njudicial interpretation should prevail over a later conflicting agency interpre-\\ntation if the “court, employing traditional tools of statutory construction, as-\\ncertain[ed] that Congress had an intention on the precise question at issue.”\\nChevron, 467 U.S. at 843 n.9. 15\\n\\n Consequently, a prior judicial decision need not “say in so many magic\\nwords that its holding is the only permissible interpretation of the statute in\\norder for that holding to be binding on an agency.” Exelon Wind 1, L.L.C. v.\\nNelson, 766 F.3d 380, 398 (5th Cir. 2014) (quoting Fernandez v. Keisler,\\n502 F.3d 337, 347 (4th Cir. 2007)). 16 To the contrary, where “the exercise of\\nstatutory interpretation makes clear the court’s view that the plain language\\nof the statute was controlling and that there existed no room for contrary\\nagency interpretation,” the court’s interpretation should prevail. Id. (quoting\\nFernandez, 502 F.3d at 347–48). 17\\n\\n Instead of requiring the prior decision to have called the relevant statute\\n“unambiguous,” reviewing courts have looked for the contrary—whether the\\ndecision called the statute “ambiguous.” For example, this court recently held\\nthat an agency’s interpretation could prevail over a prior judicial interpreta-\\ntion because the latter had “expressly recognized that the court decided to come\\n\\n\\n 15Brand X, 545 U.S. at 985, offers the rule of lenity as an example of a “rule of con-\\nstruction” that a court might have applied which “requir[ed] it to conclude that the statute\\nwas unambiguous to reach its judgment.”\\n 16 See also Silva-Trevino v. Holder, 742 F.3d 197, 201–03 (5th Cir. 2014) (upholding a\\nprior judicial interpretation in the face of a conflicting agency interpretation even though the\\nprior decision did not say that the statute was “unambiguous” because the first court was\\n“confident” that “Congress ha[d] spoken directly to the statutory question at hand” based on\\nthe text of the statute and Congress’s use of the language in other statutes).\\n 17 See also Council for Urological Interests v. Burwell, 790 F.3d 212, 221 (D.C. Cir.\\n2015) (citation omitted) (“[A] statute may foreclose an agency's preferred interpretation\\ndespite such textual ambiguities if its structure, legislative history, or purpose makes clear\\nwhat its text leaves opaque.”).\\n 11\\n\\f Case: 18-40116 Document: 00514873577 Page: 12 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\ndown on one side of a complex debate.” 18 And where other circuits have de-\\nferred to an agency’s interpretation under Brand X, those courts have “empha-\\nsize[d] that their prior decisions also noted ambiguity in the text at issue.” See\\nExelon Wind 1, 766 F.3d at 398 (collecting citations). 19\\n\\n B.\\n Ysleta I did not find “ambiguity in the text at issue.” Id. Instead, after\\napplying canons of construction and legislative history to § 107(a) and (c) of the\\nPueblo’s Restoration Act—which corresponds to § 207(a) and (c) in the\\nTribe’s—this court concluded that “the Restoration Act and IGRA establish\\n. . . fundamentally different regimes.” Ysleta I, 36 F.3d at 1334. Indeed, this\\ncourt was left with “the unmistakable conclusion that Congress—and the\\nTribe—intended for Texas’ gaming laws and regulations to operate as surro-\\ngate federal law on the Tribe’s reservation in Texas.” Id. In other words, this\\ncourt summarized, “(1) the Restoration Act and IGRA establish different regu-\\nlatory regimes with regard to gaming, [and] (2) the Restoration Act prevails\\nover IGRA when gaming activities proposed by [the Pueblo or Tribe] are at\\nissue.” Id. at 1332.\\n\\n Additionally, we cited evidence that Congress did not intend for IGRA to\\napply to all Indian gaming. 20 Moreover, we specifically rejected the theory that\\n\\n\\n 18 Acosta v. Hensel Phelps Constr. Co., 909 F.3d 723, 738 (5th Cir. 2018) (internal\\nquotation marks omitted) (quoting Melerine v. Avondale Shipyards, Inc., 659 F.2d 706, 710\\n(5th Cir. Unit A Oct. 1981) (discussing the “complex dispute” among courts)).\\n 19A plurality of the Supreme Court has likewise held that, under Brand X, a court\\nneed not have said that the statute it was interpreting was “unambiguous.” Instead, “[i]f a\\ncourt, employing traditional tools of statutory construction, ascertains that Congress had an\\nintention on the precise question at issue, that intention is the law and must be given effect.”\\nUnited States v. Home Concrete & Supply, LLC, 566 U.S. 478, 488 (2012) (plurality opinion)\\n(quoting Chevron, 467 U.S. at 843 n.9).\\n 20 See Ysleta I, 36 F.3d at 1335 (citing later enactments expressly excluding certain\\ntribes from IGRA’s coverage as evidence of “a clear intention on Congress’ part that IGRA is\\n 12\\n\\f Case: 18-40116 Document: 00514873577 Page: 13 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\n“to the extent that a conflict between the two exists, IGRA impliedly repeals\\nthe Restoration Act.” Ysleta I, 36 F.3d at 1335. Repudiating that interpreta-\\ntion, we cited (1) the presumption against implied repeals and (2) the canon\\nthat a specific statute controls over a general statute. Id. With respect to the\\nsecond, we noted that the Restoration Act was “clearly” the specific statute,\\n“whereas IGRA is a general one.” Id.\\n\\n The Tribe counters that, for two reasons, Ysleta I does not foreclose the\\nNIGC’s determination that IGRA applies to the Tribe. First, the Tribe empha-\\nsizes that Ysleta I’s holding “was based on nontextual cues from legislative\\nhistory and canons of construction” and thus could not have “follow[ed] from\\nthe unambiguous terms of the statute.” Brand X, 545 U.S. at 982. That rea-\\nsoning disregards the fact that the Brand X inquiry stems from Chevron step\\none and requires the reviewing court to apply “traditional tools of statutory\\ninterpretation”—like the canons and legislative history—to determine whether\\nCongress has spoken to the precise issue. See Chevron, 467 U.S. at 843 n.9.\\nAnd when “the canons supply an answer, Chevron leaves the stage.” Epic Sys.\\nCorp. v. Lewis, 138 S. Ct. 1612, 1630 (2018) (internal quotation marks and\\ncitation omitted).\\n\\n Second, the Tribe asserts that Ysleta I “never had occasion to determine\\nwhether the Restoration Act constitutes a federal law that specifically prohib-\\nits [c]lass II gaming on Indian lands under IGRA.” That misses what Ysleta I\\ndid hold—that the Restoration Act’s gaming provisions, and not IGRA, provide\\nthe framework for deciding the legality of any and all gaming by the Pueblo\\nand the Tribe on their Restoration Act lands. Ysleta I, 36 F.3d at 1332. 21\\n\\n\\n\\nnot to be the one and only statute addressing the subject of gaming on Indian lands”).\\n The Tribe suggests that the Restoration Act’s application of Texas laws to the Tribe’s\\n 21\\n\\ngambling is somewhat empty because Texas does not “prohibit” gaming as defined in\\n 13\\n\\f Case: 18-40116 Document: 00514873577 Page: 14 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-40116\\n In sum, Brand X teaches that a court should not defer to an agency’s\\ninterpretation of a statute if a “judicial precedent hold[s] that the statute un-\\nambiguously forecloses the agency’s interpretation.” Brand X, 545 U.S.\\nat 982–83. That requires us to apply Chevron step one to a prior judicial inter-\\npretation and to determine whether that court employed traditional tools of\\nstatutory interpretation and found that Congress spoke to the precise issue.\\nThat is what Ysleta I did in holding that “the Restoration Act prevails over\\nIGRA when gaming activities proposed by [the Pueblo or Tribe] are at issue.”\\nYsleta I, 36 F.3d at 1332. Consequently, the NIGC’s decision that IGRA applies\\nto the Tribe does not displace Ysleta I. We thus reaffirm that the Restoration\\nAct and the Texas law it invokes—and not IGRA—govern the permissibility of\\ngaming operations on the Tribe’s lands. 22 IGRA does not apply to the Tribe,\\nand the NIGC does not have jurisdiction over the Tribe.\\n\\n The district court did not abuse its discretion in denying relief from the\\npermanent injunction. The order denying the motion for relief from judgment\\nis AFFIRMED.\\n\\n\\n\\n\\nCalifornia v. Cabazon Band of Mission Indians, 480 U.S. 202 (1987). This court expressly\\nrejected that theory in Ysleta I, 36 F.3d at 1333−34, holding that “Congress did not enact the\\nRestoration Act with an eye toward Cabazon Band.” Instead, we were “left with the unmis-\\ntakable conclusion that Congress—and the [Pueblo]—intended for Texas’ gaming laws and\\nregulations to operate as surrogate federal law on the [Pueblo’s] reservation in Texas.” Id.\\nat 1334.\\n 22The Tribe alternatively contends that Ysleta I should be overruled. The rule of\\norderliness forbids us from reaching that issue. See Jacobs v. Nat’l Drug Intelligence Ctr.,\\n548 F.3d 375, 378 (5th Cir. 2008) (citations omitted) (“[O]ne panel of [this] court may not\\noverturn another panel’s decision, absent an intervening change in the law, such as by a\\nstatutory amendment, or the Supreme Court, or [the] en banc court.”).\\n 14\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1088,"cells":{"id":{"kind":"number","value":4599962,"string":"4,599,962"},"name":{"kind":"string","value":"In RE: UNITED STATES BUREAU OF PRISONS, DEPARTMENT OF JUSTICE, Respondent - Appellant"},"name_abbreviation":{"kind":"string","value":"In Re U.S. Bureau of Prisons, DEPT. OF JUSTICE"},"decision_date":{"kind":"string","value":"2019-03-14"},"docket_number":{"kind":"string","value":"18-50512"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Higginbotham, Smith, Higginson\", \"parties\": \"\", \"opinions\": [{\"author\": \"STEPHEN A. HIGGINSON, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 18-50512 Document: 00514873161 Page: 1 Date Filed: 03/14/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n March 14, 2019\\n No. 18-50512\\n Lyle W. Cayce\\n Clerk\\n\\nIn re: UNITED STATES BUREAU OF PRISONS, DEPARTMENT OF\\nJUSTICE,\\n\\n Respondent - Appellant\\n\\n\\n\\n\\n Appeal from the United States District Court\\n for the Western District of Texas\\n\\n\\nBefore HIGGINBOTHAM, SMITH, and HIGGINSON, Circuit Judges.\\nSTEPHEN A. HIGGINSON, Circuit Judge:\\n The U.S. Bureau of Prisons (BOP) appeals a contempt sanction related\\nto its calculation of sentencing credits for federal prisoners. We reverse.\\n I.\\n A.\\n This case began with a disagreement between the district court and the\\nBOP regarding the implementation of the revocation sentence of Ruben\\nHernandez. Hernandez was convicted in federal court of conspiracy to\\ntransport illegal aliens and sentenced to twelve months’ imprisonment and\\nthree years of supervised release. During his term of federal supervised\\nrelease, Hernandez was arrested by local law enforcement and charged in state\\ncourt with being a felon in possession of a firearm, theft of a firearm, and\\npossession of cocaine. Hernandez spent over a year in pretrial detention on\\nthese state charges. The two state firearm charges were later dismissed. On\\n\\f Case: 18-50512 Document: 00514873161 Page: 2 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-50512\\nNovember 15, 2016, Hernandez was acquitted of the remaining state drug\\npossession charge.\\n Federal authorities took custody of Hernandez, and the government\\npetitioned the district court to revoke his supervised release based on his\\nalleged drug and firearm possession. On March 13, 2017, the district court\\nrevoked Hernandez’s supervised release and sentenced him to 10 months\\nimprisonment. At the revocation hearing, Hernandez requested credit for time\\nserved in state custody. The district court orally denied this request. The\\nrevocation judgment orders “that the defendant, Ruben Hernandez, be\\ncommitted to the custody of the U.S. Bureau of Prisons for a term of TEN (10)\\nmonths, pursuant to 18 U.S.C. § 3583(e)(3) with credit for time served from\\nNovember 14, 2016 forward.” The BOP later determined that Hernandez\\nwas entitled to credit for the 543 days he spent in detention following his state\\narrest. Because Hernandez had already served more than his 10 month\\nsentence, he was released.\\n The district court learned of Hernandez’s release, and concluded that the\\nBOP’s sentence calculation was inconsistent with the revocation judgment.\\nAccording to the BOP, the district court then directed a probation officer to\\ncontact the BOP and express the court’s disagreement with its credit\\ncalculation. Romulo Armendariz, an Operations Manager at the BOP’s\\nDesignation and Sentence Computation Center, responded that the BOP was\\nrequired to give Hernandez credit for the full period he spent in state custody\\nunder 18 U.S.C. § 3585(b). The district court, through the probation officer,\\nmaintained that the BOP had made a mistake. The court requested that the\\nBOP either take Hernandez back into custody or provide the name and mailing\\naddress of a person to whom a summons could be sent for a Show Cause\\nhearing.\\n\\n\\n 2\\n\\f Case: 18-50512 Document: 00514873161 Page: 3 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-50512\\n B.\\n When the BOP did not re-arrest Hernandez, the district court opened a\\ncivil contempt proceeding against Armendariz. 1 The court issued an order to\\nshow cause why Armendariz should not be held in contempt for violating the\\ncourt’s revocation order by improperly calculating Hernandez’s sentence. The\\ndistrict court later issued a supplemental order to show cause related to the\\ncalculation of the sentence of another defendant, Antonio Bustamante-Huerta,\\nwho was released in 2012. 2 The district court subsequently added Craig\\nPickles, Section Chief of Sentence Computation at the BOP, as an additional\\nrespondent in the contempt proceeding.\\n The district court held a contempt hearing on January 29, 2018. The\\ncourt began by explaining that Armendariz and Pickles were named in their\\nofficial capacities, and that the contempt proceeding was not against any\\nindividual. The court then raised for the first time the case of another\\ndefendant, Francisco Javier Hernandez, whose supervised release was revoked\\nin 2011. The district court had ordered Francisco Hernandez’s sentence to run\\nconsecutively to a pending state case. Yet because Francisco Hernandez had\\nnot yet been convicted in state court at the time of the revocation, he was\\nawarded credit for time served and released. He was later convicted in state\\ncourt. The district court expressed its view that the BOP was in contempt of\\n\\n\\n\\n\\n 1 The district court initially requested that the prosecutor involved in Ruben\\nHernandez’s case prosecute the contempt proceeding. The U.S. Attorney’s Office declined the\\ncourt’s invitation to prosecute the alleged contempt, stating that it concurred with the BOP’s\\ncredit determination and did not believe that contempt was appropriate. The U.S. Attorney\\ninformed the court that it would instead represent Armendariz. The district court stated that\\nit intended to appoint a special prosecutor, but did not do so.\\n 2 Armendariz attests that he was not personally involved in Bustamante-\\nHuerta’s sentence computation, but that Bustamante-Huerta may have been released early\\ndue to a data entry error.\\n 3\\n\\f Case: 18-50512 Document: 00514873161 Page: 4 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-50512\\ncourt because the BOP awarded credit for time served in state custody despite\\nthe district court’s instruction that the federal sentence be consecutive.\\n The BOP expressed its position that it is required by statute to award\\ncredit for time served in official detention when that time has not been credited\\nto another sentence. See 18 U.S.C. § 3585(b). The BOP repeatedly explained\\nthat, although the district court has the authority to order a consecutive\\nsentence, the BOP cannot run the federal sentence consecutively if there is no\\nother sentence in place. Ruben Hernandez, for example, was acquitted in state\\ncourt and therefore had no state sentence. The BOP acknowledged that, in\\nsome instances, defendants are awarded credit for time served in pretrial state\\ndetention, released from federal custody, and subsequently convicted in state\\ncourt. But the BOP explained that it must “compute the sentence in the here\\nand now,” and it cannot hold prisoners indefinitely “until we find out what’s\\ngoing to happen in the future.” The BOP nonetheless promised “to\\ncommunicate the Court’s concerns to the Bureau and see if we can come up\\nwith some type of resolution.”\\n The district court then ordered the BOP to file an “advisory to the Court”\\nexplaining its position. The court stated that its “suggestion would be to follow\\nthe statute unless you have a court order saying otherwise.” The BOP filed a\\n“Court Advisory” restating its legal position. Dissatisfied with this response,\\nthe district court set another hearing “to determine the appropriate sanctions\\nto be imposed.” After receiving this order, the BOP requested clarification as\\nto what contempt findings the district court had made. The district court\\ndenied the request for clarification, stating that it would amount to an advisory\\nopinion, and reiterated that a hearing would be held to determine sanctions.\\n On April 25, 2018, the district court held a sanctions hearing. The court\\nsubstituted the BOP for the named individual respondents. The court\\nreiterated its view that it has the authority to order consecutive sentences, and\\n 4\\n\\f Case: 18-50512 Document: 00514873161 Page: 5 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-50512\\nthat the BOP is not running sentences consecutively when it gives prisoners\\ncredit for time served on unadjudicated state cases. At the conclusion of the\\nhearing, the district court stated that it was ordering the BOP not to award\\ncredit under § 3585(b)(2) for time served in state detention when the district\\ncourt imposes a consecutive sentence. The court described this order as a\\n“sanction.” The court further explained that its order would apply “[i]n my\\ncases only,” not nationwide, “[a]nd anybody that violates that injunction will\\nthen be facing [a] personal, individual contempt situation.”\\n The district court took no further action in the case. On June 25, 2018,\\nthe BOP filed a notice of appeal from the district court’s April 25, 2018 decision.\\n II.\\n We must first assure ourselves of our jurisdiction. See Hill v. City of\\nSeven Points, 230 F.3d 167, 169 (5th Cir. 2000). The BOP asserts that the\\ndistrict court’s contempt sanction is either a final decision appealable under 28\\nU.S.C. § 1291 or an interlocutory injunction appealable under 28 U.S.C.\\n§ 1292(a)(1). We have jurisdiction under § 1291, and therefore need not\\naddress § 1292(a)(1).\\n “The general rule in this circuit is that civil contempt orders are not\\nappealable final orders for the purposes of 28 U.S.C. § 1291,” but an exception\\n“exists ‘[w]hen a civil contempt motion is not part of continuing litigation, . . .\\nbecause no underlying case awaits final resolution.’” Quilling v. Funding\\nResource Grp., 227 F.3d 231, 234 (5th Cir. 2000) (quoting In re Grand Jury\\nSubpoena for Attorney Representing Criminal Defendant Reyes-Requena, 926\\nF.2d 1423, 1429 (5th Cir. 1991)). This is a standalone civil contempt proceeding\\ninitiated by the district court. We therefore have jurisdiction under § 1291 so\\nlong as the district court issued a final decision in this matter.\\n “A decision is final when it ‘ends the litigation on the merits and leaves\\nnothing for the court to do but execute the judgment.’” Askanase v. Livingwell,\\n 5\\n\\f Case: 18-50512 Document: 00514873161 Page: 6 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-50512\\nInc., 981 F.2d 807, 810 (5th Cir. 1993) (quoting Coopers & Lybrand v. Livesay,\\n437 U.S. 463, 467 (1978)). A “civil contempt order is not ‘final’ for purposes of\\nappeal unless two actions occur: (1) a finding of contempt is issued, and (2) an\\nappropriate sanction is imposed.” In re U.S. Abatement Corp., 39 F.3d 563, 567\\n(5th Cir. 1994). The district court in this case did not make an explicit contempt\\nfinding. And despite the BOP’s request for clarification, the court refused to\\nexplain the factual or legal basis for its conclusion that the BOP had violated\\na court order.\\n We nonetheless find that the district court held the BOP in contempt.\\nThe court repeatedly expressed its view that the BOP was violating its\\nrevocation judgments, and twice stated that it would hold a hearing to\\ndetermine appropriate sanctions. The district court then imposed a final\\nsanction in the form of an oral injunction against the BOP. The court did not\\nenter a written order, despite indicating at the sanctions hearing that it\\nplanned to do so. But the oral injunction was not tentative, and the district\\ncourt did not indicate that the sanction was open to further argument or\\nreconsideration. Rather, the district court asked the BOP to affirm that it\\nunderstood the scope of the injunction. The court also made clear that the\\ninjunction would be effective immediately and stated that, “after today, if some\\nindividual in BOP were to execute their duty in a manner in violation of this\\nCourt’s findings, it would be individual liability.”\\n The BOP understandably interprets this order to signify that its officials\\nare now operating under the threat of individual contempt sanctions. We have\\npreviously affirmed a contempt sanction for the violation of an oral injunction,\\nwhere the contemnor was aware of the injunction and “in fact considered\\n\\n\\n\\n\\n 6\\n\\f Case: 18-50512 Document: 00514873161 Page: 7 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-50512\\nhimself bound by” it. In re Bradley, 588 F.3d 254, 263 (5th Cir. 2009). 3 The\\nimmediate effect of the district court’s order distinguishes this case from\\ncontempt sanctions that we have held to be non-final, such as monetary\\nsanctions in an amount yet to be determined. See Thornton v. General Motors\\nCorp., 136 F.3d 450, 453 (5th Cir. 1998) (holding that an order suspending\\nattorney from practice effectively immediately was an appealable final\\nsanction, but an order imposing unquantified attorney’s fees was not final); see\\nalso Cruz v. Fulton, 714 F. App’x 393, 396 (5th Cir. 2018) (finding no\\njurisdiction because “the dollar amount of contempt sanctions remains yet to\\nbe determined”). Under these circumstances, the district court’s failure to put\\nits injunction in writing does not render its order non-final.\\n We note that it is highly unusual for a district court to make a finding of\\ncontempt and to issue a contempt sanction without entering a written order\\nexplaining the basis for its findings and describing the sanction imposed. These\\nomissions are relevant to the merits of this appeal. But a lack of procedural\\nformality does not shield a district court’s final decisions from appellate review\\nunder 28 U.S.C. § 1291. 4\\n\\n\\n 3 Other circuits similarly treat oral injunctions as enforceable orders. See, e.g.,\\nLau v. Meddaugh, 229 F.3d 121, 123, 123 n.2 (2d Cir. 2000); In re Charlotte Observer, 921\\nF.2d 47, 48, 50 (4th Cir. 1990). We agree with the Second Circuit that, although Federal Rule\\nof Civil Procedure 65(d) “contemplates the issuance of a written order,” a district “court’s\\nfailure to comply with the specific requirements of this rule does not render the injunction\\nvoid.” Lau, 229 F.3d at 123, 123 n.2; see also Test Masters Educ. Servs., Inc. v. Singh, 428\\nF.3d 559, 577 (5th Cir. 2005) (explaining that a district court’s failure to fully comply with\\nRule 65(d) “does not require that the injunction be reversed or vacated”) (quotation omitted).\\nAs we noted in Bradley, 588 F.3d at 261–63, the Seventh Circuit appears to take a different\\nposition. See Bates v. Johnson, 901 F.2d 1424, 1427–28 (7th Cir. 1990) (holding that an oral\\ninjunction is not enforceable, and therefore not appealable). We do not follow the Seventh\\nCircuit’s view that a party “is under no judicial compulsion” until a judge “record[s] an\\ninjunction or declaratory judgment on a separate document.” Id. at 1428.\\n 4 The district court did not set out its order in a separate document as required\\nby Federal Rule of Civil Procedure 58(a). But this “failure to set forth a judgment or order on\\na separate document when required by [Rule] 58(a) does not affect the validity of an appeal\\nfrom that judgment or order.” FED. R. APP. P. 4(a)(7)(B); see also Moreno v. LG Electronics,\\n 7\\n\\f Case: 18-50512 Document: 00514873161 Page: 8 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-50512\\n III.\\n “We review contempt orders and sanctions imposed under a court’s\\ninherent powers for an abuse of discretion.” United States v. City of Jackson,\\nMiss., 359 F.3d 727, 731 (5th Cir. 2004). A district court’s inherent power to\\nsanction contempt “is not a broad reservoir of power, ready at an imperial\\nhand, but a limited source; an implied power squeezed from the need to make\\nthe court function.” NASCO, Inc. v. Calcasieu Television and Radio, Inc., 894\\nF.2d 696, 702 (5th Cir. 1990); see also Crowe v. Smith, 151 F.3d 217, 226 (5th\\nCir. 1998). As “inherent powers are shielded from direct democratic controls,\\nthey must be exercised with restraint and discretion.” Roadway Express, Inc.\\nv. Piper, 447 U.S. 752, 764 (1980). The contempt power is not an appropriate\\nmeans for a district court to express its reasoned disagreement with a federal\\nstatute. Threatening government officials with individual contempt sanctions\\nfor complying with federal law, as the district court did here, is a clear abuse\\nof discretion.\\n A.\\n We first briefly review the legal framework governing the calculation of\\nsentencing credits. The Sentencing Reform Act of 1984 provides:\\n A defendant shall be given credit toward the service of a term of\\n imprisonment for any time he has spent in official detention prior\\n to the date the sentence commences\\n\\n (1) as a result of the offense for which the sentence was imposed;\\n or\\n (2) as a result of any other charge for which the defendant was\\n arrested after the commission of the offense for which the sentence\\n was imposed;\\n\\n that has not been credited against another sentence.\\n\\n\\nUSA Inc., 800 F.3d 692, 696–97 (5th Cir. 2015) (noting that Rule 4, as amended, states that\\na failure to comply with Rule 58(a) does not affect the validity of the appeal).\\n 8\\n\\f Case: 18-50512 Document: 00514873161 Page: 9 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-50512\\n18 U.S.C. § 3585(b).\\n The Supreme Court has squarely held that § 3585(b) “does not authorize\\na district court to compute the credit at sentencing.” United States v. Wilson,\\n503 U.S. 329, 334 (1992). This responsibility belongs to the Attorney General,\\nacting through the BOP. Id. at 335; see also Leal v. Tombone, 341 F.3d 427, 428\\n(5th Cir. 2003). The BOP’s procedures for calculating credit under § 3585(b)\\nare set out in its Sentence Computation Manual. See U.S. Dep’t of Justice,\\nFederal Bureau of Prisons Program Statement No. 5880.28 (July 20, 1999). 5\\n Confusion sometimes arises, as it did here, when a defendant requests\\nthat the district court award credit for time served and the court purports to\\ngrant or deny this request at sentencing. Because the district court lacks the\\nauthority to award or deny credit, the BOP is not bound by its decision. See,\\ne.g., Mehta v. Wigen, 597 F. App’x 676, 680 (3d Cir. 2015) (holding that the\\nBOP erred in denying credit under § 3585(b) based on the sentencing court’s\\nintent). The sentencing court does “retain residual authority” to consider a\\ndefendant’s time in custody. United States v. Hankton, 875 F.3d 786, 792 (5th\\nCir. 2017). If the court determines that the BOP will not credit a defendant’s\\nprior time served, the court can reduce the defendant’s sentence under\\n§ 5G1.3(b) or § 5K2.23 of the U.S. Sentencing Guidelines. Id. But the district\\ncourt must calculate the defendant’s final sentence itself; it cannot simply\\norder the BOP to award credit. Moreover, neither of these Guidelines\\nprovisions authorizes a district court to increase a defendant’s sentence to deny\\ncredit that the defendant is otherwise entitled under § 3585(b).\\n District courts also “have discretion to select whether the sentences they\\nimpose will run concurrently or consecutively with respect to other sentences\\nthat they impose, or that have been imposed in other proceedings, including\\n\\n\\n 5 The Manual is available at https://www.bop.gov/policy/progstat/5880_028.pdf.\\n 9\\n\\f Case: 18-50512 Document: 00514873161 Page: 10 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-50512\\nstate proceedings.” Setser v. United States, 566 U.S. 231, 236 (2012). The\\nSupreme Court has held that a district court may order that a federal sentence\\nrun consecutively to an anticipated but not yet imposed state sentence. Id. at\\n236–37. Yet the authority to choose a concurrent or consecutive sentence\\npresupposes the existence of another sentence. If a prisoner completes his\\nfederal sentence before another sentence is imposed, the BOP lacks the\\nauthority to hold him beyond his release date. 6 See 18 U.S.C. § 3624(a) (“A\\nprisoner shall be released by the Bureau of Prisons on the date of the expiration\\nof the prisoner’s term of imprisonment,” less credit for satisfactory behavior).\\n B.\\n We next review the district court’s contempt finding. “A party commits\\ncontempt when he violates a definite and specific order of the court requiring\\nhim to perform or refrain from performing a particular act or acts with\\nknowledge of the court’s order.” Waste Mgmt. of Wash., Inc. v. Kattler, 776 F.3d\\n336, 341 (5th Cir. 2015) (quoting Hornbeck Offshore Servs., LLC v. Salazar,\\n713 F.3d 787, 792 (5th Cir. 2013)). Contempt findings must be supported “by\\nclear and convincing evidence: 1) that a court order was in effect, 2) that the\\norder required certain conduct by the respondent, and 3) that the respondent\\nfailed to comply with the court’s order.” Am. Airlines, Inc. v. Allied Pilots Ass’n,\\n228 F.3d 574, 581 (5th Cir. 2000) (quotation omitted); see also Waste Mgmt. of\\nWash., 776 F.3d at 341. The district court’s factual findings are reviewed “for\\nclear error and its underlying conclusions of law de novo.” City of Jackson, 359\\nF.3d at 731.\\n The district court made no explicit factual findings to support its decision\\nto hold the BOP in contempt. Nor did it identify which specific court orders the\\n\\n\\n 6 If a prisoner is convicted on a state charge while still in BOP custody, the BOP\\nwill generally withdraw double credit for time served in state custody. See Sentence\\nComputation Manual at p. 1 – 24B.\\n 10\\n\\f Case: 18-50512 Document: 00514873161 Page: 11 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-50512\\nBOP violated, notwithstanding the BOP’s “request that the Court clarify its\\norder to reflect such findings as to how and when the Respondents violated an\\norder of th[e] court.” The district court’s refusal to identify the basis for its\\ncontempt finding was in itself an abuse of discretion.\\n Moreover, we can identify no evidence in the record to support the\\nconclusion that the BOP violated a “definite and specific” court order. Waste\\nMgmt. of Wash., 776 F.3d at 341. In light of its statements at the show cause\\nhearing, the district court appears to have deemed the BOP in contempt of\\nseveral of its revocation judgments. But the court did not identify any\\nparticular judgment that specifically instructed the BOP not to award credit\\nfor time served under 18 U.S.C. § 3585(b). The court instead expressed its view\\nthat the BOP should have interpreted the imposition of a consecutive sentence\\nto disallow credit for time served in state custody, even if no state sentence had\\nyet been imposed. As outlined above, such an interpretation is inconsistent\\nwith the statute and the Supreme Court’s holding in Wilson, 503 U.S. at 334.\\nThe BOP did not violate a court order by implementing the revocation\\njudgments according to governing law.\\n C.\\n Even if the district court had not erred in holding the BOP in contempt,\\nthe sanction imposed is contrary to law. The court ordered, in its cases only,\\nthat the BOP not award credit under 18 U.S.C. § 3585(b)(2) for time served in\\nstate detention when the district court imposes a consecutive sentence. This\\ninjunction is inconsistent with the mandatory language of § 3585(b), which\\nstates that “[a] defendant shall be given credit” if he meets the statutory\\nrequirements. As the Supreme Court has explained, “Because the offender has\\na right to certain jail-time credit under § 3585(b), and because the district court\\ncannot determine the amount of the credit at sentencing, the Attorney General\\n\\n\\n 11\\n\\f Case: 18-50512 Document: 00514873161 Page: 12 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-50512\\nhas no choice but to make the determination as an administrative matter when\\nimprisoning the defendant.” Wilson, 503 U.S. at 335 (emphasis added).\\n Given the district court’s lack of authority over credit awards, it was\\nimproper to order the BOP to deny custody credits required by statute. The\\ndistrict court’s error was compounded by its threat to hold BOP officials in\\nindividual contempt for fulfilling their statutory duties. Because the injunction\\nexceeds the district court’s legal authority, we need not address the BOP’s\\nalternative argument that it fails to comply with the specificity requirements\\nof Federal Rule of Civil Procedure 65(d)(1).\\n IV.\\n For the foregoing reasons, the district court’s contempt finding and\\ninjunction are REVERSED.\\n\\n\\n\\n\\n 12\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4377215/\", \"author_raw\": \"STEPHEN A. HIGGINSON, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"HIGGINBOTHAM"},"judge2":{"kind":"string","value":"SMITH"},"judge3":{"kind":"string","value":"HIGGINSON"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4599962/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: In RE: UNITED STATES BUREAU OF PRISONS, DEPARTMENT OF JUSTICE, Respondent - Appellant\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-14\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 18-50512 Document: 00514873161 Page: 1 Date Filed: 03/14/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT United States Court of Appeals\n Fifth Circuit\n\n FILED\n March 14, 2019\n No. 18-50512\n Lyle W. Cayce\n Clerk\n\nIn re: UNITED STATES BUREAU OF PRISONS, DEPARTMENT OF\nJUSTICE,\n\n Respondent - Appellant\n\n\n\n\n Appeal from the United States District Court\n for the Western District of Texas\n\n\nBefore HIGGINBOTHAM, SMITH, and HIGGINSON, Circuit Judges.\nSTEPHEN A. HIGGINSON, Circuit Judge:\n The U.S. Bureau of Prisons (BOP) appeals a contempt sanction related\nto its calculation of sentencing credits for federal prisoners. We reverse.\n I.\n A.\n This case began with a disagreement between the district court and the\nBOP regarding the implementation of the revocation sentence of Ruben\nHernandez. Hernandez was convicted in federal court of conspiracy to\ntransport illegal aliens and sentenced to twelve months’ imprisonment and\nthree years of supervised release. During his term of federal supervised\nrelease, Hernandez was arrested by local law enforcement and charged in state\ncourt with being a felon in possession of a firearm, theft of a firearm, and\npossession of cocaine. Hernandez spent over a year in pretrial detention on\nthese state charges. The two state firearm charges were later dismissed. On\n\f Case: 18-50512 Document: 00514873161 Page: 2 Date Filed: 03/14/2019\n\n\n\n No. 18-50512\nNovember 15, 2016, Hernandez was acquitted of the remaining state drug\npossession charge.\n Federal authorities took custody of Hernandez, and the government\npetitioned the district court to revoke his supervised release based on his\nalleged drug and firearm possession. On March 13, 2017, the district court\nrevoked Hernandez’s supervised release and sentenced him to 10 months\nimprisonment. At the revocation hearing, Hernandez requested credit for time\nserved in state custody. The district court orally denied this request. The\nrevocation judgment orders “that the defendant, Ruben Hernandez, be\ncommitted to the custody of the U.S. Bureau of Prisons for a term of TEN (10)\nmonths, pursuant to 18 U.S.C. § 3583(e)(3) with credit for time served from\nNovember 14, 2016 forward.” The BOP later determined that Hernandez\nwas entitled to credit for the 543 days he spent in detention following his state\narrest. Because Hernandez had already served more than his 10 month\nsentence, he was released.\n The district court learned of Hernandez’s release, and concluded that the\nBOP’s sentence calculation was inconsistent with the revocation judgment.\nAccording to the BOP, the district court then directed a probation officer to\ncontact the BOP and express the court’s disagreement with its credit\ncalculation. Romulo Armendariz, an Operations Manager at the BOP’s\nDesignation and Sentence Computation Center, responded that the BOP was\nrequired to give Hernandez credit for the full period he spent in state custody\nunder 18 U.S.C. § 3585(b). The district court, through the probation officer,\nmaintained that the BOP had made a mistake. The court requested that the\nBOP either take Hernandez back into custody or provide the name and mailing\naddress of a person to whom a summons could be sent for a Show Cause\nhearing.\n\n\n 2\n\f Case: 18-50512 Document: 00514873161 Page: 3 Date Filed: 03/14/2019\n\n\n\n No. 18-50512\n B.\n When the BOP did not re-arrest Hernandez, the district court opened a\ncivil contempt proceeding against Armendariz. 1 The court issued an order to\nshow cause why Armendariz should not be held in contempt for violating the\ncourt’s revocation order by improperly calculating Hernandez’s sentence. The\ndistrict court later issued a supplemental order to show cause related to the\ncalculation of the sentence of another defendant, Antonio Bustamante-Huerta,\nwho was released in 2012. 2 The district court subsequently added Craig\nPickles, Section Chief of Sentence Computation at the BOP, as an additional\nrespondent in the contempt proceeding.\n The district court held a contempt hearing on January 29, 2018. The\ncourt began by explaining that Armendariz and Pickles were named in their\nofficial capacities, and that the contempt proceeding was not against any\nindividual. The court then raised for the first time the case of another\ndefendant, Francisco Javier Hernandez, whose supervised release was revoked\nin 2011. The district court had ordered Francisco Hernandez’s sentence to run\nconsecutively to a pending state case. Yet because Francisco Hernandez had\nnot yet been convicted in state court at the time of the revocation, he was\nawarded credit for time served and released. He was later convicted in state\ncourt. The district court expressed its view that the BOP was in contempt of\n\n\n\n\n 1 The district court initially requested that the prosecutor involved in Ruben\nHernandez’s case prosecute the contempt proceeding. The U.S. Attorney’s Office declined the\ncourt’s invitation to prosecute the alleged contempt, stating that it concurred with the BOP’s\ncredit determination and did not believe that contempt was appropriate. The U.S. Attorney\ninformed the court that it would instead represent Armendariz. The district court stated that\nit intended to appoint a special prosecutor, but did not do so.\n 2 Armendariz attests that he was not personally involved in Bustamante-\nHuerta’s sentence computation, but that Bustamante-Huerta may have been released early\ndue to a data entry error.\n 3\n\f Case: 18-50512 Document: 00514873161 Page: 4 Date Filed: 03/14/2019\n\n\n\n No. 18-50512\ncourt because the BOP awarded credit for time served in state custody despite\nthe district court’s instruction that the federal sentence be consecutive.\n The BOP expressed its position that it is required by statute to award\ncredit for time served in official detention when that time has not been credited\nto another sentence. See 18 U.S.C. § 3585(b). The BOP repeatedly explained\nthat, although the district court has the authority to order a consecutive\nsentence, the BOP cannot run the federal sentence consecutively if there is no\nother sentence in place. Ruben Hernandez, for example, was acquitted in state\ncourt and therefore had no state sentence. The BOP acknowledged that, in\nsome instances, defendants are awarded credit for time served in pretrial state\ndetention, released from federal custody, and subsequently convicted in state\ncourt. But the BOP explained that it must “compute the sentence in the here\nand now,” and it cannot hold prisoners indefinitely “until we find out what’s\ngoing to happen in the future.” The BOP nonetheless promised “to\ncommunicate the Court’s concerns to the Bureau and see if we can come up\nwith some type of resolution.”\n The district court then ordered the BOP to file an “advisory to the Court”\nexplaining its position. The court stated that its “suggestion would be to follow\nthe statute unless you have a court order saying otherwise.” The BOP filed a\n“Court Advisory” restating its legal position. Dissatisfied with this response,\nthe district court set another hearing “to determine the appropriate sanctions\nto be imposed.” After receiving this order, the BOP requested clarification as\nto what contempt findings the district court had made. The district court\ndenied the request for clarification, stating that it would amount to an advisory\nopinion, and reiterated that a hearing would be held to determine sanctions.\n On April 25, 2018, the district court held a sanctions hearing. The court\nsubstituted the BOP for the named individual respondents. The court\nreiterated its view that it has the authority to order consecutive sentences, and\n 4\n\f Case: 18-50512 Document: 00514873161 Page: 5 Date Filed: 03/14/2019\n\n\n\n No. 18-50512\nthat the BOP is not running sentences consecutively when it gives prisoners\ncredit for time served on unadjudicated state cases. At the conclusion of the\nhearing, the district court stated that it was ordering the BOP not to award\ncredit under § 3585(b)(2) for time served in state detention when the district\ncourt imposes a consecutive sentence. The court described this order as a\n“sanction.” The court further explained that its order would apply “[i]n my\ncases only,” not nationwide, “[a]nd anybody that violates that injunction will\nthen be facing [a] personal, individual contempt situation.”\n The district court took no further action in the case. On June 25, 2018,\nthe BOP filed a notice of appeal from the district court’s April 25, 2018 decision.\n II.\n We must first assure ourselves of our jurisdiction. See Hill v. City of\nSeven Points, 230 F.3d 167, 169 (5th Cir. 2000). The BOP asserts that the\ndistrict court’s contempt sanction is either a final decision appealable under 28\nU.S.C. § 1291 or an interlocutory injunction appealable under 28 U.S.C.\n§ 1292(a)(1). We have jurisdiction under § 1291, and therefore need not\naddress § 1292(a)(1).\n “The general rule in this circuit is that civil contempt orders are not\nappealable final orders for the purposes of 28 U.S.C. § 1291,” but an exception\n“exists ‘[w]hen a civil contempt motion is not part of continuing litigation, . . .\nbecause no underlying case awaits final resolution.’” Quilling v. Funding\nResource Grp., 227 F.3d 231, 234 (5th Cir. 2000) (quoting In re Grand Jury\nSubpoena for Attorney Representing Criminal Defendant Reyes-Requena, 926\nF.2d 1423, 1429 (5th Cir. 1991)). This is a standalone civil contempt proceeding\ninitiated by the district court. We therefore have jurisdiction under § 1291 so\nlong as the district court issued a final decision in this matter.\n “A decision is final when it ‘ends the litigation on the merits and leaves\nnothing for the court to do but execute the judgment.’” Askanase v. Livingwell,\n 5\n\f Case: 18-50512 Document: 00514873161 Page: 6 Date Filed: 03/14/2019\n\n\n\n No. 18-50512\nInc., 981 F.2d 807, 810 (5th Cir. 1993) (quoting Coopers & Lybrand v. Livesay,\n437 U.S. 463, 467 (1978)). A “civil contempt order is not ‘final’ for purposes of\nappeal unless two actions occur: (1) a finding of contempt is issued, and (2) an\nappropriate sanction is imposed.” In re U.S. Abatement Corp., 39 F.3d 563, 567\n(5th Cir. 1994). The district court in this case did not make an explicit contempt\nfinding. And despite the BOP’s request for clarification, the court refused to\nexplain the factual or legal basis for its conclusion that the BOP had violated\na court order.\n We nonetheless find that the district court held the BOP in contempt.\nThe court repeatedly expressed its view that the BOP was violating its\nrevocation judgments, and twice stated that it would hold a hearing to\ndetermine appropriate sanctions. The district court then imposed a final\nsanction in the form of an oral injunction against the BOP. The court did not\nenter a written order, despite indicating at the sanctions hearing that it\nplanned to do so. But the oral injunction was not tentative, and the district\ncourt did not indicate that the sanction was open to further argument or\nreconsideration. Rather, the district court asked the BOP to affirm that it\nunderstood the scope of the injunction. The court also made clear that the\ninjunction would be effective immediately and stated that, “after today, if some\nindividual in BOP were to execute their duty in a manner in violation of this\nCourt’s findings, it would be individual liability.”\n The BOP understandably interprets this order to signify that its officials\nare now operating under the threat of individual contempt sanctions. We have\npreviously affirmed a contempt sanction for the violation of an oral injunction,\nwhere the contemnor was aware of the injunction and “in fact considered\n\n\n\n\n 6\n\f Case: 18-50512 Document: 00514873161 Page: 7 Date Filed: 03/14/2019\n\n\n\n No. 18-50512\nhimself bound by” it. In re Bradley, 588 F.3d 254, 263 (5th Cir. 2009). 3 The\nimmediate effect of the district court’s order distinguishes this case from\ncontempt sanctions that we have held to be non-final, such as monetary\nsanctions in an amount yet to be determined. See Thornton v. General Motors\nCorp., 136 F.3d 450, 453 (5th Cir. 1998) (holding that an order suspending\nattorney from practice effectively immediately was an appealable final\nsanction, but an order imposing unquantified attorney’s fees was not final); see\nalso Cruz v. Fulton, 714 F. App’x 393, 396 (5th Cir. 2018) (finding no\njurisdiction because “the dollar amount of contempt sanctions remains yet to\nbe determined”). Under these circumstances, the district court’s failure to put\nits injunction in writing does not render its order non-final.\n We note that it is highly unusual for a district court to make a finding of\ncontempt and to issue a contempt sanction without entering a written order\nexplaining the basis for its findings and describing the sanction imposed. These\nomissions are relevant to the merits of this appeal. But a lack of procedural\nformality does not shield a district court’s final decisions from appellate review\nunder 28 U.S.C. § 1291. 4\n\n\n 3 Other circuits similarly treat oral injunctions as enforceable orders. See, e.g.,\nLau v. Meddaugh, 229 F.3d 121, 123, 123 n.2 (2d Cir. 2000); In re Charlotte Observer, 921\nF.2d 47, 48, 50 (4th Cir. 1990). We agree with the Second Circuit that, although Federal Rule\nof Civil Procedure 65(d) “contemplates the issuance of a written order,” a district “court’s\nfailure to comply with the specific requirements of this rule does not render the injunction\nvoid.” Lau, 229 F.3d at 123, 123 n.2; see also Test Masters Educ. Servs., Inc. v. Singh, 428\nF.3d 559, 577 (5th Cir. 2005) (explaining that a district court’s failure to fully comply with\nRule 65(d) “does not require that the injunction be reversed or vacated”) (quotation omitted).\nAs we noted in Bradley, 588 F.3d at 261–63, the Seventh Circuit appears to take a different\nposition. See Bates v. Johnson, 901 F.2d 1424, 1427–28 (7th Cir. 1990) (holding that an oral\ninjunction is not enforceable, and therefore not appealable). We do not follow the Seventh\nCircuit’s view that a party “is under no judicial compulsion” until a judge “record[s] an\ninjunction or declaratory judgment on a separate document.” Id. at 1428.\n 4 The district court did not set out its order in a separate document as required\nby Federal Rule of Civil Procedure 58(a). But this “failure to set forth a judgment or order on\na separate document when required by [Rule] 58(a) does not affect the validity of an appeal\nfrom that judgment or order.” FED. R. APP. P. 4(a)(7)(B); see also Moreno v. LG Electronics,\n 7\n\f Case: 18-50512 Document: 00514873161 Page: 8 Date Filed: 03/14/2019\n\n\n\n No. 18-50512\n III.\n “We review contempt orders and sanctions imposed under a court’s\ninherent powers for an abuse of discretion.” United States v. City of Jackson,\nMiss., 359 F.3d 727, 731 (5th Cir. 2004). A district court’s inherent power to\nsanction contempt “is not a broad reservoir of power, ready at an imperial\nhand, but a limited source; an implied power squeezed from the need to make\nthe court function.” NASCO, Inc. v. Calcasieu Television and Radio, Inc., 894\nF.2d 696, 702 (5th Cir. 1990); see also Crowe v. Smith, 151 F.3d 217, 226 (5th\nCir. 1998). As “inherent powers are shielded from direct democratic controls,\nthey must be exercised with restraint and discretion.” Roadway Express, Inc.\nv. Piper, 447 U.S. 752, 764 (1980). The contempt power is not an appropriate\nmeans for a district court to express its reasoned disagreement with a federal\nstatute. Threatening government officials with individual contempt sanctions\nfor complying with federal law, as the district court did here, is a clear abuse\nof discretion.\n A.\n We first briefly review the legal framework governing the calculation of\nsentencing credits. The Sentencing Reform Act of 1984 provides:\n A defendant shall be given credit toward the service of a term of\n imprisonment for any time he has spent in official detention prior\n to the date the sentence commences\n\n (1) as a result of the offense for which the sentence was imposed;\n or\n (2) as a result of any other charge for which the defendant was\n arrested after the commission of the offense for which the sentence\n was imposed;\n\n that has not been credited against another sentence.\n\n\nUSA Inc., 800 F.3d 692, 696–97 (5th Cir. 2015) (noting that Rule 4, as amended, states that\na failure to comply with Rule 58(a) does not affect the validity of the appeal).\n 8\n\f Case: 18-50512 Document: 00514873161 Page: 9 Date Filed: 03/14/2019\n\n\n\n No. 18-50512\n18 U.S.C. § 3585(b).\n The Supreme Court has squarely held that § 3585(b) “does not authorize\na district court to compute the credit at sentencing.” United States v. Wilson,\n503 U.S. 329, 334 (1992). This responsibility belongs to the Attorney General,\nacting through the BOP. Id. at 335; see also Leal v. Tombone, 341 F.3d 427, 428\n(5th Cir. 2003). The BOP’s procedures for calculating credit under § 3585(b)\nare set out in its Sentence Computation Manual. See U.S. Dep’t of Justice,\nFederal Bureau of Prisons Program Statement No. 5880.28 (July 20, 1999). 5\n Confusion sometimes arises, as it did here, when a defendant requests\nthat the district court award credit for time served and the court purports to\ngrant or deny this request at sentencing. Because the district court lacks the\nauthority to award or deny credit, the BOP is not bound by its decision. See,\ne.g., Mehta v. Wigen, 597 F. App’x 676, 680 (3d Cir. 2015) (holding that the\nBOP erred in denying credit under § 3585(b) based on the sentencing court’s\nintent). The sentencing court does “retain residual authority” to consider a\ndefendant’s time in custody. United States v. Hankton, 875 F.3d 786, 792 (5th\nCir. 2017). If the court determines that the BOP will not credit a defendant’s\nprior time served, the court can reduce the defendant’s sentence under\n§ 5G1.3(b) or § 5K2.23 of the U.S. Sentencing Guidelines. Id. But the district\ncourt must calculate the defendant’s final sentence itself; it cannot simply\norder the BOP to award credit. Moreover, neither of these Guidelines\nprovisions authorizes a district court to increase a defendant’s sentence to deny\ncredit that the defendant is otherwise entitled under § 3585(b).\n District courts also “have discretion to select whether the sentences they\nimpose will run concurrently or consecutively with respect to other sentences\nthat they impose, or that have been imposed in other proceedings, including\n\n\n 5 The Manual is available at https://www.bop.gov/policy/progstat/5880_028.pdf.\n 9\n\f Case: 18-50512 Document: 00514873161 Page: 10 Date Filed: 03/14/2019\n\n\n\n No. 18-50512\nstate proceedings.” Setser v. United States, 566 U.S. 231, 236 (2012). The\nSupreme Court has held that a district court may order that a federal sentence\nrun consecutively to an anticipated but not yet imposed state sentence. Id. at\n236–37. Yet the authority to choose a concurrent or consecutive sentence\npresupposes the existence of another sentence. If a prisoner completes his\nfederal sentence before another sentence is imposed, the BOP lacks the\nauthority to hold him beyond his release date. 6 See 18 U.S.C. § 3624(a) (“A\nprisoner shall be released by the Bureau of Prisons on the date of the expiration\nof the prisoner’s term of imprisonment,” less credit for satisfactory behavior).\n B.\n We next review the district court’s contempt finding. “A party commits\ncontempt when he violates a definite and specific order of the court requiring\nhim to perform or refrain from performing a particular act or acts with\nknowledge of the court’s order.” Waste Mgmt. of Wash., Inc. v. Kattler, 776 F.3d\n336, 341 (5th Cir. 2015) (quoting Hornbeck Offshore Servs., LLC v. Salazar,\n713 F.3d 787, 792 (5th Cir. 2013)). Contempt findings must be supported “by\nclear and convincing evidence: 1) that a court order was in effect, 2) that the\norder required certain conduct by the respondent, and 3) that the respondent\nfailed to comply with the court’s order.” Am. Airlines, Inc. v. Allied Pilots Ass’n,\n228 F.3d 574, 581 (5th Cir. 2000) (quotation omitted); see also Waste Mgmt. of\nWash., 776 F.3d at 341. The district court’s factual findings are reviewed “for\nclear error and its underlying conclusions of law de novo.” City of Jackson, 359\nF.3d at 731.\n The district court made no explicit factual findings to support its decision\nto hold the BOP in contempt. Nor did it identify which specific court orders the\n\n\n 6 If a prisoner is convicted on a state charge while still in BOP custody, the BOP\nwill generally withdraw double credit for time served in state custody. See Sentence\nComputation Manual at p. 1 – 24B.\n 10\n\f Case: 18-50512 Document: 00514873161 Page: 11 Date Filed: 03/14/2019\n\n\n\n No. 18-50512\nBOP violated, notwithstanding the BOP’s “request that the Court clarify its\norder to reflect such findings as to how and when the Respondents violated an\norder of th[e] court.” The district court’s refusal to identify the basis for its\ncontempt finding was in itself an abuse of discretion.\n Moreover, we can identify no evidence in the record to support the\nconclusion that the BOP violated a “definite and specific” court order. Waste\nMgmt. of Wash., 776 F.3d at 341. In light of its statements at the show cause\nhearing, the district court appears to have deemed the BOP in contempt of\nseveral of its revocation judgments. But the court did not identify any\nparticular judgment that specifically instructed the BOP not to award credit\nfor time served under 18 U.S.C. § 3585(b). The court instead expressed its view\nthat the BOP should have interpreted the imposition of a consecutive sentence\nto disallow credit for time served in state custody, even if no state sentence had\nyet been imposed. As outlined above, such an interpretation is inconsistent\nwith the statute and the Supreme Court’s holding in Wilson, 503 U.S. at 334.\nThe BOP did not violate a court order by implementing the revocation\njudgments according to governing law.\n C.\n Even if the district court had not erred in holding the BOP in contempt,\nthe sanction imposed is contrary to law. The court ordered, in its cases only,\nthat the BOP not award credit under 18 U.S.C. § 3585(b)(2) for time served in\nstate detention when the district court imposes a consecutive sentence. This\ninjunction is inconsistent with the mandatory language of § 3585(b), which\nstates that “[a] defendant shall be given credit” if he meets the statutory\nrequirements. As the Supreme Court has explained, “Because the offender has\na right to certain jail-time credit under § 3585(b), and because the district court\ncannot determine the amount of the credit at sentencing, the Attorney General\n\n\n 11\n\f Case: 18-50512 Document: 00514873161 Page: 12 Date Filed: 03/14/2019\n\n\n\n No. 18-50512\nhas no choice but to make the determination as an administrative matter when\nimprisoning the defendant.” Wilson, 503 U.S. at 335 (emphasis added).\n Given the district court’s lack of authority over credit awards, it was\nimproper to order the BOP to deny custody credits required by statute. The\ndistrict court’s error was compounded by its threat to hold BOP officials in\nindividual contempt for fulfilling their statutory duties. Because the injunction\nexceeds the district court’s legal authority, we need not address the BOP’s\nalternative argument that it fails to comply with the specificity requirements\nof Federal Rule of Civil Procedure 65(d)(1).\n IV.\n For the foregoing reasons, the district court’s contempt finding and\ninjunction are REVERSED.\n\n\n\n\n 12\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: In RE: UNITED STATES BUREAU OF PRISONS, DEPARTMENT OF JUSTICE, Respondent - Appellant\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-14\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 18-50512 Document: 00514873161 Page: 1 Date Filed: 03/14/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n March 14, 2019\\n No. 18-50512\\n Lyle W. Cayce\\n Clerk\\n\\nIn re: UNITED STATES BUREAU OF PRISONS, DEPARTMENT OF\\nJUSTICE,\\n\\n Respondent - Appellant\\n\\n\\n\\n\\n Appeal from the United States District Court\\n for the Western District of Texas\\n\\n\\nBefore HIGGINBOTHAM, SMITH, and HIGGINSON, Circuit Judges.\\nSTEPHEN A. HIGGINSON, Circuit Judge:\\n The U.S. Bureau of Prisons (BOP) appeals a contempt sanction related\\nto its calculation of sentencing credits for federal prisoners. We reverse.\\n I.\\n A.\\n This case began with a disagreement between the district court and the\\nBOP regarding the implementation of the revocation sentence of Ruben\\nHernandez. Hernandez was convicted in federal court of conspiracy to\\ntransport illegal aliens and sentenced to twelve months’ imprisonment and\\nthree years of supervised release. During his term of federal supervised\\nrelease, Hernandez was arrested by local law enforcement and charged in state\\ncourt with being a felon in possession of a firearm, theft of a firearm, and\\npossession of cocaine. Hernandez spent over a year in pretrial detention on\\nthese state charges. The two state firearm charges were later dismissed. On\\n\\f Case: 18-50512 Document: 00514873161 Page: 2 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-50512\\nNovember 15, 2016, Hernandez was acquitted of the remaining state drug\\npossession charge.\\n Federal authorities took custody of Hernandez, and the government\\npetitioned the district court to revoke his supervised release based on his\\nalleged drug and firearm possession. On March 13, 2017, the district court\\nrevoked Hernandez’s supervised release and sentenced him to 10 months\\nimprisonment. At the revocation hearing, Hernandez requested credit for time\\nserved in state custody. The district court orally denied this request. The\\nrevocation judgment orders “that the defendant, Ruben Hernandez, be\\ncommitted to the custody of the U.S. Bureau of Prisons for a term of TEN (10)\\nmonths, pursuant to 18 U.S.C. § 3583(e)(3) with credit for time served from\\nNovember 14, 2016 forward.” The BOP later determined that Hernandez\\nwas entitled to credit for the 543 days he spent in detention following his state\\narrest. Because Hernandez had already served more than his 10 month\\nsentence, he was released.\\n The district court learned of Hernandez’s release, and concluded that the\\nBOP’s sentence calculation was inconsistent with the revocation judgment.\\nAccording to the BOP, the district court then directed a probation officer to\\ncontact the BOP and express the court’s disagreement with its credit\\ncalculation. Romulo Armendariz, an Operations Manager at the BOP’s\\nDesignation and Sentence Computation Center, responded that the BOP was\\nrequired to give Hernandez credit for the full period he spent in state custody\\nunder 18 U.S.C. § 3585(b). The district court, through the probation officer,\\nmaintained that the BOP had made a mistake. The court requested that the\\nBOP either take Hernandez back into custody or provide the name and mailing\\naddress of a person to whom a summons could be sent for a Show Cause\\nhearing.\\n\\n\\n 2\\n\\f Case: 18-50512 Document: 00514873161 Page: 3 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-50512\\n B.\\n When the BOP did not re-arrest Hernandez, the district court opened a\\ncivil contempt proceeding against Armendariz. 1 The court issued an order to\\nshow cause why Armendariz should not be held in contempt for violating the\\ncourt’s revocation order by improperly calculating Hernandez’s sentence. The\\ndistrict court later issued a supplemental order to show cause related to the\\ncalculation of the sentence of another defendant, Antonio Bustamante-Huerta,\\nwho was released in 2012. 2 The district court subsequently added Craig\\nPickles, Section Chief of Sentence Computation at the BOP, as an additional\\nrespondent in the contempt proceeding.\\n The district court held a contempt hearing on January 29, 2018. The\\ncourt began by explaining that Armendariz and Pickles were named in their\\nofficial capacities, and that the contempt proceeding was not against any\\nindividual. The court then raised for the first time the case of another\\ndefendant, Francisco Javier Hernandez, whose supervised release was revoked\\nin 2011. The district court had ordered Francisco Hernandez’s sentence to run\\nconsecutively to a pending state case. Yet because Francisco Hernandez had\\nnot yet been convicted in state court at the time of the revocation, he was\\nawarded credit for time served and released. He was later convicted in state\\ncourt. The district court expressed its view that the BOP was in contempt of\\n\\n\\n\\n\\n 1 The district court initially requested that the prosecutor involved in Ruben\\nHernandez’s case prosecute the contempt proceeding. The U.S. Attorney’s Office declined the\\ncourt’s invitation to prosecute the alleged contempt, stating that it concurred with the BOP’s\\ncredit determination and did not believe that contempt was appropriate. The U.S. Attorney\\ninformed the court that it would instead represent Armendariz. The district court stated that\\nit intended to appoint a special prosecutor, but did not do so.\\n 2 Armendariz attests that he was not personally involved in Bustamante-\\nHuerta’s sentence computation, but that Bustamante-Huerta may have been released early\\ndue to a data entry error.\\n 3\\n\\f Case: 18-50512 Document: 00514873161 Page: 4 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-50512\\ncourt because the BOP awarded credit for time served in state custody despite\\nthe district court’s instruction that the federal sentence be consecutive.\\n The BOP expressed its position that it is required by statute to award\\ncredit for time served in official detention when that time has not been credited\\nto another sentence. See 18 U.S.C. § 3585(b). The BOP repeatedly explained\\nthat, although the district court has the authority to order a consecutive\\nsentence, the BOP cannot run the federal sentence consecutively if there is no\\nother sentence in place. Ruben Hernandez, for example, was acquitted in state\\ncourt and therefore had no state sentence. The BOP acknowledged that, in\\nsome instances, defendants are awarded credit for time served in pretrial state\\ndetention, released from federal custody, and subsequently convicted in state\\ncourt. But the BOP explained that it must “compute the sentence in the here\\nand now,” and it cannot hold prisoners indefinitely “until we find out what’s\\ngoing to happen in the future.” The BOP nonetheless promised “to\\ncommunicate the Court’s concerns to the Bureau and see if we can come up\\nwith some type of resolution.”\\n The district court then ordered the BOP to file an “advisory to the Court”\\nexplaining its position. The court stated that its “suggestion would be to follow\\nthe statute unless you have a court order saying otherwise.” The BOP filed a\\n“Court Advisory” restating its legal position. Dissatisfied with this response,\\nthe district court set another hearing “to determine the appropriate sanctions\\nto be imposed.” After receiving this order, the BOP requested clarification as\\nto what contempt findings the district court had made. The district court\\ndenied the request for clarification, stating that it would amount to an advisory\\nopinion, and reiterated that a hearing would be held to determine sanctions.\\n On April 25, 2018, the district court held a sanctions hearing. The court\\nsubstituted the BOP for the named individual respondents. The court\\nreiterated its view that it has the authority to order consecutive sentences, and\\n 4\\n\\f Case: 18-50512 Document: 00514873161 Page: 5 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-50512\\nthat the BOP is not running sentences consecutively when it gives prisoners\\ncredit for time served on unadjudicated state cases. At the conclusion of the\\nhearing, the district court stated that it was ordering the BOP not to award\\ncredit under § 3585(b)(2) for time served in state detention when the district\\ncourt imposes a consecutive sentence. The court described this order as a\\n“sanction.” The court further explained that its order would apply “[i]n my\\ncases only,” not nationwide, “[a]nd anybody that violates that injunction will\\nthen be facing [a] personal, individual contempt situation.”\\n The district court took no further action in the case. On June 25, 2018,\\nthe BOP filed a notice of appeal from the district court’s April 25, 2018 decision.\\n II.\\n We must first assure ourselves of our jurisdiction. See Hill v. City of\\nSeven Points, 230 F.3d 167, 169 (5th Cir. 2000). The BOP asserts that the\\ndistrict court’s contempt sanction is either a final decision appealable under 28\\nU.S.C. § 1291 or an interlocutory injunction appealable under 28 U.S.C.\\n§ 1292(a)(1). We have jurisdiction under § 1291, and therefore need not\\naddress § 1292(a)(1).\\n “The general rule in this circuit is that civil contempt orders are not\\nappealable final orders for the purposes of 28 U.S.C. § 1291,” but an exception\\n“exists ‘[w]hen a civil contempt motion is not part of continuing litigation, . . .\\nbecause no underlying case awaits final resolution.’” Quilling v. Funding\\nResource Grp., 227 F.3d 231, 234 (5th Cir. 2000) (quoting In re Grand Jury\\nSubpoena for Attorney Representing Criminal Defendant Reyes-Requena, 926\\nF.2d 1423, 1429 (5th Cir. 1991)). This is a standalone civil contempt proceeding\\ninitiated by the district court. We therefore have jurisdiction under § 1291 so\\nlong as the district court issued a final decision in this matter.\\n “A decision is final when it ‘ends the litigation on the merits and leaves\\nnothing for the court to do but execute the judgment.’” Askanase v. Livingwell,\\n 5\\n\\f Case: 18-50512 Document: 00514873161 Page: 6 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-50512\\nInc., 981 F.2d 807, 810 (5th Cir. 1993) (quoting Coopers & Lybrand v. Livesay,\\n437 U.S. 463, 467 (1978)). A “civil contempt order is not ‘final’ for purposes of\\nappeal unless two actions occur: (1) a finding of contempt is issued, and (2) an\\nappropriate sanction is imposed.” In re U.S. Abatement Corp., 39 F.3d 563, 567\\n(5th Cir. 1994). The district court in this case did not make an explicit contempt\\nfinding. And despite the BOP’s request for clarification, the court refused to\\nexplain the factual or legal basis for its conclusion that the BOP had violated\\na court order.\\n We nonetheless find that the district court held the BOP in contempt.\\nThe court repeatedly expressed its view that the BOP was violating its\\nrevocation judgments, and twice stated that it would hold a hearing to\\ndetermine appropriate sanctions. The district court then imposed a final\\nsanction in the form of an oral injunction against the BOP. The court did not\\nenter a written order, despite indicating at the sanctions hearing that it\\nplanned to do so. But the oral injunction was not tentative, and the district\\ncourt did not indicate that the sanction was open to further argument or\\nreconsideration. Rather, the district court asked the BOP to affirm that it\\nunderstood the scope of the injunction. The court also made clear that the\\ninjunction would be effective immediately and stated that, “after today, if some\\nindividual in BOP were to execute their duty in a manner in violation of this\\nCourt’s findings, it would be individual liability.”\\n The BOP understandably interprets this order to signify that its officials\\nare now operating under the threat of individual contempt sanctions. We have\\npreviously affirmed a contempt sanction for the violation of an oral injunction,\\nwhere the contemnor was aware of the injunction and “in fact considered\\n\\n\\n\\n\\n 6\\n\\f Case: 18-50512 Document: 00514873161 Page: 7 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-50512\\nhimself bound by” it. In re Bradley, 588 F.3d 254, 263 (5th Cir. 2009). 3 The\\nimmediate effect of the district court’s order distinguishes this case from\\ncontempt sanctions that we have held to be non-final, such as monetary\\nsanctions in an amount yet to be determined. See Thornton v. General Motors\\nCorp., 136 F.3d 450, 453 (5th Cir. 1998) (holding that an order suspending\\nattorney from practice effectively immediately was an appealable final\\nsanction, but an order imposing unquantified attorney’s fees was not final); see\\nalso Cruz v. Fulton, 714 F. App’x 393, 396 (5th Cir. 2018) (finding no\\njurisdiction because “the dollar amount of contempt sanctions remains yet to\\nbe determined”). Under these circumstances, the district court’s failure to put\\nits injunction in writing does not render its order non-final.\\n We note that it is highly unusual for a district court to make a finding of\\ncontempt and to issue a contempt sanction without entering a written order\\nexplaining the basis for its findings and describing the sanction imposed. These\\nomissions are relevant to the merits of this appeal. But a lack of procedural\\nformality does not shield a district court’s final decisions from appellate review\\nunder 28 U.S.C. § 1291. 4\\n\\n\\n 3 Other circuits similarly treat oral injunctions as enforceable orders. See, e.g.,\\nLau v. Meddaugh, 229 F.3d 121, 123, 123 n.2 (2d Cir. 2000); In re Charlotte Observer, 921\\nF.2d 47, 48, 50 (4th Cir. 1990). We agree with the Second Circuit that, although Federal Rule\\nof Civil Procedure 65(d) “contemplates the issuance of a written order,” a district “court’s\\nfailure to comply with the specific requirements of this rule does not render the injunction\\nvoid.” Lau, 229 F.3d at 123, 123 n.2; see also Test Masters Educ. Servs., Inc. v. Singh, 428\\nF.3d 559, 577 (5th Cir. 2005) (explaining that a district court’s failure to fully comply with\\nRule 65(d) “does not require that the injunction be reversed or vacated”) (quotation omitted).\\nAs we noted in Bradley, 588 F.3d at 261–63, the Seventh Circuit appears to take a different\\nposition. See Bates v. Johnson, 901 F.2d 1424, 1427–28 (7th Cir. 1990) (holding that an oral\\ninjunction is not enforceable, and therefore not appealable). We do not follow the Seventh\\nCircuit’s view that a party “is under no judicial compulsion” until a judge “record[s] an\\ninjunction or declaratory judgment on a separate document.” Id. at 1428.\\n 4 The district court did not set out its order in a separate document as required\\nby Federal Rule of Civil Procedure 58(a). But this “failure to set forth a judgment or order on\\na separate document when required by [Rule] 58(a) does not affect the validity of an appeal\\nfrom that judgment or order.” FED. R. APP. P. 4(a)(7)(B); see also Moreno v. LG Electronics,\\n 7\\n\\f Case: 18-50512 Document: 00514873161 Page: 8 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-50512\\n III.\\n “We review contempt orders and sanctions imposed under a court’s\\ninherent powers for an abuse of discretion.” United States v. City of Jackson,\\nMiss., 359 F.3d 727, 731 (5th Cir. 2004). A district court’s inherent power to\\nsanction contempt “is not a broad reservoir of power, ready at an imperial\\nhand, but a limited source; an implied power squeezed from the need to make\\nthe court function.” NASCO, Inc. v. Calcasieu Television and Radio, Inc., 894\\nF.2d 696, 702 (5th Cir. 1990); see also Crowe v. Smith, 151 F.3d 217, 226 (5th\\nCir. 1998). As “inherent powers are shielded from direct democratic controls,\\nthey must be exercised with restraint and discretion.” Roadway Express, Inc.\\nv. Piper, 447 U.S. 752, 764 (1980). The contempt power is not an appropriate\\nmeans for a district court to express its reasoned disagreement with a federal\\nstatute. Threatening government officials with individual contempt sanctions\\nfor complying with federal law, as the district court did here, is a clear abuse\\nof discretion.\\n A.\\n We first briefly review the legal framework governing the calculation of\\nsentencing credits. The Sentencing Reform Act of 1984 provides:\\n A defendant shall be given credit toward the service of a term of\\n imprisonment for any time he has spent in official detention prior\\n to the date the sentence commences\\n\\n (1) as a result of the offense for which the sentence was imposed;\\n or\\n (2) as a result of any other charge for which the defendant was\\n arrested after the commission of the offense for which the sentence\\n was imposed;\\n\\n that has not been credited against another sentence.\\n\\n\\nUSA Inc., 800 F.3d 692, 696–97 (5th Cir. 2015) (noting that Rule 4, as amended, states that\\na failure to comply with Rule 58(a) does not affect the validity of the appeal).\\n 8\\n\\f Case: 18-50512 Document: 00514873161 Page: 9 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-50512\\n18 U.S.C. § 3585(b).\\n The Supreme Court has squarely held that § 3585(b) “does not authorize\\na district court to compute the credit at sentencing.” United States v. Wilson,\\n503 U.S. 329, 334 (1992). This responsibility belongs to the Attorney General,\\nacting through the BOP. Id. at 335; see also Leal v. Tombone, 341 F.3d 427, 428\\n(5th Cir. 2003). The BOP’s procedures for calculating credit under § 3585(b)\\nare set out in its Sentence Computation Manual. See U.S. Dep’t of Justice,\\nFederal Bureau of Prisons Program Statement No. 5880.28 (July 20, 1999). 5\\n Confusion sometimes arises, as it did here, when a defendant requests\\nthat the district court award credit for time served and the court purports to\\ngrant or deny this request at sentencing. Because the district court lacks the\\nauthority to award or deny credit, the BOP is not bound by its decision. See,\\ne.g., Mehta v. Wigen, 597 F. App’x 676, 680 (3d Cir. 2015) (holding that the\\nBOP erred in denying credit under § 3585(b) based on the sentencing court’s\\nintent). The sentencing court does “retain residual authority” to consider a\\ndefendant’s time in custody. United States v. Hankton, 875 F.3d 786, 792 (5th\\nCir. 2017). If the court determines that the BOP will not credit a defendant’s\\nprior time served, the court can reduce the defendant’s sentence under\\n§ 5G1.3(b) or § 5K2.23 of the U.S. Sentencing Guidelines. Id. But the district\\ncourt must calculate the defendant’s final sentence itself; it cannot simply\\norder the BOP to award credit. Moreover, neither of these Guidelines\\nprovisions authorizes a district court to increase a defendant’s sentence to deny\\ncredit that the defendant is otherwise entitled under § 3585(b).\\n District courts also “have discretion to select whether the sentences they\\nimpose will run concurrently or consecutively with respect to other sentences\\nthat they impose, or that have been imposed in other proceedings, including\\n\\n\\n 5 The Manual is available at https://www.bop.gov/policy/progstat/5880_028.pdf.\\n 9\\n\\f Case: 18-50512 Document: 00514873161 Page: 10 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-50512\\nstate proceedings.” Setser v. United States, 566 U.S. 231, 236 (2012). The\\nSupreme Court has held that a district court may order that a federal sentence\\nrun consecutively to an anticipated but not yet imposed state sentence. Id. at\\n236–37. Yet the authority to choose a concurrent or consecutive sentence\\npresupposes the existence of another sentence. If a prisoner completes his\\nfederal sentence before another sentence is imposed, the BOP lacks the\\nauthority to hold him beyond his release date. 6 See 18 U.S.C. § 3624(a) (“A\\nprisoner shall be released by the Bureau of Prisons on the date of the expiration\\nof the prisoner’s term of imprisonment,” less credit for satisfactory behavior).\\n B.\\n We next review the district court’s contempt finding. “A party commits\\ncontempt when he violates a definite and specific order of the court requiring\\nhim to perform or refrain from performing a particular act or acts with\\nknowledge of the court’s order.” Waste Mgmt. of Wash., Inc. v. Kattler, 776 F.3d\\n336, 341 (5th Cir. 2015) (quoting Hornbeck Offshore Servs., LLC v. Salazar,\\n713 F.3d 787, 792 (5th Cir. 2013)). Contempt findings must be supported “by\\nclear and convincing evidence: 1) that a court order was in effect, 2) that the\\norder required certain conduct by the respondent, and 3) that the respondent\\nfailed to comply with the court’s order.” Am. Airlines, Inc. v. Allied Pilots Ass’n,\\n228 F.3d 574, 581 (5th Cir. 2000) (quotation omitted); see also Waste Mgmt. of\\nWash., 776 F.3d at 341. The district court’s factual findings are reviewed “for\\nclear error and its underlying conclusions of law de novo.” City of Jackson, 359\\nF.3d at 731.\\n The district court made no explicit factual findings to support its decision\\nto hold the BOP in contempt. Nor did it identify which specific court orders the\\n\\n\\n 6 If a prisoner is convicted on a state charge while still in BOP custody, the BOP\\nwill generally withdraw double credit for time served in state custody. See Sentence\\nComputation Manual at p. 1 – 24B.\\n 10\\n\\f Case: 18-50512 Document: 00514873161 Page: 11 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-50512\\nBOP violated, notwithstanding the BOP’s “request that the Court clarify its\\norder to reflect such findings as to how and when the Respondents violated an\\norder of th[e] court.” The district court’s refusal to identify the basis for its\\ncontempt finding was in itself an abuse of discretion.\\n Moreover, we can identify no evidence in the record to support the\\nconclusion that the BOP violated a “definite and specific” court order. Waste\\nMgmt. of Wash., 776 F.3d at 341. In light of its statements at the show cause\\nhearing, the district court appears to have deemed the BOP in contempt of\\nseveral of its revocation judgments. But the court did not identify any\\nparticular judgment that specifically instructed the BOP not to award credit\\nfor time served under 18 U.S.C. § 3585(b). The court instead expressed its view\\nthat the BOP should have interpreted the imposition of a consecutive sentence\\nto disallow credit for time served in state custody, even if no state sentence had\\nyet been imposed. As outlined above, such an interpretation is inconsistent\\nwith the statute and the Supreme Court’s holding in Wilson, 503 U.S. at 334.\\nThe BOP did not violate a court order by implementing the revocation\\njudgments according to governing law.\\n C.\\n Even if the district court had not erred in holding the BOP in contempt,\\nthe sanction imposed is contrary to law. The court ordered, in its cases only,\\nthat the BOP not award credit under 18 U.S.C. § 3585(b)(2) for time served in\\nstate detention when the district court imposes a consecutive sentence. This\\ninjunction is inconsistent with the mandatory language of § 3585(b), which\\nstates that “[a] defendant shall be given credit” if he meets the statutory\\nrequirements. As the Supreme Court has explained, “Because the offender has\\na right to certain jail-time credit under § 3585(b), and because the district court\\ncannot determine the amount of the credit at sentencing, the Attorney General\\n\\n\\n 11\\n\\f Case: 18-50512 Document: 00514873161 Page: 12 Date Filed: 03/14/2019\\n\\n\\n\\n No. 18-50512\\nhas no choice but to make the determination as an administrative matter when\\nimprisoning the defendant.” Wilson, 503 U.S. at 335 (emphasis added).\\n Given the district court’s lack of authority over credit awards, it was\\nimproper to order the BOP to deny custody credits required by statute. The\\ndistrict court’s error was compounded by its threat to hold BOP officials in\\nindividual contempt for fulfilling their statutory duties. Because the injunction\\nexceeds the district court’s legal authority, we need not address the BOP’s\\nalternative argument that it fails to comply with the specificity requirements\\nof Federal Rule of Civil Procedure 65(d)(1).\\n IV.\\n For the foregoing reasons, the district court’s contempt finding and\\ninjunction are REVERSED.\\n\\n\\n\\n\\n 12\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1089,"cells":{"id":{"kind":"number","value":4600876,"string":"4,600,876"},"name":{"kind":"string","value":"PAPALOTE CREEK II, L.L.C., Formerly Known as Papalote Creek Windfarm II, L.L.C., Plaintiff-Appellant, v. LOWER COLORADO RIVER AUTHORITY, Defendant-Appellee."},"name_abbreviation":{"kind":"string","value":"Papalote Creek II, L.L.C. v. Lower Colorado River"},"decision_date":{"kind":"string","value":"2019-03-15"},"docket_number":{"kind":"string","value":"17-50852"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before HIGGINBOTHAM, ELROD, and HO, Circuit Judges.\", \"parties\": \"\", \"opinions\": [{\"author\": \"JENNIFER WALKER ELROD, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 17-50852 Document: 00514875536 Page: 1 Date Filed: 03/15/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n March 15, 2019\\n No. 17-50852 Lyle W. Cayce\\n Clerk\\n\\nPAPALOTE CREEK II, L.L.C., formerly known as Papalote Creek Windfarm\\nII, L.L.C.,\\n\\n Plaintiff–Appellant,\\n\\nv.\\n\\nLOWER COLORADO RIVER AUTHORITY,\\n\\n Defendant–Appellee.\\n\\n\\n\\n\\n Appeal from the United States District Court\\n for the Western District of Texas\\n\\n\\nBefore HIGGINBOTHAM, ELROD, and HO, Circuit Judges.\\nJENNIFER WALKER ELROD, Circuit Judge:\\n Papalote Creek II, LLC (Papalote) appeals the district court’s order\\ncompelling Papalote to arbitrate a dispute raised by Lower Colorado River\\nAuthority (LCRA)—whether their contractual agreement limits LCRA’s\\nliability to $60 million. The arbitration clause requires Papalote and LCRA to\\narbitrate “any dispute [that] arises with respect to either [p]arty’s\\nperformance.” Because the dispute that LCRA has raised is an interpretative\\ndispute—not a performance dispute—we reverse and remand.\\n\\f Case: 17-50852 Document: 00514875536 Page: 2 Date Filed: 03/15/2019\\n\\n\\n\\n No. 17-50852\\n I.\\n This is the second time Papalote and LCRA have appeared before us. See\\nLower Colo. River Auth. v. Papalote Creek II, LLC, 858 F.3d 916 (5th Cir. 2017)\\n(Papalote I). In the previous appeal, we vacated the district court’s order\\ncompelling arbitration on ripeness grounds without addressing whether\\nLCRA’s dispute is arbitrable. Id. at 918. This case has returned to us with\\nsubsequent procedural development after the remand. We summarized the\\nrelevant facts in Papalote I:\\n In December 2009, LCRA entered into a Power Purchase\\n Agreement [(Agreement)] with [Papalote]. Papalote planned to\\n build an 87-turbine wind farm in Texas . . . , and under the\\n [Agreement], LCRA agreed to purchase all of the energy . . . at a\\n fixed price for an 18-year term.\\n\\n Relevant to this appeal are four sections of the [Agreement]: § 4.3,\\n § 9.3, § 13.1, and § 13.2. First, § 4.3, which is entitled “Liquidated\\n Damages Due to [LCRA's] Failure to Take,” provides a formula for\\n how to calculate the liquidated damages that LCRA would owe to\\n Papalote in the event that LCRA failed to take all of the Project's\\n energy. As noted above, LCRA is required to take all of the energy\\n generated by the Project. However, should LCRA fail to do so, § 4.3\\n details how to calculate Papalote's “exclusive remedy” of liquidated\\n damages. This liquidated damages calculation would depend in\\n part on the difference between the [Agreement’s] fixed price and\\n the price that Papalote is otherwise able to obtain in selling the\\n energy.\\n\\n Second, § 9.3, which is entitled “Limitation on Damages for Certain\\n Types of Failures,” provides the following: [Papalote's] aggregate\\n liability for [its failure to construct and operate the wind farm by\\n the agreed-upon date] shall be limited in the aggregate to sixty\\n million dollars ($60,000,000). [LCRA's] damages for failure to\\n perform its material obligations under [the Agreement] shall\\n likewise be limited in the aggregate to sixty million dollars\\n ($60,000,000). . . .\\n\\n Finally, § 13.1 and § 13.2 provide a two-step arbitration procedure.\\n The first step, as dictated in § 13.1, requires, inter alia, that “[i]f\\n 2\\n\\fCase: 17-50852 Document: 00514875536 Page: 3 Date Filed: 03/15/2019\\n\\n\\n\\n No. 17-50852\\n any dispute arises with respect to either Party's performance\\n hereunder,” the senior officers of LCRA and Papalote meet in an\\n attempt to resolve the dispute. Under the second step, as outlined\\n in § 13.2, if the dispute is not resolved through the first step within\\n a certain timeframe, either party may submit that dispute “to\\n binding arbitration[.]” . . .\\n\\n Papalote completed construction of the Project in 2010, and in the\\n ensuing years, LCRA complied with its obligations under the\\n [Agreement] by purchasing all of the energy generated by the\\n Project. In April 2015, however, LCRA initiated discussions with\\n Papalote regarding the [Agreement]. . . . [I]n June 2015, LCRA\\n sent Papalote a letter stating that, pursuant to § 13.2, LCRA was\\n “initiat[ing] the arbitration process to resolve the dispute between\\n LCRA and Papalote regarding LCRA's limitation of liability under\\n the [Agreement] and its impact on LCRA's performance\\n obligations.” LCRA also noted that it “intends to continue to fully\\n perform its obligations under the [Agreement] during this\\n arbitration process.” . . . Papalote rejected LCRA’s request to\\n proceed to arbitration, reasoning that “[a]n academic question\\n about the damages LCRA might owe for a hypothetical breach\\n simply does not constitute a ‘dispute’ that is proper for arbitration\\n under the [Agreement].” Papalote also argued that a dispute over\\n LCRA’s potential liability limitation was not covered by the\\n arbitration provision in the PPA, which was limited to disputes\\n regarding performance obligations.\\n\\n Following Papalote’s refusal to arbitrate, LCRA filed a petition to\\n compel arbitration in Texas state court on June 30, 2015. Papalote\\n timely removed the petition to federal district court on the basis of\\n diversity jurisdiction. . . . In February 2016, the district court\\n granted LCRA's petition to compel arbitration. . . . [T]he district\\n court framed the question as “whether the dispute LCRA seeks to\\n arbitrate—whether or not LCRA's liability would be capped at $60\\n million in the event it elected to purchase from Papalote less than\\n the total amount of energy it contracted to buy—qualifies as a\\n dispute ‘with respect to either Party's performance’ under the\\n [Agreement].” In answering that question, the district court\\n recognized that, “in a certain sense, one could understand\\n ‘performance’ to concern only those promises which were the\\n essence of the [Agreement]—the sale and production of wind\\n energy—and conceptualize the buyer’s obligation to pay for failing\\n 3\\n\\f Case: 17-50852 Document: 00514875536 Page: 4 Date Filed: 03/15/2019\\n\\n\\n\\n No. 17-50852\\n to take as compensation for its failure to perform, rather than as\\n an independent performance obligation.” The district court\\n reasoned, however, that ‘the better view here . . . is that LCRA’s\\n bargained-for-obligation to pay Papalote a specified sum if LCRA\\n takes less than all of the energy produced is itself a performance\\n obligation under the [Agreement].”\\n\\nId. at 919–20.\\n Although Papalote appealed the order compelling arbitration, the\\ndistrict court denied a stay of arbitration pending appeal. Id. at 921 n.2.\\nPapalote, however, did not appeal the denial of a stay pending appeal; instead,\\non June 1, 2016, Papalote and LCRA submitted to us a “Joint Motion to Abate\\nAppeal Without Prejudice to Automatic Reinstatement” to allow the parties to\\nfully arbitrate. After we stayed the appeal, the parties arbitrated their\\ndispute, and on June 28, 2016, the arbitrator issued a decision in LCRA’s favor,\\nstating that § 9.3 of the Agreement limits LCRA’s liability to $60 million. After\\nthe arbitrator’s adverse decision, Papalote moved to reinstate the appeal,\\nwhich we granted. In addition to seeking the reinstatement of the appeal,\\nPapalote also initiated a separate suit in the district court by filing a motion to\\nvacate the arbitration award. The district court stayed the proceedings for\\nPapalote’s motion to vacate the arbitration award pending the appeal of the\\ninitial order compelling arbitration. While the appeal was pending, “[o]n\\nOctober 10, 2016, LCRA notified Papalote that it would cease taking energy\\nunder the [Agreement] beginning on October 12, 2016, and that its resulting\\nliquidated damages would be capped at $60 million per § 9.3.” Id.\\n In the previous appeal, Papalote argued that LCRA’s dispute: (1) was\\nnot ripe when the district court compelled arbitration; and (2) was outside the\\nscope of the arbitration clause. We agreed with Papalote that the dispute was\\nnot ripe because LCRA was still taking energy from Papalote when the district\\ncourt compelled arbitration. Id. at 927. In holding so, we concluded that\\n\\n 4\\n\\f Case: 17-50852 Document: 00514875536 Page: 5 Date Filed: 03/15/2019\\n\\n\\n\\n No. 17-50852\\nLCRA’s subsequent decision to cease taking energy after the district court\\ncompelled arbitration could not “retroactively cure the void order compelling\\nPapalote to an arbitration that it should not have been forced to attend at the\\ntime.” Id. Accordingly, we vacated the order compelling arbitration and\\nremanded without addressing the arbitrability issue. Id. n.6.\\n On remand, the district court dismissed LCRA’s initial suit concerning\\nits petition to compel arbitration. In Papalote’s separate suit to vacate the\\narbitration award, the district court lifted the stay, and LCRA filed a cross-\\nmotion to affirm the arbitration award and, alternatively, to compel another\\narbitration. Consistent with this court’s judgment in Papalote I, the district\\ncourt vacated the arbitration award as it was the fruit of an order that the\\ndistrict court had entered without subject matter jurisdiction. However,\\nholding that the dispute was now ripe and again concluding that the dispute\\nfell within the scope of the arbitration clause, the district court once again\\ncompelled arbitration. Papalote appeals, contending that LCRA’s dispute is\\noutside of the scope of the arbitration clause.\\n II.\\n A.\\n We review de novo whether the district court properly compelled\\narbitration. Hays v. HCA Holdings, Inc., 838 F.3d 605, 608 (5th Cir. 2016).\\nWe begin with “the proper framework for deciding when disputes are\\narbitrable.” Granite Rock Co. v. Int’l Bhd. of Teamsters, 561 U.S. 287, 297\\n(2010). “Under that framework, a court may order arbitration of a particular\\ndispute only where the court is satisfied that the parties agreed to arbitrate\\nthat dispute.” Id.; see also id. at 304 n.11 (“The test for arbitrability remains\\nwhether the parties consented to arbitrate the dispute in question.”). This\\nframework “involves two questions: ‘(1) whether there is a valid agreement to\\narbitrate between the parties; and (2) whether the dispute in question falls\\n 5\\n\\f Case: 17-50852 Document: 00514875536 Page: 6 Date Filed: 03/15/2019\\n\\n\\n\\n No. 17-50852\\nwithin the scope of that arbitration agreement.’ ” Gross v. GGNSC Southaven,\\nLLC, 817 F.3d 169, 176 (5th Cir. 2016) (quoting Tittle v. Enron Corp., 463 F.3d\\n410, 418 (5th Cir. 2006)). Because neither Papalote nor LCRA disputes the\\nvalidity of the Agreement’s arbitration clause, this appeal concerns only\\nwhether LCRA’s dispute falls within the scope of that arbitration clause.\\n Determining the scope of an arbitration clause is a matter of contract.\\nHebbronville Lone Star Rentals, LLC v. Sunbelt Rentals Indus. Servs., LLC,\\n898 F.3d 629, 632 (5th Cir. 2018); see also First Options of Chi., Inc. v. Kaplan,\\n514 U.S. 938, 943 (1995) (observing that arbitration is “simply a matter of\\ncontract” and “a way to resolve those disputes—but only those disputes—that\\nthe parties have agreed to submit to arbitration”). Under Texas law, the\\nprimary object of contract interpretation “is to ascertain and give effect to the\\nintent of the parties as that intent is expressed in the contract.” Seagull\\nEnergy E & P, Inc. v. Eland Energy, Inc., 207 S.W.3d 342, 345 (Tex. 2006).\\nAlthough both federal law and Texas law create a presumption in favor of\\narbitrability, “unambiguous language controls when the question is the scope\\nof an arbitrator’s power,” and the “policy that favors resolving doubts in favor\\nof arbitration ‘cannot serve to stretch a contractual clause beyond the scope\\nintended by the parties.’ ” Hebbronville Lone Star Rentals, 898 F.3d at 632–33\\n(quoting Smith v. Transp. Workers Union of Am., AFL-CIO Air Transp. Local\\n556, 374 F.3d 372, 375 (5th Cir. 2004)); see also G.T. Leach Builders, LLC v.\\nSapphire V.P., L.P., 458 S.W.3d 502, 521 (Tex. 2015) (discussing presumption\\nof arbitrability under Texas law).\\n The parties may agree upon a broad language in the arbitration clause\\neither by incorporating “[t]he standard broad arbitration provision\\nrecommended by the American Arbitration Association” or by creating their\\nown broad provision. United Offshore Co. v. So. Deepwater Pipeline Co., 899\\nF.2d 405, 409 (5th Cir. 1990). These standard arbitration provisions typically\\n 6\\n\\f Case: 17-50852 Document: 00514875536 Page: 7 Date Filed: 03/15/2019\\n\\n\\n\\n No. 17-50852\\nrequire arbitration of “[a]ny controversy or claim arising out of or relating to\\n[the] contract” or “any dispute . . . with respect to the interpretation or\\nperformance.” Id. at 409–10 (emphasis added) (quoting Mar-Len of La., Inc. v.\\nParsons-Gilbane, 773 F.2d 633, 634 (5th Cir. 1985)). “[W]hen parties choose\\nsuch broad language, only . . . ‘the most forceful evidence of a purpose to\\nexclude the claim from arbitration’ would render the dispute non-arbitrable.”\\nId. (quoting Mar-Len, 773 F.2d at 636).\\n Alternatively, the parties may agree upon a narrow language in the\\narbitration clause by deviating from the broad standard provisions and by\\nlimiting arbitration only to a subset of disputes that may arise out of the\\ncontract. See United Offshore, 374 F.3d at 410; see also Texaco, Inc. v. Am.\\nTrading Transp. Co., 644 F.2d 1152, 1154 (5th Cir. 1981) (relying on “more\\nrestrictive language limiting arbitration” in declining to compel arbitration).\\nFor example, the parties may limit arbitration to either interpretation-related\\ndisputes or performance-based disputes at the exclusion of other categories of\\ndisputes. Negrin v. Kalina, No. 09-Civ-6234, 2010 WL 2816809, at *5 (S.D.N.Y.\\nJuly 15, 2010) (“The parties’ use of precise language in the arbitration clause\\nsuggests an intent to limit arbitration to a particular subset of disputes.”); see\\nalso Taylor v. Inv’rs Assocs., Inc., 29 F.3d 211, 215 (5th Cir. 1994) (applying\\nexpressio unius est exclusio alterius to limit the arbitration clause’s application\\nto a subset of parties).\\n We have previously observed that if an arbitration clause “restricts [the\\narbitrator’s] power to an interpretation of the contract, it leaves the arbitrator\\npowerless to decide matters on which the agreement is silent.” United\\nOffshore, 899 F.3d at 410. In Beckham v. William Bayley Co., a contract for\\ndelivery of “standard” insect screens required arbitration of “[a]ny\\ndisagreement . . . as to the intent of [the] contract”—i.e., interpretation of the\\ncontract. 655 F. Supp. 288, 291 (N.D. Tex. 1987). “Had the parties disputed\\n 7\\n\\f Case: 17-50852 Document: 00514875536 Page: 8 Date Filed: 03/15/2019\\n\\n\\n\\n No. 17-50852\\nwhether the screens, as delivered, were in fact ‘standard’ screens, the\\narbitration clause would have required that the intent as to the meaning of the\\nterm ‘standard’ be resolved by arbitration.” Id. But the parties agreed on what\\n“standard” insect screens meant, and the dispute was simply over whether the\\ndelivered insect screens were damaged. Id. Because such a dispute concerned\\nperformance, the court held that the dispute fell outside the scope of the\\narbitration clause. Id.\\n The opposite is also true: If the arbitration clause limits arbitration to\\nperformance-related disputes, then the arbitrator cannot decide other matters,\\nsuch as interpretative disputes. Cf. Negrin, 2010 WL 2816809, at *6 (holding\\nthat “[t]he arbitration clause cover[ing] disputes relating to ‘non-\\nperformance’ ” did not apply when there was no allegation that “[d]efendants\\nfailed to discharge . . . any obligation under the [contract]”). The Seventh\\nCircuit has illustrated this distinction:\\n We can imagine a case in which both parties agree that for example\\n some form of notice is a condition precedent to performance, and\\n the only dispute is over whether the notice was given. That\\n dispute would be arbitrable if the arbitration clause included\\n performance disputes, not if it did not.\\n\\nSelcke v. New England Ins. Co., 995 F.2d 688, 690 (7th Cir. 1993). Thus, the\\nparties may decide what disputes they wish to submit to an arbitrator. If they\\nlimit arbitration to a specific category of disputes, at the exclusion of other\\ncategories of disputes, then the arbitrator’s power is limited to those disputes\\nto which the parties expressly consented. See First Options, 514 U.S. at 943.\\n Here, Papalote and LCRA agreed to submit to binding arbitration “[i]f\\nany dispute arises with respect to either Party’s performance.” This clause\\nclearly signifies the parties’ intent to limit arbitration to performance-related\\ndisputes only, and the arbitration clause neither requires nor authorizes\\n\\n\\n 8\\n\\f Case: 17-50852 Document: 00514875536 Page: 9 Date Filed: 03/15/2019\\n\\n\\n\\n No. 17-50852\\narbitration of disputes that are not performance-related disputes, such as\\ndisputes related to the interpretation of the Agreement.\\n B.\\n Because the Agreement limits arbitration to “any dispute [that] arises\\nwith respect to either Party’s performance,” LCRA’s dispute—whether the\\nAgreement limits LCRA’s liability to $60 million—is arbitrable only if it\\nconstitutes a dispute with respect to either LCRA’s or Papalote’s performance.\\nWe hold that LCRA’s dispute is a dispute related to the interpretation of the\\nAgreement, not a performance-related dispute, and thus does not fall within\\nthe scope of the Agreement’s arbitration clause.\\n Interpretative disputes arise when the parties disagree over a text’s\\nmeaning. See Interpretation, Black’s Law Dictionary (10th ed. 2014) (“The\\nascertainment of a text’s meaning[.]”). Here, LCRA’s own demand letter to\\nPapalote frames LCRA’s dispute as an interpretative dispute: The letter states\\nthat “[t]he dispute is whether LCRA’s liability is limited to $60,000,000 under\\nthe [Agreement’s § 9.3].” And even LCRA’s brief on appeal observes that this\\ndispute is “about the meaning of the [Agreement’s] liability limitation.”\\nLCRA’s Br. at 35 (emphasis added).\\n As Papalote points out, one needs only to examine the Agreement to\\ndetermine what the Agreement says and means, and what LCRA and Papalote\\nhad intended while drafting the Agreement. See Selcke, 995 F.2d at 690. The\\nissue in this case can be answered without any reference to factual allegations\\nof failure to perform. See Negrin, 2010 WL 2816809, at *6. Accordingly,\\nLCRA’s dispute is squarely in the realm of interpretation. 1 See also Papalote\\n\\n\\n 1 We are not alone in making this observation. The previous panel of this court has\\nmade similar observations—albeit in dictum—that this dispute revolved around\\ninterpretation. See Papalote I, 858 F.3d at 924. So did the district court. Although the\\ndistrict court ultimately concluded that this interpretative dispute related to performance,\\nthus constituting a performance-based dispute—a conclusion that we reject today—it could\\n 9\\n\\f Case: 17-50852 Document: 00514875536 Page: 10 Date Filed: 03/15/2019\\n\\n\\n\\n No. 17-50852\\nI, 858 F.3d at 924 (noting in dicta that “the underlying claim that LCRA sought\\nto arbitrate is effectively one for a declaratory judgment [by an arbitrator] that\\nits interpretation of § 9.3 is correct.”). Here, although Papalote and LCRA\\ncontractually committed “to have someone—other than a judge—decide”\\nperformance-related disputes, they did not agree to have an arbitrator decide\\nmatters of contract interpretation. In re M.W.M., Jr., 523 S.W.3d 203, 207\\n(Tex. App.—Dallas 2017).\\n In resisting this conclusion, LCRA heavily relies on the phrase “with\\nrespect to,” which, it contends, means “relating to.” LCRA argues that, because\\nthe interpretative dispute “relat[es] to LCRA’s ongoing and future performance\\nunder the [Agreement],” the interpretative dispute is a dispute “with respect\\nto” performance. However, § 9.3 is a damages provision, not a provision about\\nperformance, and LCRA’s interpretative dispute is with respect to damages,\\nnot performance. Therefore, even if we agree with LCRA’s broad reading of\\nthe phrase “with respect to,” LCRA cannot prevail. Because LCRA’s\\ninterpretative dispute is outside the scope of the arbitration clause, the district\\ncourt erred in compelling Papalote to arbitrate.\\n III.\\n For the foregoing reasons, we REVERSE the district court’s order\\ncompelling arbitration and REMAND for further proceedings consistent with\\nthis opinion.\\n\\n\\n\\n\\nnot avoid observing that LCRA’s dispute “concerns the proper interpretation of a clause in\\nthe [Agreement].” Thus, even though LCRA may contend that it has raised a performance-\\nrelated dispute, those who have examined its dispute have unavoidably characterized this as\\nan interpretative one. See Tidelands Marine Serv. v. Patterson, 719 F.2d 126, 128 n.3 (5th\\nCir. 1983) (“That which looks like a duck, walks like a duck, and quacks like a duck will be\\ntreated as a duck even though some would insist upon calling it a chicken.”).\\n 10\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4378129/\", \"author_raw\": \"JENNIFER WALKER ELROD, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"HIGGINBOTHAM"},"judge2":{"kind":"string","value":"ELROD"},"judge3":{"kind":"string","value":"HO"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"HIGGINBOTHAM\": \", Circuit\", \"ELROD\": \", Circuit\", \"HO\": \", Circuit\"}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4600876/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: PAPALOTE CREEK II, L.L.C., Formerly Known as Papalote Creek Windfarm II, L.L.C., Plaintiff-Appellant, v. LOWER COLORADO RIVER AUTHORITY, Defendant-Appellee.\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-15\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 17-50852 Document: 00514875536 Page: 1 Date Filed: 03/15/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\n United States Court of Appeals\n Fifth Circuit\n\n FILED\n March 15, 2019\n No. 17-50852 Lyle W. Cayce\n Clerk\n\nPAPALOTE CREEK II, L.L.C., formerly known as Papalote Creek Windfarm\nII, L.L.C.,\n\n Plaintiff–Appellant,\n\nv.\n\nLOWER COLORADO RIVER AUTHORITY,\n\n Defendant–Appellee.\n\n\n\n\n Appeal from the United States District Court\n for the Western District of Texas\n\n\nBefore HIGGINBOTHAM, ELROD, and HO, Circuit Judges.\nJENNIFER WALKER ELROD, Circuit Judge:\n Papalote Creek II, LLC (Papalote) appeals the district court’s order\ncompelling Papalote to arbitrate a dispute raised by Lower Colorado River\nAuthority (LCRA)—whether their contractual agreement limits LCRA’s\nliability to $60 million. The arbitration clause requires Papalote and LCRA to\narbitrate “any dispute [that] arises with respect to either [p]arty’s\nperformance.” Because the dispute that LCRA has raised is an interpretative\ndispute—not a performance dispute—we reverse and remand.\n\f Case: 17-50852 Document: 00514875536 Page: 2 Date Filed: 03/15/2019\n\n\n\n No. 17-50852\n I.\n This is the second time Papalote and LCRA have appeared before us. See\nLower Colo. River Auth. v. Papalote Creek II, LLC, 858 F.3d 916 (5th Cir. 2017)\n(Papalote I). In the previous appeal, we vacated the district court’s order\ncompelling arbitration on ripeness grounds without addressing whether\nLCRA’s dispute is arbitrable. Id. at 918. This case has returned to us with\nsubsequent procedural development after the remand. We summarized the\nrelevant facts in Papalote I:\n In December 2009, LCRA entered into a Power Purchase\n Agreement [(Agreement)] with [Papalote]. Papalote planned to\n build an 87-turbine wind farm in Texas . . . , and under the\n [Agreement], LCRA agreed to purchase all of the energy . . . at a\n fixed price for an 18-year term.\n\n Relevant to this appeal are four sections of the [Agreement]: § 4.3,\n § 9.3, § 13.1, and § 13.2. First, § 4.3, which is entitled “Liquidated\n Damages Due to [LCRA's] Failure to Take,” provides a formula for\n how to calculate the liquidated damages that LCRA would owe to\n Papalote in the event that LCRA failed to take all of the Project's\n energy. As noted above, LCRA is required to take all of the energy\n generated by the Project. However, should LCRA fail to do so, § 4.3\n details how to calculate Papalote's “exclusive remedy” of liquidated\n damages. This liquidated damages calculation would depend in\n part on the difference between the [Agreement’s] fixed price and\n the price that Papalote is otherwise able to obtain in selling the\n energy.\n\n Second, § 9.3, which is entitled “Limitation on Damages for Certain\n Types of Failures,” provides the following: [Papalote's] aggregate\n liability for [its failure to construct and operate the wind farm by\n the agreed-upon date] shall be limited in the aggregate to sixty\n million dollars ($60,000,000). [LCRA's] damages for failure to\n perform its material obligations under [the Agreement] shall\n likewise be limited in the aggregate to sixty million dollars\n ($60,000,000). . . .\n\n Finally, § 13.1 and § 13.2 provide a two-step arbitration procedure.\n The first step, as dictated in § 13.1, requires, inter alia, that “[i]f\n 2\n\fCase: 17-50852 Document: 00514875536 Page: 3 Date Filed: 03/15/2019\n\n\n\n No. 17-50852\n any dispute arises with respect to either Party's performance\n hereunder,” the senior officers of LCRA and Papalote meet in an\n attempt to resolve the dispute. Under the second step, as outlined\n in § 13.2, if the dispute is not resolved through the first step within\n a certain timeframe, either party may submit that dispute “to\n binding arbitration[.]” . . .\n\n Papalote completed construction of the Project in 2010, and in the\n ensuing years, LCRA complied with its obligations under the\n [Agreement] by purchasing all of the energy generated by the\n Project. In April 2015, however, LCRA initiated discussions with\n Papalote regarding the [Agreement]. . . . [I]n June 2015, LCRA\n sent Papalote a letter stating that, pursuant to § 13.2, LCRA was\n “initiat[ing] the arbitration process to resolve the dispute between\n LCRA and Papalote regarding LCRA's limitation of liability under\n the [Agreement] and its impact on LCRA's performance\n obligations.” LCRA also noted that it “intends to continue to fully\n perform its obligations under the [Agreement] during this\n arbitration process.” . . . Papalote rejected LCRA’s request to\n proceed to arbitration, reasoning that “[a]n academic question\n about the damages LCRA might owe for a hypothetical breach\n simply does not constitute a ‘dispute’ that is proper for arbitration\n under the [Agreement].” Papalote also argued that a dispute over\n LCRA’s potential liability limitation was not covered by the\n arbitration provision in the PPA, which was limited to disputes\n regarding performance obligations.\n\n Following Papalote’s refusal to arbitrate, LCRA filed a petition to\n compel arbitration in Texas state court on June 30, 2015. Papalote\n timely removed the petition to federal district court on the basis of\n diversity jurisdiction. . . . In February 2016, the district court\n granted LCRA's petition to compel arbitration. . . . [T]he district\n court framed the question as “whether the dispute LCRA seeks to\n arbitrate—whether or not LCRA's liability would be capped at $60\n million in the event it elected to purchase from Papalote less than\n the total amount of energy it contracted to buy—qualifies as a\n dispute ‘with respect to either Party's performance’ under the\n [Agreement].” In answering that question, the district court\n recognized that, “in a certain sense, one could understand\n ‘performance’ to concern only those promises which were the\n essence of the [Agreement]—the sale and production of wind\n energy—and conceptualize the buyer’s obligation to pay for failing\n 3\n\f Case: 17-50852 Document: 00514875536 Page: 4 Date Filed: 03/15/2019\n\n\n\n No. 17-50852\n to take as compensation for its failure to perform, rather than as\n an independent performance obligation.” The district court\n reasoned, however, that ‘the better view here . . . is that LCRA’s\n bargained-for-obligation to pay Papalote a specified sum if LCRA\n takes less than all of the energy produced is itself a performance\n obligation under the [Agreement].”\n\nId. at 919–20.\n Although Papalote appealed the order compelling arbitration, the\ndistrict court denied a stay of arbitration pending appeal. Id. at 921 n.2.\nPapalote, however, did not appeal the denial of a stay pending appeal; instead,\non June 1, 2016, Papalote and LCRA submitted to us a “Joint Motion to Abate\nAppeal Without Prejudice to Automatic Reinstatement” to allow the parties to\nfully arbitrate. After we stayed the appeal, the parties arbitrated their\ndispute, and on June 28, 2016, the arbitrator issued a decision in LCRA’s favor,\nstating that § 9.3 of the Agreement limits LCRA’s liability to $60 million. After\nthe arbitrator’s adverse decision, Papalote moved to reinstate the appeal,\nwhich we granted. In addition to seeking the reinstatement of the appeal,\nPapalote also initiated a separate suit in the district court by filing a motion to\nvacate the arbitration award. The district court stayed the proceedings for\nPapalote’s motion to vacate the arbitration award pending the appeal of the\ninitial order compelling arbitration. While the appeal was pending, “[o]n\nOctober 10, 2016, LCRA notified Papalote that it would cease taking energy\nunder the [Agreement] beginning on October 12, 2016, and that its resulting\nliquidated damages would be capped at $60 million per § 9.3.” Id.\n In the previous appeal, Papalote argued that LCRA’s dispute: (1) was\nnot ripe when the district court compelled arbitration; and (2) was outside the\nscope of the arbitration clause. We agreed with Papalote that the dispute was\nnot ripe because LCRA was still taking energy from Papalote when the district\ncourt compelled arbitration. Id. at 927. In holding so, we concluded that\n\n 4\n\f Case: 17-50852 Document: 00514875536 Page: 5 Date Filed: 03/15/2019\n\n\n\n No. 17-50852\nLCRA’s subsequent decision to cease taking energy after the district court\ncompelled arbitration could not “retroactively cure the void order compelling\nPapalote to an arbitration that it should not have been forced to attend at the\ntime.” Id. Accordingly, we vacated the order compelling arbitration and\nremanded without addressing the arbitrability issue. Id. n.6.\n On remand, the district court dismissed LCRA’s initial suit concerning\nits petition to compel arbitration. In Papalote’s separate suit to vacate the\narbitration award, the district court lifted the stay, and LCRA filed a cross-\nmotion to affirm the arbitration award and, alternatively, to compel another\narbitration. Consistent with this court’s judgment in Papalote I, the district\ncourt vacated the arbitration award as it was the fruit of an order that the\ndistrict court had entered without subject matter jurisdiction. However,\nholding that the dispute was now ripe and again concluding that the dispute\nfell within the scope of the arbitration clause, the district court once again\ncompelled arbitration. Papalote appeals, contending that LCRA’s dispute is\noutside of the scope of the arbitration clause.\n II.\n A.\n We review de novo whether the district court properly compelled\narbitration. Hays v. HCA Holdings, Inc., 838 F.3d 605, 608 (5th Cir. 2016).\nWe begin with “the proper framework for deciding when disputes are\narbitrable.” Granite Rock Co. v. Int’l Bhd. of Teamsters, 561 U.S. 287, 297\n(2010). “Under that framework, a court may order arbitration of a particular\ndispute only where the court is satisfied that the parties agreed to arbitrate\nthat dispute.” Id.; see also id. at 304 n.11 (“The test for arbitrability remains\nwhether the parties consented to arbitrate the dispute in question.”). This\nframework “involves two questions: ‘(1) whether there is a valid agreement to\narbitrate between the parties; and (2) whether the dispute in question falls\n 5\n\f Case: 17-50852 Document: 00514875536 Page: 6 Date Filed: 03/15/2019\n\n\n\n No. 17-50852\nwithin the scope of that arbitration agreement.’ ” Gross v. GGNSC Southaven,\nLLC, 817 F.3d 169, 176 (5th Cir. 2016) (quoting Tittle v. Enron Corp., 463 F.3d\n410, 418 (5th Cir. 2006)). Because neither Papalote nor LCRA disputes the\nvalidity of the Agreement’s arbitration clause, this appeal concerns only\nwhether LCRA’s dispute falls within the scope of that arbitration clause.\n Determining the scope of an arbitration clause is a matter of contract.\nHebbronville Lone Star Rentals, LLC v. Sunbelt Rentals Indus. Servs., LLC,\n898 F.3d 629, 632 (5th Cir. 2018); see also First Options of Chi., Inc. v. Kaplan,\n514 U.S. 938, 943 (1995) (observing that arbitration is “simply a matter of\ncontract” and “a way to resolve those disputes—but only those disputes—that\nthe parties have agreed to submit to arbitration”). Under Texas law, the\nprimary object of contract interpretation “is to ascertain and give effect to the\nintent of the parties as that intent is expressed in the contract.” Seagull\nEnergy E & P, Inc. v. Eland Energy, Inc., 207 S.W.3d 342, 345 (Tex. 2006).\nAlthough both federal law and Texas law create a presumption in favor of\narbitrability, “unambiguous language controls when the question is the scope\nof an arbitrator’s power,” and the “policy that favors resolving doubts in favor\nof arbitration ‘cannot serve to stretch a contractual clause beyond the scope\nintended by the parties.’ ” Hebbronville Lone Star Rentals, 898 F.3d at 632–33\n(quoting Smith v. Transp. Workers Union of Am., AFL-CIO Air Transp. Local\n556, 374 F.3d 372, 375 (5th Cir. 2004)); see also G.T. Leach Builders, LLC v.\nSapphire V.P., L.P., 458 S.W.3d 502, 521 (Tex. 2015) (discussing presumption\nof arbitrability under Texas law).\n The parties may agree upon a broad language in the arbitration clause\neither by incorporating “[t]he standard broad arbitration provision\nrecommended by the American Arbitration Association” or by creating their\nown broad provision. United Offshore Co. v. So. Deepwater Pipeline Co., 899\nF.2d 405, 409 (5th Cir. 1990). These standard arbitration provisions typically\n 6\n\f Case: 17-50852 Document: 00514875536 Page: 7 Date Filed: 03/15/2019\n\n\n\n No. 17-50852\nrequire arbitration of “[a]ny controversy or claim arising out of or relating to\n[the] contract” or “any dispute . . . with respect to the interpretation or\nperformance.” Id. at 409–10 (emphasis added) (quoting Mar-Len of La., Inc. v.\nParsons-Gilbane, 773 F.2d 633, 634 (5th Cir. 1985)). “[W]hen parties choose\nsuch broad language, only . . . ‘the most forceful evidence of a purpose to\nexclude the claim from arbitration’ would render the dispute non-arbitrable.”\nId. (quoting Mar-Len, 773 F.2d at 636).\n Alternatively, the parties may agree upon a narrow language in the\narbitration clause by deviating from the broad standard provisions and by\nlimiting arbitration only to a subset of disputes that may arise out of the\ncontract. See United Offshore, 374 F.3d at 410; see also Texaco, Inc. v. Am.\nTrading Transp. Co., 644 F.2d 1152, 1154 (5th Cir. 1981) (relying on “more\nrestrictive language limiting arbitration” in declining to compel arbitration).\nFor example, the parties may limit arbitration to either interpretation-related\ndisputes or performance-based disputes at the exclusion of other categories of\ndisputes. Negrin v. Kalina, No. 09-Civ-6234, 2010 WL 2816809, at *5 (S.D.N.Y.\nJuly 15, 2010) (“The parties’ use of precise language in the arbitration clause\nsuggests an intent to limit arbitration to a particular subset of disputes.”); see\nalso Taylor v. Inv’rs Assocs., Inc., 29 F.3d 211, 215 (5th Cir. 1994) (applying\nexpressio unius est exclusio alterius to limit the arbitration clause’s application\nto a subset of parties).\n We have previously observed that if an arbitration clause “restricts [the\narbitrator’s] power to an interpretation of the contract, it leaves the arbitrator\npowerless to decide matters on which the agreement is silent.” United\nOffshore, 899 F.3d at 410. In Beckham v. William Bayley Co., a contract for\ndelivery of “standard” insect screens required arbitration of “[a]ny\ndisagreement . . . as to the intent of [the] contract”—i.e., interpretation of the\ncontract. 655 F. Supp. 288, 291 (N.D. Tex. 1987). “Had the parties disputed\n 7\n\f Case: 17-50852 Document: 00514875536 Page: 8 Date Filed: 03/15/2019\n\n\n\n No. 17-50852\nwhether the screens, as delivered, were in fact ‘standard’ screens, the\narbitration clause would have required that the intent as to the meaning of the\nterm ‘standard’ be resolved by arbitration.” Id. But the parties agreed on what\n“standard” insect screens meant, and the dispute was simply over whether the\ndelivered insect screens were damaged. Id. Because such a dispute concerned\nperformance, the court held that the dispute fell outside the scope of the\narbitration clause. Id.\n The opposite is also true: If the arbitration clause limits arbitration to\nperformance-related disputes, then the arbitrator cannot decide other matters,\nsuch as interpretative disputes. Cf. Negrin, 2010 WL 2816809, at *6 (holding\nthat “[t]he arbitration clause cover[ing] disputes relating to ‘non-\nperformance’ ” did not apply when there was no allegation that “[d]efendants\nfailed to discharge . . . any obligation under the [contract]”). The Seventh\nCircuit has illustrated this distinction:\n We can imagine a case in which both parties agree that for example\n some form of notice is a condition precedent to performance, and\n the only dispute is over whether the notice was given. That\n dispute would be arbitrable if the arbitration clause included\n performance disputes, not if it did not.\n\nSelcke v. New England Ins. Co., 995 F.2d 688, 690 (7th Cir. 1993). Thus, the\nparties may decide what disputes they wish to submit to an arbitrator. If they\nlimit arbitration to a specific category of disputes, at the exclusion of other\ncategories of disputes, then the arbitrator’s power is limited to those disputes\nto which the parties expressly consented. See First Options, 514 U.S. at 943.\n Here, Papalote and LCRA agreed to submit to binding arbitration “[i]f\nany dispute arises with respect to either Party’s performance.” This clause\nclearly signifies the parties’ intent to limit arbitration to performance-related\ndisputes only, and the arbitration clause neither requires nor authorizes\n\n\n 8\n\f Case: 17-50852 Document: 00514875536 Page: 9 Date Filed: 03/15/2019\n\n\n\n No. 17-50852\narbitration of disputes that are not performance-related disputes, such as\ndisputes related to the interpretation of the Agreement.\n B.\n Because the Agreement limits arbitration to “any dispute [that] arises\nwith respect to either Party’s performance,” LCRA’s dispute—whether the\nAgreement limits LCRA’s liability to $60 million—is arbitrable only if it\nconstitutes a dispute with respect to either LCRA’s or Papalote’s performance.\nWe hold that LCRA’s dispute is a dispute related to the interpretation of the\nAgreement, not a performance-related dispute, and thus does not fall within\nthe scope of the Agreement’s arbitration clause.\n Interpretative disputes arise when the parties disagree over a text’s\nmeaning. See Interpretation, Black’s Law Dictionary (10th ed. 2014) (“The\nascertainment of a text’s meaning[.]”). Here, LCRA’s own demand letter to\nPapalote frames LCRA’s dispute as an interpretative dispute: The letter states\nthat “[t]he dispute is whether LCRA’s liability is limited to $60,000,000 under\nthe [Agreement’s § 9.3].” And even LCRA’s brief on appeal observes that this\ndispute is “about the meaning of the [Agreement’s] liability limitation.”\nLCRA’s Br. at 35 (emphasis added).\n As Papalote points out, one needs only to examine the Agreement to\ndetermine what the Agreement says and means, and what LCRA and Papalote\nhad intended while drafting the Agreement. See Selcke, 995 F.2d at 690. The\nissue in this case can be answered without any reference to factual allegations\nof failure to perform. See Negrin, 2010 WL 2816809, at *6. Accordingly,\nLCRA’s dispute is squarely in the realm of interpretation. 1 See also Papalote\n\n\n 1 We are not alone in making this observation. The previous panel of this court has\nmade similar observations—albeit in dictum—that this dispute revolved around\ninterpretation. See Papalote I, 858 F.3d at 924. So did the district court. Although the\ndistrict court ultimately concluded that this interpretative dispute related to performance,\nthus constituting a performance-based dispute—a conclusion that we reject today—it could\n 9\n\f Case: 17-50852 Document: 00514875536 Page: 10 Date Filed: 03/15/2019\n\n\n\n No. 17-50852\nI, 858 F.3d at 924 (noting in dicta that “the underlying claim that LCRA sought\nto arbitrate is effectively one for a declaratory judgment [by an arbitrator] that\nits interpretation of § 9.3 is correct.”). Here, although Papalote and LCRA\ncontractually committed “to have someone—other than a judge—decide”\nperformance-related disputes, they did not agree to have an arbitrator decide\nmatters of contract interpretation. In re M.W.M., Jr., 523 S.W.3d 203, 207\n(Tex. App.—Dallas 2017).\n In resisting this conclusion, LCRA heavily relies on the phrase “with\nrespect to,” which, it contends, means “relating to.” LCRA argues that, because\nthe interpretative dispute “relat[es] to LCRA’s ongoing and future performance\nunder the [Agreement],” the interpretative dispute is a dispute “with respect\nto” performance. However, § 9.3 is a damages provision, not a provision about\nperformance, and LCRA’s interpretative dispute is with respect to damages,\nnot performance. Therefore, even if we agree with LCRA’s broad reading of\nthe phrase “with respect to,” LCRA cannot prevail. Because LCRA’s\ninterpretative dispute is outside the scope of the arbitration clause, the district\ncourt erred in compelling Papalote to arbitrate.\n III.\n For the foregoing reasons, we REVERSE the district court’s order\ncompelling arbitration and REMAND for further proceedings consistent with\nthis opinion.\n\n\n\n\nnot avoid observing that LCRA’s dispute “concerns the proper interpretation of a clause in\nthe [Agreement].” Thus, even though LCRA may contend that it has raised a performance-\nrelated dispute, those who have examined its dispute have unavoidably characterized this as\nan interpretative one. See Tidelands Marine Serv. v. Patterson, 719 F.2d 126, 128 n.3 (5th\nCir. 1983) (“That which looks like a duck, walks like a duck, and quacks like a duck will be\ntreated as a duck even though some would insist upon calling it a chicken.”).\n 10\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: PAPALOTE CREEK II, L.L.C., Formerly Known as Papalote Creek Windfarm II, L.L.C., Plaintiff-Appellant, v. LOWER COLORADO RIVER AUTHORITY, Defendant-Appellee.\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-15\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 17-50852 Document: 00514875536 Page: 1 Date Filed: 03/15/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n March 15, 2019\\n No. 17-50852 Lyle W. Cayce\\n Clerk\\n\\nPAPALOTE CREEK II, L.L.C., formerly known as Papalote Creek Windfarm\\nII, L.L.C.,\\n\\n Plaintiff–Appellant,\\n\\nv.\\n\\nLOWER COLORADO RIVER AUTHORITY,\\n\\n Defendant–Appellee.\\n\\n\\n\\n\\n Appeal from the United States District Court\\n for the Western District of Texas\\n\\n\\nBefore HIGGINBOTHAM, ELROD, and HO, Circuit Judges.\\nJENNIFER WALKER ELROD, Circuit Judge:\\n Papalote Creek II, LLC (Papalote) appeals the district court’s order\\ncompelling Papalote to arbitrate a dispute raised by Lower Colorado River\\nAuthority (LCRA)—whether their contractual agreement limits LCRA’s\\nliability to $60 million. The arbitration clause requires Papalote and LCRA to\\narbitrate “any dispute [that] arises with respect to either [p]arty’s\\nperformance.” Because the dispute that LCRA has raised is an interpretative\\ndispute—not a performance dispute—we reverse and remand.\\n\\f Case: 17-50852 Document: 00514875536 Page: 2 Date Filed: 03/15/2019\\n\\n\\n\\n No. 17-50852\\n I.\\n This is the second time Papalote and LCRA have appeared before us. See\\nLower Colo. River Auth. v. Papalote Creek II, LLC, 858 F.3d 916 (5th Cir. 2017)\\n(Papalote I). In the previous appeal, we vacated the district court’s order\\ncompelling arbitration on ripeness grounds without addressing whether\\nLCRA’s dispute is arbitrable. Id. at 918. This case has returned to us with\\nsubsequent procedural development after the remand. We summarized the\\nrelevant facts in Papalote I:\\n In December 2009, LCRA entered into a Power Purchase\\n Agreement [(Agreement)] with [Papalote]. Papalote planned to\\n build an 87-turbine wind farm in Texas . . . , and under the\\n [Agreement], LCRA agreed to purchase all of the energy . . . at a\\n fixed price for an 18-year term.\\n\\n Relevant to this appeal are four sections of the [Agreement]: § 4.3,\\n § 9.3, § 13.1, and § 13.2. First, § 4.3, which is entitled “Liquidated\\n Damages Due to [LCRA's] Failure to Take,” provides a formula for\\n how to calculate the liquidated damages that LCRA would owe to\\n Papalote in the event that LCRA failed to take all of the Project's\\n energy. As noted above, LCRA is required to take all of the energy\\n generated by the Project. However, should LCRA fail to do so, § 4.3\\n details how to calculate Papalote's “exclusive remedy” of liquidated\\n damages. This liquidated damages calculation would depend in\\n part on the difference between the [Agreement’s] fixed price and\\n the price that Papalote is otherwise able to obtain in selling the\\n energy.\\n\\n Second, § 9.3, which is entitled “Limitation on Damages for Certain\\n Types of Failures,” provides the following: [Papalote's] aggregate\\n liability for [its failure to construct and operate the wind farm by\\n the agreed-upon date] shall be limited in the aggregate to sixty\\n million dollars ($60,000,000). [LCRA's] damages for failure to\\n perform its material obligations under [the Agreement] shall\\n likewise be limited in the aggregate to sixty million dollars\\n ($60,000,000). . . .\\n\\n Finally, § 13.1 and § 13.2 provide a two-step arbitration procedure.\\n The first step, as dictated in § 13.1, requires, inter alia, that “[i]f\\n 2\\n\\fCase: 17-50852 Document: 00514875536 Page: 3 Date Filed: 03/15/2019\\n\\n\\n\\n No. 17-50852\\n any dispute arises with respect to either Party's performance\\n hereunder,” the senior officers of LCRA and Papalote meet in an\\n attempt to resolve the dispute. Under the second step, as outlined\\n in § 13.2, if the dispute is not resolved through the first step within\\n a certain timeframe, either party may submit that dispute “to\\n binding arbitration[.]” . . .\\n\\n Papalote completed construction of the Project in 2010, and in the\\n ensuing years, LCRA complied with its obligations under the\\n [Agreement] by purchasing all of the energy generated by the\\n Project. In April 2015, however, LCRA initiated discussions with\\n Papalote regarding the [Agreement]. . . . [I]n June 2015, LCRA\\n sent Papalote a letter stating that, pursuant to § 13.2, LCRA was\\n “initiat[ing] the arbitration process to resolve the dispute between\\n LCRA and Papalote regarding LCRA's limitation of liability under\\n the [Agreement] and its impact on LCRA's performance\\n obligations.” LCRA also noted that it “intends to continue to fully\\n perform its obligations under the [Agreement] during this\\n arbitration process.” . . . Papalote rejected LCRA’s request to\\n proceed to arbitration, reasoning that “[a]n academic question\\n about the damages LCRA might owe for a hypothetical breach\\n simply does not constitute a ‘dispute’ that is proper for arbitration\\n under the [Agreement].” Papalote also argued that a dispute over\\n LCRA’s potential liability limitation was not covered by the\\n arbitration provision in the PPA, which was limited to disputes\\n regarding performance obligations.\\n\\n Following Papalote’s refusal to arbitrate, LCRA filed a petition to\\n compel arbitration in Texas state court on June 30, 2015. Papalote\\n timely removed the petition to federal district court on the basis of\\n diversity jurisdiction. . . . In February 2016, the district court\\n granted LCRA's petition to compel arbitration. . . . [T]he district\\n court framed the question as “whether the dispute LCRA seeks to\\n arbitrate—whether or not LCRA's liability would be capped at $60\\n million in the event it elected to purchase from Papalote less than\\n the total amount of energy it contracted to buy—qualifies as a\\n dispute ‘with respect to either Party's performance’ under the\\n [Agreement].” In answering that question, the district court\\n recognized that, “in a certain sense, one could understand\\n ‘performance’ to concern only those promises which were the\\n essence of the [Agreement]—the sale and production of wind\\n energy—and conceptualize the buyer’s obligation to pay for failing\\n 3\\n\\f Case: 17-50852 Document: 00514875536 Page: 4 Date Filed: 03/15/2019\\n\\n\\n\\n No. 17-50852\\n to take as compensation for its failure to perform, rather than as\\n an independent performance obligation.” The district court\\n reasoned, however, that ‘the better view here . . . is that LCRA’s\\n bargained-for-obligation to pay Papalote a specified sum if LCRA\\n takes less than all of the energy produced is itself a performance\\n obligation under the [Agreement].”\\n\\nId. at 919–20.\\n Although Papalote appealed the order compelling arbitration, the\\ndistrict court denied a stay of arbitration pending appeal. Id. at 921 n.2.\\nPapalote, however, did not appeal the denial of a stay pending appeal; instead,\\non June 1, 2016, Papalote and LCRA submitted to us a “Joint Motion to Abate\\nAppeal Without Prejudice to Automatic Reinstatement” to allow the parties to\\nfully arbitrate. After we stayed the appeal, the parties arbitrated their\\ndispute, and on June 28, 2016, the arbitrator issued a decision in LCRA’s favor,\\nstating that § 9.3 of the Agreement limits LCRA’s liability to $60 million. After\\nthe arbitrator’s adverse decision, Papalote moved to reinstate the appeal,\\nwhich we granted. In addition to seeking the reinstatement of the appeal,\\nPapalote also initiated a separate suit in the district court by filing a motion to\\nvacate the arbitration award. The district court stayed the proceedings for\\nPapalote’s motion to vacate the arbitration award pending the appeal of the\\ninitial order compelling arbitration. While the appeal was pending, “[o]n\\nOctober 10, 2016, LCRA notified Papalote that it would cease taking energy\\nunder the [Agreement] beginning on October 12, 2016, and that its resulting\\nliquidated damages would be capped at $60 million per § 9.3.” Id.\\n In the previous appeal, Papalote argued that LCRA’s dispute: (1) was\\nnot ripe when the district court compelled arbitration; and (2) was outside the\\nscope of the arbitration clause. We agreed with Papalote that the dispute was\\nnot ripe because LCRA was still taking energy from Papalote when the district\\ncourt compelled arbitration. Id. at 927. In holding so, we concluded that\\n\\n 4\\n\\f Case: 17-50852 Document: 00514875536 Page: 5 Date Filed: 03/15/2019\\n\\n\\n\\n No. 17-50852\\nLCRA’s subsequent decision to cease taking energy after the district court\\ncompelled arbitration could not “retroactively cure the void order compelling\\nPapalote to an arbitration that it should not have been forced to attend at the\\ntime.” Id. Accordingly, we vacated the order compelling arbitration and\\nremanded without addressing the arbitrability issue. Id. n.6.\\n On remand, the district court dismissed LCRA’s initial suit concerning\\nits petition to compel arbitration. In Papalote’s separate suit to vacate the\\narbitration award, the district court lifted the stay, and LCRA filed a cross-\\nmotion to affirm the arbitration award and, alternatively, to compel another\\narbitration. Consistent with this court’s judgment in Papalote I, the district\\ncourt vacated the arbitration award as it was the fruit of an order that the\\ndistrict court had entered without subject matter jurisdiction. However,\\nholding that the dispute was now ripe and again concluding that the dispute\\nfell within the scope of the arbitration clause, the district court once again\\ncompelled arbitration. Papalote appeals, contending that LCRA’s dispute is\\noutside of the scope of the arbitration clause.\\n II.\\n A.\\n We review de novo whether the district court properly compelled\\narbitration. Hays v. HCA Holdings, Inc., 838 F.3d 605, 608 (5th Cir. 2016).\\nWe begin with “the proper framework for deciding when disputes are\\narbitrable.” Granite Rock Co. v. Int’l Bhd. of Teamsters, 561 U.S. 287, 297\\n(2010). “Under that framework, a court may order arbitration of a particular\\ndispute only where the court is satisfied that the parties agreed to arbitrate\\nthat dispute.” Id.; see also id. at 304 n.11 (“The test for arbitrability remains\\nwhether the parties consented to arbitrate the dispute in question.”). This\\nframework “involves two questions: ‘(1) whether there is a valid agreement to\\narbitrate between the parties; and (2) whether the dispute in question falls\\n 5\\n\\f Case: 17-50852 Document: 00514875536 Page: 6 Date Filed: 03/15/2019\\n\\n\\n\\n No. 17-50852\\nwithin the scope of that arbitration agreement.’ ” Gross v. GGNSC Southaven,\\nLLC, 817 F.3d 169, 176 (5th Cir. 2016) (quoting Tittle v. Enron Corp., 463 F.3d\\n410, 418 (5th Cir. 2006)). Because neither Papalote nor LCRA disputes the\\nvalidity of the Agreement’s arbitration clause, this appeal concerns only\\nwhether LCRA’s dispute falls within the scope of that arbitration clause.\\n Determining the scope of an arbitration clause is a matter of contract.\\nHebbronville Lone Star Rentals, LLC v. Sunbelt Rentals Indus. Servs., LLC,\\n898 F.3d 629, 632 (5th Cir. 2018); see also First Options of Chi., Inc. v. Kaplan,\\n514 U.S. 938, 943 (1995) (observing that arbitration is “simply a matter of\\ncontract” and “a way to resolve those disputes—but only those disputes—that\\nthe parties have agreed to submit to arbitration”). Under Texas law, the\\nprimary object of contract interpretation “is to ascertain and give effect to the\\nintent of the parties as that intent is expressed in the contract.” Seagull\\nEnergy E & P, Inc. v. Eland Energy, Inc., 207 S.W.3d 342, 345 (Tex. 2006).\\nAlthough both federal law and Texas law create a presumption in favor of\\narbitrability, “unambiguous language controls when the question is the scope\\nof an arbitrator’s power,” and the “policy that favors resolving doubts in favor\\nof arbitration ‘cannot serve to stretch a contractual clause beyond the scope\\nintended by the parties.’ ” Hebbronville Lone Star Rentals, 898 F.3d at 632–33\\n(quoting Smith v. Transp. Workers Union of Am., AFL-CIO Air Transp. Local\\n556, 374 F.3d 372, 375 (5th Cir. 2004)); see also G.T. Leach Builders, LLC v.\\nSapphire V.P., L.P., 458 S.W.3d 502, 521 (Tex. 2015) (discussing presumption\\nof arbitrability under Texas law).\\n The parties may agree upon a broad language in the arbitration clause\\neither by incorporating “[t]he standard broad arbitration provision\\nrecommended by the American Arbitration Association” or by creating their\\nown broad provision. United Offshore Co. v. So. Deepwater Pipeline Co., 899\\nF.2d 405, 409 (5th Cir. 1990). These standard arbitration provisions typically\\n 6\\n\\f Case: 17-50852 Document: 00514875536 Page: 7 Date Filed: 03/15/2019\\n\\n\\n\\n No. 17-50852\\nrequire arbitration of “[a]ny controversy or claim arising out of or relating to\\n[the] contract” or “any dispute . . . with respect to the interpretation or\\nperformance.” Id. at 409–10 (emphasis added) (quoting Mar-Len of La., Inc. v.\\nParsons-Gilbane, 773 F.2d 633, 634 (5th Cir. 1985)). “[W]hen parties choose\\nsuch broad language, only . . . ‘the most forceful evidence of a purpose to\\nexclude the claim from arbitration’ would render the dispute non-arbitrable.”\\nId. (quoting Mar-Len, 773 F.2d at 636).\\n Alternatively, the parties may agree upon a narrow language in the\\narbitration clause by deviating from the broad standard provisions and by\\nlimiting arbitration only to a subset of disputes that may arise out of the\\ncontract. See United Offshore, 374 F.3d at 410; see also Texaco, Inc. v. Am.\\nTrading Transp. Co., 644 F.2d 1152, 1154 (5th Cir. 1981) (relying on “more\\nrestrictive language limiting arbitration” in declining to compel arbitration).\\nFor example, the parties may limit arbitration to either interpretation-related\\ndisputes or performance-based disputes at the exclusion of other categories of\\ndisputes. Negrin v. Kalina, No. 09-Civ-6234, 2010 WL 2816809, at *5 (S.D.N.Y.\\nJuly 15, 2010) (“The parties’ use of precise language in the arbitration clause\\nsuggests an intent to limit arbitration to a particular subset of disputes.”); see\\nalso Taylor v. Inv’rs Assocs., Inc., 29 F.3d 211, 215 (5th Cir. 1994) (applying\\nexpressio unius est exclusio alterius to limit the arbitration clause’s application\\nto a subset of parties).\\n We have previously observed that if an arbitration clause “restricts [the\\narbitrator’s] power to an interpretation of the contract, it leaves the arbitrator\\npowerless to decide matters on which the agreement is silent.” United\\nOffshore, 899 F.3d at 410. In Beckham v. William Bayley Co., a contract for\\ndelivery of “standard” insect screens required arbitration of “[a]ny\\ndisagreement . . . as to the intent of [the] contract”—i.e., interpretation of the\\ncontract. 655 F. Supp. 288, 291 (N.D. Tex. 1987). “Had the parties disputed\\n 7\\n\\f Case: 17-50852 Document: 00514875536 Page: 8 Date Filed: 03/15/2019\\n\\n\\n\\n No. 17-50852\\nwhether the screens, as delivered, were in fact ‘standard’ screens, the\\narbitration clause would have required that the intent as to the meaning of the\\nterm ‘standard’ be resolved by arbitration.” Id. But the parties agreed on what\\n“standard” insect screens meant, and the dispute was simply over whether the\\ndelivered insect screens were damaged. Id. Because such a dispute concerned\\nperformance, the court held that the dispute fell outside the scope of the\\narbitration clause. Id.\\n The opposite is also true: If the arbitration clause limits arbitration to\\nperformance-related disputes, then the arbitrator cannot decide other matters,\\nsuch as interpretative disputes. Cf. Negrin, 2010 WL 2816809, at *6 (holding\\nthat “[t]he arbitration clause cover[ing] disputes relating to ‘non-\\nperformance’ ” did not apply when there was no allegation that “[d]efendants\\nfailed to discharge . . . any obligation under the [contract]”). The Seventh\\nCircuit has illustrated this distinction:\\n We can imagine a case in which both parties agree that for example\\n some form of notice is a condition precedent to performance, and\\n the only dispute is over whether the notice was given. That\\n dispute would be arbitrable if the arbitration clause included\\n performance disputes, not if it did not.\\n\\nSelcke v. New England Ins. Co., 995 F.2d 688, 690 (7th Cir. 1993). Thus, the\\nparties may decide what disputes they wish to submit to an arbitrator. If they\\nlimit arbitration to a specific category of disputes, at the exclusion of other\\ncategories of disputes, then the arbitrator’s power is limited to those disputes\\nto which the parties expressly consented. See First Options, 514 U.S. at 943.\\n Here, Papalote and LCRA agreed to submit to binding arbitration “[i]f\\nany dispute arises with respect to either Party’s performance.” This clause\\nclearly signifies the parties’ intent to limit arbitration to performance-related\\ndisputes only, and the arbitration clause neither requires nor authorizes\\n\\n\\n 8\\n\\f Case: 17-50852 Document: 00514875536 Page: 9 Date Filed: 03/15/2019\\n\\n\\n\\n No. 17-50852\\narbitration of disputes that are not performance-related disputes, such as\\ndisputes related to the interpretation of the Agreement.\\n B.\\n Because the Agreement limits arbitration to “any dispute [that] arises\\nwith respect to either Party’s performance,” LCRA’s dispute—whether the\\nAgreement limits LCRA’s liability to $60 million—is arbitrable only if it\\nconstitutes a dispute with respect to either LCRA’s or Papalote’s performance.\\nWe hold that LCRA’s dispute is a dispute related to the interpretation of the\\nAgreement, not a performance-related dispute, and thus does not fall within\\nthe scope of the Agreement’s arbitration clause.\\n Interpretative disputes arise when the parties disagree over a text’s\\nmeaning. See Interpretation, Black’s Law Dictionary (10th ed. 2014) (“The\\nascertainment of a text’s meaning[.]”). Here, LCRA’s own demand letter to\\nPapalote frames LCRA’s dispute as an interpretative dispute: The letter states\\nthat “[t]he dispute is whether LCRA’s liability is limited to $60,000,000 under\\nthe [Agreement’s § 9.3].” And even LCRA’s brief on appeal observes that this\\ndispute is “about the meaning of the [Agreement’s] liability limitation.”\\nLCRA’s Br. at 35 (emphasis added).\\n As Papalote points out, one needs only to examine the Agreement to\\ndetermine what the Agreement says and means, and what LCRA and Papalote\\nhad intended while drafting the Agreement. See Selcke, 995 F.2d at 690. The\\nissue in this case can be answered without any reference to factual allegations\\nof failure to perform. See Negrin, 2010 WL 2816809, at *6. Accordingly,\\nLCRA’s dispute is squarely in the realm of interpretation. 1 See also Papalote\\n\\n\\n 1 We are not alone in making this observation. The previous panel of this court has\\nmade similar observations—albeit in dictum—that this dispute revolved around\\ninterpretation. See Papalote I, 858 F.3d at 924. So did the district court. Although the\\ndistrict court ultimately concluded that this interpretative dispute related to performance,\\nthus constituting a performance-based dispute—a conclusion that we reject today—it could\\n 9\\n\\f Case: 17-50852 Document: 00514875536 Page: 10 Date Filed: 03/15/2019\\n\\n\\n\\n No. 17-50852\\nI, 858 F.3d at 924 (noting in dicta that “the underlying claim that LCRA sought\\nto arbitrate is effectively one for a declaratory judgment [by an arbitrator] that\\nits interpretation of § 9.3 is correct.”). Here, although Papalote and LCRA\\ncontractually committed “to have someone—other than a judge—decide”\\nperformance-related disputes, they did not agree to have an arbitrator decide\\nmatters of contract interpretation. In re M.W.M., Jr., 523 S.W.3d 203, 207\\n(Tex. App.—Dallas 2017).\\n In resisting this conclusion, LCRA heavily relies on the phrase “with\\nrespect to,” which, it contends, means “relating to.” LCRA argues that, because\\nthe interpretative dispute “relat[es] to LCRA’s ongoing and future performance\\nunder the [Agreement],” the interpretative dispute is a dispute “with respect\\nto” performance. However, § 9.3 is a damages provision, not a provision about\\nperformance, and LCRA’s interpretative dispute is with respect to damages,\\nnot performance. Therefore, even if we agree with LCRA’s broad reading of\\nthe phrase “with respect to,” LCRA cannot prevail. Because LCRA’s\\ninterpretative dispute is outside the scope of the arbitration clause, the district\\ncourt erred in compelling Papalote to arbitrate.\\n III.\\n For the foregoing reasons, we REVERSE the district court’s order\\ncompelling arbitration and REMAND for further proceedings consistent with\\nthis opinion.\\n\\n\\n\\n\\nnot avoid observing that LCRA’s dispute “concerns the proper interpretation of a clause in\\nthe [Agreement].” Thus, even though LCRA may contend that it has raised a performance-\\nrelated dispute, those who have examined its dispute have unavoidably characterized this as\\nan interpretative one. See Tidelands Marine Serv. v. Patterson, 719 F.2d 126, 128 n.3 (5th\\nCir. 1983) (“That which looks like a duck, walks like a duck, and quacks like a duck will be\\ntreated as a duck even though some would insist upon calling it a chicken.”).\\n 10\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1090,"cells":{"id":{"kind":"number","value":4601588,"string":"4,601,588"},"name":{"kind":"string","value":"BP EXPLORATION & PRODUCTION, INCORPORATED; BP America Production Company; BP, P.L.C., Requesting Parties-Appellants, v. CLAIMANT ID 100217946, Objecting Party-Appellee."},"name_abbreviation":{"kind":"string","value":"BP Exploration & Prodn, Inc. v. ID"},"decision_date":{"kind":"string","value":"2019-03-18"},"docket_number":{"kind":"string","value":"18-30147"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before WIENER, DENNIS, and OWEN, Circuit Judges.\", \"parties\": \"\", \"opinions\": [{\"author\": \"PER CURIAM\", \"type\": \"010combined\", \"text\": \"IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n March 18, 2019\\n No. 18-30147\\n Lyle W. Cayce\\n Clerk\\nBP EXPLORATION & PRODUCTION, INCORPORATED; BP AMERICA\\nPRODUCTION COMPANY; BP, P.L.C.,\\n\\n Requesting Parties–Appellants,\\n\\nv.\\n\\nCLAIMANT ID 100217946,\\n\\n Objecting Party–Appellee.\\n\\n\\n\\n\\n Appeal from the United States District Court\\n for the Eastern District of Louisiana\\n\\n\\nBefore WIENER, DENNIS, and OWEN, Circuit Judges.\\nPER CURIAM:\\n This is an appeal from an award to Claimant ID 100217946 (Claimant)\\nunder the Settlement Program established following the Deepwater Horizon oil\\nspill. The Claims Administrator concluded that the non-profit Claimant is\\nentitled to compensation of nearly $15 million. An Appeal Panel within the\\nSettlement Program affirmed, and the district court denied discretionary\\nreview. BP appeals, arguing that two donations were improperly counted by\\nthe Claims Administrator and the district court was required to review the\\naward. We affirm the district court’s judgment.\\n\\f No. 18-30147\\n I\\n In April 2010, an explosion on the Deepwater Horizon, a mobile offshore\\ndrilling unit leased by BP Exploration & Production, Inc., BP America\\nProduction Company, and BP, P.L.C. (collectively, BP), caused the discharge\\nof millions of gallons of oil into the Gulf of Mexico. 1 Two years later, BP entered\\ninto the “Deepwater Horizon Economic and Property Damages Settlement\\nAgreement” with a class of individuals and entities allegedly injured by the\\nDeepwater Horizon oil spill. The Settlement Agreement created the Settlement\\nProgram under which claims for settlement benefits are reviewed by the\\nClaims Administrator, whose decisions may be appealed to an Appeal Panel.\\n Businesses seeking settlement benefits as compensation for economic\\nlosses “must establish that their loss was due to or resulting from the\\nDeepwater Horizon Incident” by meeting the applicable “causation\\nrequirement[].” The Settlement Agreement imposes different causation\\nrequirements on businesses located in different geographic “zones.”\\nBusinesses located in Zone A are not required to establish causation unless\\nthey fall into one of the agreed-upon exceptions. Claimant is located in Zone A\\nand is not one of the agreed-upon exceptions, so it was not required to establish\\ncausation.\\n Once causation is established or inferred, claimants must prove an\\neconomic loss using the methodology in Exhibit 4C. Under Step 1 of the\\nformula, claimants compare their Variable Profit in the Compensation\\nPeriod—a consecutive three-month period between May and December 2010—\\nto their Variable Profit during a Benchmark Period of the claimant’s choosing.\\nThe Variable Profit is calculated by considering the total monthly revenue over\\n\\n\\n\\n 1 Ctr. for Biological Diversity, Inc. v. BP Am. Prod. Co., 704 F.3d 413, 418 (5th Cir.\\n2013).\\n 2\\n\\f No. 18-30147\\nthe period and subtracting the corresponding variable expenses over the same\\ntime period, including “Variable Costs,” variable portions of salaries, and other\\nexpenses. If the Claimant has less Variable Profit in the Compensation Period\\nthan in the Benchmark period, it is entitled to compensation for that\\ndifference. Under Step 2 of the compensation formula, claimants are also\\ncompensated for incremental profits the claimant might have expected to\\ngenerate in 2010 in the absence of the spill, based on the claimant’s revenue\\ntrend before the spill. Claimants may also be entitled to a Risk Transfer\\nPremium (RTP) depending on where the business is located. The amount of\\nthe risk transfer premium is based on the total Step 1 and Step 2\\nCompensation multiplied by a variable found in Exhibit 15 of the Settlement\\nAgreement, the RTP Chart.\\n Claimant is a non-profit organization that solicits donations for its own\\nprogramming and distributes grants to other non-profit organizations.\\nClaimant submitted a Business Economic Loss (BEL) Claim to the Settlement\\nProgram. The Claims Administrator determined that Claimant was eligible\\nfor $5,814,307.79 at Step 1 Compensation by comparing its Variable Profit in\\nAugust through October 2010 with the same period in 2009. The Claims\\nAdministrator then determined that Claimant was entitled to an RTP of 1.5\\ntimes the amount of its losses, which was $8,721,461.69. In addition, the\\nClaims Administrator awarded $7,062.50 of Claimant Accounting support as\\nreimbursement for expenses that Claimant incurred in the claims process. All\\ntold, the Claims Administrator awarded $14,542,831.98 to Claimant.\\n BP appealed the award to a three-member Appeal Panel. It argued that\\ntwo large donations received by Claimant totaling $8.9 million were\\nimproperly included in the economic loss calculation, which resulted in an\\nexcessive award. The first donation was an unsecured non-negotiable\\npromissory note for $5,913,491.66 to be paid in eight equal annual installments\\n 3\\n\\f No. 18-30147\\nbeginning June 30, 2010, with interest accruing on the unpaid balance. The\\nother donation at issue was a $3,000,000 pledge to be paid over ten years in\\nannual installments of $300,000, with a check for the first $300,000 attached\\nto the pledge. BP argued there were four issues with the inclusion of these\\ndonations in the economic loss calculation: (1) The donations were not\\n“revenue,” (2) even if the payments were revenue, Claimant could only treat\\nthose payments that were actually received in 2009 as revenue for 2009, (3) if\\nthe entire $8.9 million could be properly treated as revenue, the Settlement\\nProgram failed to match the donations with corresponding distributions that\\nClaimant granted to other non-profits that should be treated as expenses, and\\n(4) awards made to entities that maintained funds with Claimant should offset\\nClaimant’s award to avoid impermissible double recovery.\\n BP requested that an en banc Appeal Panel review the award to\\n“promote and maintain uniformity and consistency of the Appeal Panel\\ndecisions,” contending that an Appeal Panel in another case involving a non-\\nprofit had ruled differently than the Claims Administrator. The Appeal Panel\\ninitially indicated that it would consider the appeal en banc. Before rendering\\na decision, the Appeal Panel decided not to address the issue en banc. An\\nAppeal Panel then reviewed the decision de novo and rejected each of BP’s\\narguments.\\n BP then requested discretionary review in the district court. BP\\nrepeated its arguments with one exception. It did not argue that the award\\nshould be offset by awards to other non-profits to whom it had made grants to\\nprevent double recovery. The district court denied discretionary review. BP\\nappeals the denial of discretionary review.\\n\\n\\n\\n\\n 4\\n\\f No. 18-30147\\n II\\n We review the district court’s denial of discretionary review for abuse of\\ndiscretion. 2 It is generally an abuse of discretion not to review a decision that\\n“actually contradicted or misapplied the Settlement Agreement, or had the\\nclear potential to” do so. 3 However, we have been careful to note that it is\\n“wrong to suggest that the district court must grant review of all claims that\\nraise a question about the proper interpretation of the Settlement\\nAgreement.” 4 It is not an abuse of discretion to deny a request for review that\\n“involve[s] no pressing question of how the Settlement Agreement should be\\ninterpreted or implemented, but simply raise[s] the correctness of a\\ndiscretionary administrative decision in the facts of a single claimant's case.” 5\\nIt may also be an abuse of discretion to deny a request for review that raises a\\nrecurring issue on which the Appeal Panels are split if “the resolution of the\\nquestion will substantially impact the administration of the Agreement.” 6\\n BP argues that the district court abused its discretion by failing (1) to\\nresolve a recurring issue on which the Appeal Panels are split, and (2) to review\\nan Appeal Panel’s decision that contradicts the Settlement Agreement. We\\naddress each argument.\\n A\\n BP argues that the treatment of grant-making entities like Claimant is\\n“a recurring and important issue in administering the Settlement\\n\\n\\n 2 Claimant ID 100212278 v. BP Expl. & Prod., Inc., 848 F.3d 407, 410 (5th Cir. 2017)\\n(citing Holmes Motors, Inc. v. BP Expl. & Prod., 829 F.3d 313, 315 (5th Cir. 2016)).\\n 3 Id. (quoting Holmes Motors, 829 F.3d at 315) (internal quotations omitted).\\n 4 Id. (quoting Holmes Motors, 829 F.3d at 316) (internal quotations omitted); see also\\n\\nIn re Deepwater Horizon, 785 F.3d 986, 999 (5th Cir. 2015) (“We do not intend any part of\\nthis opinion to turn the district court's discretionary review into a mandatory review. To do\\nso would frustrate the clear purpose of the Settlement Agreement to curtail litigation.”).\\n 5 Claimant ID 100212278, 848 F.3d at 410 (quoting In re Deepwater Horizon, 641 F.\\n\\nApp’x 405, 410 (5th Cir. 2016)) (alterations in original).\\n 6 Id. (quoting In re Deepwater Horizon, 632 F. App’x 199, 203-04 (5th Cir. 2015)).\\n\\n 5\\n\\f No. 18-30147\\n[Agreement].” It reasons that the award is significant because of (1) the\\namount involved, (2) the “unusually lengthy” analysis of the Appeal Panel, (3)\\nthe Panel’s reliance on contested characterization of precedent, (4) Claimant’s\\nadmission that donors play a role in determining how grants are made, and (5)\\nthe threat of double-recovery. BP additionally maintains that there is a “split”\\namong the Appeal Panels.\\n BP points to a decision of an Appeal Panel that excluded from “revenue”\\nfunds received by a non-profit that were immediately distributed to other non-\\nprofit affiliates. In that appeal, the claimant challenged the Claims\\nAdministrator’s decision to exclude a state-grant from revenue because the\\nClaims Administrator found the funds were a “pass-through” grant in which\\nthe state granted money to claimant and claimant distributed an identical\\namount to its affiliates. The Appeal Panel upheld the exclusion.\\n “For [a] ruling to create a conflict with the one now before us, it must\\nhave involved substantially identical claimants relying on substantially\\nidentical documentation.” 7 The one award identified by BP does not show a\\nsplit among the Appeal Panels. In that case, the receipt of funds coupled with\\nan exactly matching distribution in the same month supported the Claims\\nAdministrator’s decision to treat the funds as pass-through and not revenue.\\nHere, BP has not shown that Claimant is engaged in the same type of dollar-\\nfor-dollar distribution. Claimant does not dispute that it grants a large\\npercentage of funds it receives to other entities. However, Claimant contests\\nthe characterization of its funding as merely a pass-through, and the Appeal\\nPanel agreed. The question of what particular percentage of funds that a\\ncharity passes through will give rise to the characterization of the donations\\n\\n\\n\\n 7 Claimant ID 100128765 v. BP Expl. & Prod., Inc., 709 F. App’x 771, 773 (5th Cir.\\n2017) (per curiam).\\n 6\\n\\f No. 18-30147\\nas pass-throughs instead of revenue is a difficult one. But, we cannot say that\\nthe Appeal Panels are split. The Appeal Panel here explicitly rejected BP’s\\nargument that Claimant is primarily a pass-through organization because a\\nlarge part of its donations are passed through and donors are involved in the\\nultimate decision about where donated funds are spent. Rather than reflecting\\na split that must be resolved by the district court, the Appeal Panel’s decision\\nreflects that the Panels are conscious of factual differences that may\\ndistinguish claimants. 8\\n Nor can we agree with BP’s argument that the size of the award requires\\nappellate review. While any multi-million dollar award is “significant” in the\\nordinary sense, the size of the award alone does not make the issue significant\\nenough to require district court review. 9 Further, the “unusually lengthy”\\ndecision of the Appeal Panel is not a reason to doubt the Panel—it is an\\nindication that the Panel thoroughly considered all of BP’s arguments and\\nassessed the documentation provided by Claimant to apply the Settlement\\nAgreement. Finally, BP did not argue to the district court that it should have\\naddressed the specter of double recovery, so BP cannot rely on that argument\\nto show that the district court abused its discretion. 10\\n\\n\\n\\n\\n 8 See Claimant ID 100190818 v. BP Expl. & Prod., Inc., 718 F. App’x 220, 222 (5th Cir.\\n2018); Claimant ID 100051301 v. BP Expl. & Prod., Inc., 694 F. App’x 236, 240 (5th Cir. 2017)\\n(“[T]he fact that Appeal Panels have reached different conclusions for this issue depending\\non the circumstances of each case does not represent the type of Appeal Panel split that would\\nrequire the district court’s review.”).\\n 9 See In re Deepwater Horizon, 785 F.3d 1003, 1021 (5th Cir. 2015) (“Non-Profit\\n\\nDecision”) (“[D]enying this award because of its size would open the floodgates to a flurry of\\nchallenges to nonprofit awards, undermining the aims of the [settlement program].”)\\n 10 In re Deepwater Horizon, 814 F.3d 748, 752 (5th Cir. 2016) (citing Cent. Sw. Tex.\\n\\nDev., L.L.C. v. JPMorgan Chase Bank, Nat’l Ass’n, 780 F.3d 296, 300-01 (5th Cir. 2015))\\n(“Claimants did not make this argument in their memorandum in support of their motion\\nbefore the district court, and it is accordingly forfeited.”).\\n\\n 7\\n\\f No. 18-30147\\n B\\n BP also argues that the district court abused its discretion because the\\naward is contrary to the terms of the Settlement Agreement. BP argues three\\nways in which the award is contrary to “economic reality”: (1) The donations at\\nissue are not “revenue,” (2) if the donations are revenue, the Appeal Panel did\\nnot properly match expenses to revenue in the month earned, and (3) if the\\ndonations are revenue, the entire $8.9 million should not be recorded in 2009.\\n 1\\n BP’s contention that the $8.9 million donations are not “revenue” is\\ncontrary to this court’s Non-Profit Decision. 11 In that case, we were confronted\\nwith the argument that donations and grants to non-profits did not qualify as\\n“revenue” for purposes of Exhibit 4C’s compensation formula. 12 We recognized\\nthat “modern nonprofits are commercial entities that seek to generate cash\\nsurpluses,” and held that revenue includes donations and grants to non-\\nprofits. 13 We also addressed the work that non-profits do to raise funds, and\\nnoted that non-profits must do significant work to solicit donations and grants\\n“to keep their doors open.” 14 We rejected BP’s narrow view of the work that\\nnon-profits perform to “earn their revenue” and upheld the Claims\\nAdministrator’s reading of the Settlement Agreement that non-profit\\ndonations and grants are typically “revenue” under Exhibit 4C. 15\\n While acknowledging our Non-Profit Decision, BP nevertheless argues\\nthat these particular $8.9 million donations are not revenue. It insists that\\nthe donations are not made to Claimant, but that Claimant merely acts as a\\n“‘fiduciary’ for the ultimate beneficiaries.” BP likens Claimant to Western\\n\\n\\n 11 785 F.3d 1003 (5th Cir. 2015).\\n 12 Id. at 1012.\\n 13 Id.\\n 14 Id. at 1013.\\n 15 Id.\\n\\n 8\\n\\f No. 18-30147\\nUnion, arguing that none of the funds belong to Claimant and must be\\ndistributed according to the wishes of the donors. The basis of this argument\\nis that Claimant solicits donations for placement in donor-advised funds,\\nwhere the donor expresses how the donations are to be spent. Despite the fact\\nthat the Internal Revenue Code requires all charitable donations in donor-\\nadvised funds to be exclusively the funds of the non-profit, 16 BP argues that\\nClaimant is ultimately subject to the will of donors and therefore those\\ndonations cannot be considered Claimant’s revenue. The Appeal Panel\\ndisagreed and focused on the aspects of Claimant’s operations that cannot be\\nconsidered pass-through, such as the workshops it conducts, the series of\\nlectures and performances it presents, and the funding of a police perception\\nsurvey which was used in undertaking police reform in Claimant’s community.\\nThe Appeal Panel held that the contested donations were unrestricted\\ndonations made to Claimant, and thus fall squarely within the definition of\\n“revenue” we set forth in Non-Profit Decision. 17\\n BP argues that this factual determination was error and urges us to\\nremand to the district court for evidentiary hearings to determine whether the\\nparticular donations were of donor-advised funds. However, the district court\\ndid not abuse its discretion by deferring to the Claims Administrator’s\\ndiscretionary administrative decision regarding the documentation required to\\nsubstantiate a BEL claim. 18 The Settlement Agreement contemplates that the\\nClaims Administrator will review supporting documentation to process claims.\\nThe district court’s decision to defer to the Claims Administrator’s\\n\\n\\n\\n\\n 16 See 26 U.S.C. § 170(f)(18).\\n 17 785 F.3d 1003 (5th Cir. 2015).\\n 18 See Claimant ID 100212278 v. BP Expl. & Prod., Inc., 848 F.3d 407, 410 (5th Cir.\\n\\n2017) (quoting In re Deepwater Horizon, 641 F. App’x 405, 410 (5th Cir. 2016)) (alterations in\\noriginal).\\n 9\\n\\f No. 18-30147\\nsubstantiation requirements and factual finding that the two donations at\\nissue were unrestricted grants was not an abuse of discretion.\\n 2\\n BP also argues that, even if the donations are revenue, the Claims\\nAdministrator did not properly match the $8.9 million donations with\\nexpenses. In BP’s view, Claimant gave some or all of the donations at issue to\\nother non-profits and those grants should be considered “Variable Expenses”\\nthat must be matched to the month in which the donations were received. The\\nClaims Administrator determined the expenses of the claim were “not\\nsufficiently matched” and applied “Policy 495” to match the expenses. Policy\\n495 was created by the Claims Administrator and approved by the district\\ncourt in response to a decision of this court. 19 We first held in Deepwater\\nHorizon I 20 that the Settlement Agreement should be interpreted “in\\naccordance with economic reality” and remanded for the district court to\\ndetermine whether the agreement required the Claims Administrator to\\n“match” profits and losses. 21 In “matched” profit and loss statements, costs\\nfollow revenue—which is registered when generated or received—and this\\nprovides a clear picture of net income. 22 In “unmatched” profit and loss\\nstatements, revenue is registered when generated or received, and costs are\\nregistered when incurred. 23 We noted that unmatched profit and loss\\nstatements can “make it appear as if a claimant has suffered damages that he,\\n\\n\\n\\n\\n 19 See In Re Deepwater Horizon, 858 F.3d 298, 300-01 (5th Cir. 2017) (“Policy 495\\nDecision”).\\n 20 732 F.3d 326 (5th Cir. 2013) (“Deepwater Horizon I”).\\n 21 Id. at 339.\\n 22 Policy 495 Decision, 858 F.3d at 301.\\n 23 Id.\\n\\n\\n\\n 10\\n\\f No. 18-30147\\nin fact, did not suffer.” 24 Policy 495 was created to address the problem of\\nunmatched revenues. 25\\n This court approved of a portion of Policy 495 in our Policy 495\\nDecision. 26 Policy 495 had five different formulas for matching revenue with\\nexpenses, and we upheld only the Annual Variable Margin Methodology\\n(AVMM). 27 “The AVMM requires the Claims Administrator to match all\\nunmatched profit and loss statements.” 28 We held the other methodologies\\nwere impermissible because they required the Claims Administrator to “move,\\nsmooth, or otherwise reallocate revenue for claimants,” contrary to the express\\nterms of the Settlement Agreement that gives each claimant the right to choose\\nits own Compensation Period. 29 We had assumed that “process[ing] claims in\\naccordance with economic reality” would comport with the text of the\\nSettlement Agreement, but recognized that will not always be true. 30\\nAccordingly, when the text of the Settlement Agreement conflicts with\\neconomic reality, the text controls. 31\\n The Claims Administrator applied the AVMM to Claimant’s claims and\\nmatched the unmatched profit and loss statements. BP is not satisfied with\\nthat methodology in this case because, in its view, real matching would\\ncorrelate any distributions from the $8.9 million donations back to the month\\nin which the donations were generated. It argues, without support, that the\\nClaims Administrator did not undertake the first step of making line-by-line\\ncorrections to a claimant’s records. BP has not identified any errors that\\n\\n\\n\\n 24 Id.\\n 25 Id. at 301-02.\\n 26 Id. at 301.\\n 27 Id. at 300-01.\\n 28 Id. at 302.\\n 29 Id. at 303.\\n 30 See id. at 304 (quoting Deepwater Horizon I, 732 F.3d 326, 339 (5th Cir. 2013)).\\n 31 Id.\\n\\n 11\\n\\f No. 18-30147\\nshould have been corrected, except for its blanket assertion that the $8.9\\nmillion was donated for the express purpose of granting those funds to other\\norganizations.\\n Policy 495 and the AVMM recognize that the Settlement Agreement does\\nnot mandate that BEL claimants keep profit and loss statements under any\\nparticular basis, so the Claims Administrator “will analyze the P&Ls under\\nthe basis . . . of accounting used by the claimant in the normal course of\\nbusiness.” The Claims Administrator analyzed Claimant’s profit and loss\\nstatements under its usual accounting method, found that such statements\\nwere not sufficiently matched, and then applied the AVMM to match them.\\nThe Appeal Panel upheld the application of the AVMM. Claimant maintains\\nthat it properly attributes expenses to the months in which it distributes funds\\nand that the donations to which BP objects were not tied to any planned or\\naccrued distribution. BP’s objection is limited to the individual factual\\ndetermination of a specific claimant, and denying review was not an abuse of\\ndiscretion. 32\\n 3\\n Finally, BP argues that the entire $8.9 million should not be recorded as\\nrevenue in 2009. In BP’s view, because Claimant did not receive the entire\\namount in cash in 2009, Claimant should have recorded its donations in the\\nyears in which it received cash payments. Claimant records the entire value\\nof unconditional promises to give in the year of the pledge, discounted to\\npresent value, in accordance with Generally Accepted Accounting Principles\\n(GAAP), and its auditors approved of this method. BP seeks to reallocate\\n\\n\\n\\n 32See Claimant ID 100236236 v. BP Expl. & Prod., Inc., 699 F. App’x 308, 310-11 (5th\\nCir. 2017) (citing In re Deepwater (Sexton), 641 F. App’x 405, 410 (5th Cir. 2016)); Claimant\\nID 100051301 v. BP Expl. & Prod., Inc., 694 F. App’x 236, 240 (5th Cir. 2017).\\n\\n 12\\n\\f No. 18-30147\\nrevenue to a different time period. We disapproved of such a practice in the\\nPolicy 495 Decision. 33 Requiring the Claims Administrator to take the\\nrevenue, properly allocated under Claimant’s normal accounting procedures\\nthat follow GAAP, and reallocate them to the month in which Claimant\\nreceived the cash payment would deprive “claimant [of] the right to choose his\\nor her Compensation Period.” 34 The Appeal Panel’s decision to apply the\\nClaimant’s usual accounting procedure did not contradict the Settlement\\nAgreement. Accordingly, the district court did not abuse its discretion in\\ndenying review.\\n * * *\\n For the foregoing reasons, we AFFIRM the judgment of the district court.\\n\\n\\n\\n\\n 33 858 F.3d 298, 304 (5th Cir. 2017).\\n 34 Id.\\n 13\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4378841/\", \"author_raw\": \"PER CURIAM\"}]}"},"judge1":{"kind":"string","value":"WIENER"},"judge2":{"kind":"string","value":"DENNIS"},"judge3":{"kind":"string","value":"OWEN"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"WIENER\": \", Circuit\", \"DENNIS\": \", Circuit\", \"OWEN\": \", Circuit\"}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4601588/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: BP EXPLORATION & PRODUCTION, INCORPORATED; BP America Production Company; BP, P.L.C., Requesting Parties-Appellants, v. CLAIMANT ID 100217946, Objecting Party-Appellee.\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-18\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nIN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT United States Court of Appeals\n Fifth Circuit\n\n FILED\n March 18, 2019\n No. 18-30147\n Lyle W. Cayce\n Clerk\nBP EXPLORATION & PRODUCTION, INCORPORATED; BP AMERICA\nPRODUCTION COMPANY; BP, P.L.C.,\n\n Requesting Parties–Appellants,\n\nv.\n\nCLAIMANT ID 100217946,\n\n Objecting Party–Appellee.\n\n\n\n\n Appeal from the United States District Court\n for the Eastern District of Louisiana\n\n\nBefore WIENER, DENNIS, and OWEN, Circuit Judges.\nPER CURIAM:\n This is an appeal from an award to Claimant ID 100217946 (Claimant)\nunder the Settlement Program established following the Deepwater Horizon oil\nspill. The Claims Administrator concluded that the non-profit Claimant is\nentitled to compensation of nearly $15 million. An Appeal Panel within the\nSettlement Program affirmed, and the district court denied discretionary\nreview. BP appeals, arguing that two donations were improperly counted by\nthe Claims Administrator and the district court was required to review the\naward. We affirm the district court’s judgment.\n\f No. 18-30147\n I\n In April 2010, an explosion on the Deepwater Horizon, a mobile offshore\ndrilling unit leased by BP Exploration & Production, Inc., BP America\nProduction Company, and BP, P.L.C. (collectively, BP), caused the discharge\nof millions of gallons of oil into the Gulf of Mexico. 1 Two years later, BP entered\ninto the “Deepwater Horizon Economic and Property Damages Settlement\nAgreement” with a class of individuals and entities allegedly injured by the\nDeepwater Horizon oil spill. The Settlement Agreement created the Settlement\nProgram under which claims for settlement benefits are reviewed by the\nClaims Administrator, whose decisions may be appealed to an Appeal Panel.\n Businesses seeking settlement benefits as compensation for economic\nlosses “must establish that their loss was due to or resulting from the\nDeepwater Horizon Incident” by meeting the applicable “causation\nrequirement[].” The Settlement Agreement imposes different causation\nrequirements on businesses located in different geographic “zones.”\nBusinesses located in Zone A are not required to establish causation unless\nthey fall into one of the agreed-upon exceptions. Claimant is located in Zone A\nand is not one of the agreed-upon exceptions, so it was not required to establish\ncausation.\n Once causation is established or inferred, claimants must prove an\neconomic loss using the methodology in Exhibit 4C. Under Step 1 of the\nformula, claimants compare their Variable Profit in the Compensation\nPeriod—a consecutive three-month period between May and December 2010—\nto their Variable Profit during a Benchmark Period of the claimant’s choosing.\nThe Variable Profit is calculated by considering the total monthly revenue over\n\n\n\n 1 Ctr. for Biological Diversity, Inc. v. BP Am. Prod. Co., 704 F.3d 413, 418 (5th Cir.\n2013).\n 2\n\f No. 18-30147\nthe period and subtracting the corresponding variable expenses over the same\ntime period, including “Variable Costs,” variable portions of salaries, and other\nexpenses. If the Claimant has less Variable Profit in the Compensation Period\nthan in the Benchmark period, it is entitled to compensation for that\ndifference. Under Step 2 of the compensation formula, claimants are also\ncompensated for incremental profits the claimant might have expected to\ngenerate in 2010 in the absence of the spill, based on the claimant’s revenue\ntrend before the spill. Claimants may also be entitled to a Risk Transfer\nPremium (RTP) depending on where the business is located. The amount of\nthe risk transfer premium is based on the total Step 1 and Step 2\nCompensation multiplied by a variable found in Exhibit 15 of the Settlement\nAgreement, the RTP Chart.\n Claimant is a non-profit organization that solicits donations for its own\nprogramming and distributes grants to other non-profit organizations.\nClaimant submitted a Business Economic Loss (BEL) Claim to the Settlement\nProgram. The Claims Administrator determined that Claimant was eligible\nfor $5,814,307.79 at Step 1 Compensation by comparing its Variable Profit in\nAugust through October 2010 with the same period in 2009. The Claims\nAdministrator then determined that Claimant was entitled to an RTP of 1.5\ntimes the amount of its losses, which was $8,721,461.69. In addition, the\nClaims Administrator awarded $7,062.50 of Claimant Accounting support as\nreimbursement for expenses that Claimant incurred in the claims process. All\ntold, the Claims Administrator awarded $14,542,831.98 to Claimant.\n BP appealed the award to a three-member Appeal Panel. It argued that\ntwo large donations received by Claimant totaling $8.9 million were\nimproperly included in the economic loss calculation, which resulted in an\nexcessive award. The first donation was an unsecured non-negotiable\npromissory note for $5,913,491.66 to be paid in eight equal annual installments\n 3\n\f No. 18-30147\nbeginning June 30, 2010, with interest accruing on the unpaid balance. The\nother donation at issue was a $3,000,000 pledge to be paid over ten years in\nannual installments of $300,000, with a check for the first $300,000 attached\nto the pledge. BP argued there were four issues with the inclusion of these\ndonations in the economic loss calculation: (1) The donations were not\n“revenue,” (2) even if the payments were revenue, Claimant could only treat\nthose payments that were actually received in 2009 as revenue for 2009, (3) if\nthe entire $8.9 million could be properly treated as revenue, the Settlement\nProgram failed to match the donations with corresponding distributions that\nClaimant granted to other non-profits that should be treated as expenses, and\n(4) awards made to entities that maintained funds with Claimant should offset\nClaimant’s award to avoid impermissible double recovery.\n BP requested that an en banc Appeal Panel review the award to\n“promote and maintain uniformity and consistency of the Appeal Panel\ndecisions,” contending that an Appeal Panel in another case involving a non-\nprofit had ruled differently than the Claims Administrator. The Appeal Panel\ninitially indicated that it would consider the appeal en banc. Before rendering\na decision, the Appeal Panel decided not to address the issue en banc. An\nAppeal Panel then reviewed the decision de novo and rejected each of BP’s\narguments.\n BP then requested discretionary review in the district court. BP\nrepeated its arguments with one exception. It did not argue that the award\nshould be offset by awards to other non-profits to whom it had made grants to\nprevent double recovery. The district court denied discretionary review. BP\nappeals the denial of discretionary review.\n\n\n\n\n 4\n\f No. 18-30147\n II\n We review the district court’s denial of discretionary review for abuse of\ndiscretion. 2 It is generally an abuse of discretion not to review a decision that\n“actually contradicted or misapplied the Settlement Agreement, or had the\nclear potential to” do so. 3 However, we have been careful to note that it is\n“wrong to suggest that the district court must grant review of all claims that\nraise a question about the proper interpretation of the Settlement\nAgreement.” 4 It is not an abuse of discretion to deny a request for review that\n“involve[s] no pressing question of how the Settlement Agreement should be\ninterpreted or implemented, but simply raise[s] the correctness of a\ndiscretionary administrative decision in the facts of a single claimant's case.” 5\nIt may also be an abuse of discretion to deny a request for review that raises a\nrecurring issue on which the Appeal Panels are split if “the resolution of the\nquestion will substantially impact the administration of the Agreement.” 6\n BP argues that the district court abused its discretion by failing (1) to\nresolve a recurring issue on which the Appeal Panels are split, and (2) to review\nan Appeal Panel’s decision that contradicts the Settlement Agreement. We\naddress each argument.\n A\n BP argues that the treatment of grant-making entities like Claimant is\n“a recurring and important issue in administering the Settlement\n\n\n 2 Claimant ID 100212278 v. BP Expl. & Prod., Inc., 848 F.3d 407, 410 (5th Cir. 2017)\n(citing Holmes Motors, Inc. v. BP Expl. & Prod., 829 F.3d 313, 315 (5th Cir. 2016)).\n 3 Id. (quoting Holmes Motors, 829 F.3d at 315) (internal quotations omitted).\n 4 Id. (quoting Holmes Motors, 829 F.3d at 316) (internal quotations omitted); see also\n\nIn re Deepwater Horizon, 785 F.3d 986, 999 (5th Cir. 2015) (“We do not intend any part of\nthis opinion to turn the district court's discretionary review into a mandatory review. To do\nso would frustrate the clear purpose of the Settlement Agreement to curtail litigation.”).\n 5 Claimant ID 100212278, 848 F.3d at 410 (quoting In re Deepwater Horizon, 641 F.\n\nApp’x 405, 410 (5th Cir. 2016)) (alterations in original).\n 6 Id. (quoting In re Deepwater Horizon, 632 F. App’x 199, 203-04 (5th Cir. 2015)).\n\n 5\n\f No. 18-30147\n[Agreement].” It reasons that the award is significant because of (1) the\namount involved, (2) the “unusually lengthy” analysis of the Appeal Panel, (3)\nthe Panel’s reliance on contested characterization of precedent, (4) Claimant’s\nadmission that donors play a role in determining how grants are made, and (5)\nthe threat of double-recovery. BP additionally maintains that there is a “split”\namong the Appeal Panels.\n BP points to a decision of an Appeal Panel that excluded from “revenue”\nfunds received by a non-profit that were immediately distributed to other non-\nprofit affiliates. In that appeal, the claimant challenged the Claims\nAdministrator’s decision to exclude a state-grant from revenue because the\nClaims Administrator found the funds were a “pass-through” grant in which\nthe state granted money to claimant and claimant distributed an identical\namount to its affiliates. The Appeal Panel upheld the exclusion.\n “For [a] ruling to create a conflict with the one now before us, it must\nhave involved substantially identical claimants relying on substantially\nidentical documentation.” 7 The one award identified by BP does not show a\nsplit among the Appeal Panels. In that case, the receipt of funds coupled with\nan exactly matching distribution in the same month supported the Claims\nAdministrator’s decision to treat the funds as pass-through and not revenue.\nHere, BP has not shown that Claimant is engaged in the same type of dollar-\nfor-dollar distribution. Claimant does not dispute that it grants a large\npercentage of funds it receives to other entities. However, Claimant contests\nthe characterization of its funding as merely a pass-through, and the Appeal\nPanel agreed. The question of what particular percentage of funds that a\ncharity passes through will give rise to the characterization of the donations\n\n\n\n 7 Claimant ID 100128765 v. BP Expl. & Prod., Inc., 709 F. App’x 771, 773 (5th Cir.\n2017) (per curiam).\n 6\n\f No. 18-30147\nas pass-throughs instead of revenue is a difficult one. But, we cannot say that\nthe Appeal Panels are split. The Appeal Panel here explicitly rejected BP’s\nargument that Claimant is primarily a pass-through organization because a\nlarge part of its donations are passed through and donors are involved in the\nultimate decision about where donated funds are spent. Rather than reflecting\na split that must be resolved by the district court, the Appeal Panel’s decision\nreflects that the Panels are conscious of factual differences that may\ndistinguish claimants. 8\n Nor can we agree with BP’s argument that the size of the award requires\nappellate review. While any multi-million dollar award is “significant” in the\nordinary sense, the size of the award alone does not make the issue significant\nenough to require district court review. 9 Further, the “unusually lengthy”\ndecision of the Appeal Panel is not a reason to doubt the Panel—it is an\nindication that the Panel thoroughly considered all of BP’s arguments and\nassessed the documentation provided by Claimant to apply the Settlement\nAgreement. Finally, BP did not argue to the district court that it should have\naddressed the specter of double recovery, so BP cannot rely on that argument\nto show that the district court abused its discretion. 10\n\n\n\n\n 8 See Claimant ID 100190818 v. BP Expl. & Prod., Inc., 718 F. App’x 220, 222 (5th Cir.\n2018); Claimant ID 100051301 v. BP Expl. & Prod., Inc., 694 F. App’x 236, 240 (5th Cir. 2017)\n(“[T]he fact that Appeal Panels have reached different conclusions for this issue depending\non the circumstances of each case does not represent the type of Appeal Panel split that would\nrequire the district court’s review.”).\n 9 See In re Deepwater Horizon, 785 F.3d 1003, 1021 (5th Cir. 2015) (“Non-Profit\n\nDecision”) (“[D]enying this award because of its size would open the floodgates to a flurry of\nchallenges to nonprofit awards, undermining the aims of the [settlement program].”)\n 10 In re Deepwater Horizon, 814 F.3d 748, 752 (5th Cir. 2016) (citing Cent. Sw. Tex.\n\nDev., L.L.C. v. JPMorgan Chase Bank, Nat’l Ass’n, 780 F.3d 296, 300-01 (5th Cir. 2015))\n(“Claimants did not make this argument in their memorandum in support of their motion\nbefore the district court, and it is accordingly forfeited.”).\n\n 7\n\f No. 18-30147\n B\n BP also argues that the district court abused its discretion because the\naward is contrary to the terms of the Settlement Agreement. BP argues three\nways in which the award is contrary to “economic reality”: (1) The donations at\nissue are not “revenue,” (2) if the donations are revenue, the Appeal Panel did\nnot properly match expenses to revenue in the month earned, and (3) if the\ndonations are revenue, the entire $8.9 million should not be recorded in 2009.\n 1\n BP’s contention that the $8.9 million donations are not “revenue” is\ncontrary to this court’s Non-Profit Decision. 11 In that case, we were confronted\nwith the argument that donations and grants to non-profits did not qualify as\n“revenue” for purposes of Exhibit 4C’s compensation formula. 12 We recognized\nthat “modern nonprofits are commercial entities that seek to generate cash\nsurpluses,” and held that revenue includes donations and grants to non-\nprofits. 13 We also addressed the work that non-profits do to raise funds, and\nnoted that non-profits must do significant work to solicit donations and grants\n“to keep their doors open.” 14 We rejected BP’s narrow view of the work that\nnon-profits perform to “earn their revenue” and upheld the Claims\nAdministrator’s reading of the Settlement Agreement that non-profit\ndonations and grants are typically “revenue” under Exhibit 4C. 15\n While acknowledging our Non-Profit Decision, BP nevertheless argues\nthat these particular $8.9 million donations are not revenue. It insists that\nthe donations are not made to Claimant, but that Claimant merely acts as a\n“‘fiduciary’ for the ultimate beneficiaries.” BP likens Claimant to Western\n\n\n 11 785 F.3d 1003 (5th Cir. 2015).\n 12 Id. at 1012.\n 13 Id.\n 14 Id. at 1013.\n 15 Id.\n\n 8\n\f No. 18-30147\nUnion, arguing that none of the funds belong to Claimant and must be\ndistributed according to the wishes of the donors. The basis of this argument\nis that Claimant solicits donations for placement in donor-advised funds,\nwhere the donor expresses how the donations are to be spent. Despite the fact\nthat the Internal Revenue Code requires all charitable donations in donor-\nadvised funds to be exclusively the funds of the non-profit, 16 BP argues that\nClaimant is ultimately subject to the will of donors and therefore those\ndonations cannot be considered Claimant’s revenue. The Appeal Panel\ndisagreed and focused on the aspects of Claimant’s operations that cannot be\nconsidered pass-through, such as the workshops it conducts, the series of\nlectures and performances it presents, and the funding of a police perception\nsurvey which was used in undertaking police reform in Claimant’s community.\nThe Appeal Panel held that the contested donations were unrestricted\ndonations made to Claimant, and thus fall squarely within the definition of\n“revenue” we set forth in Non-Profit Decision. 17\n BP argues that this factual determination was error and urges us to\nremand to the district court for evidentiary hearings to determine whether the\nparticular donations were of donor-advised funds. However, the district court\ndid not abuse its discretion by deferring to the Claims Administrator’s\ndiscretionary administrative decision regarding the documentation required to\nsubstantiate a BEL claim. 18 The Settlement Agreement contemplates that the\nClaims Administrator will review supporting documentation to process claims.\nThe district court’s decision to defer to the Claims Administrator’s\n\n\n\n\n 16 See 26 U.S.C. § 170(f)(18).\n 17 785 F.3d 1003 (5th Cir. 2015).\n 18 See Claimant ID 100212278 v. BP Expl. & Prod., Inc., 848 F.3d 407, 410 (5th Cir.\n\n2017) (quoting In re Deepwater Horizon, 641 F. App’x 405, 410 (5th Cir. 2016)) (alterations in\noriginal).\n 9\n\f No. 18-30147\nsubstantiation requirements and factual finding that the two donations at\nissue were unrestricted grants was not an abuse of discretion.\n 2\n BP also argues that, even if the donations are revenue, the Claims\nAdministrator did not properly match the $8.9 million donations with\nexpenses. In BP’s view, Claimant gave some or all of the donations at issue to\nother non-profits and those grants should be considered “Variable Expenses”\nthat must be matched to the month in which the donations were received. The\nClaims Administrator determined the expenses of the claim were “not\nsufficiently matched” and applied “Policy 495” to match the expenses. Policy\n495 was created by the Claims Administrator and approved by the district\ncourt in response to a decision of this court. 19 We first held in Deepwater\nHorizon I 20 that the Settlement Agreement should be interpreted “in\naccordance with economic reality” and remanded for the district court to\ndetermine whether the agreement required the Claims Administrator to\n“match” profits and losses. 21 In “matched” profit and loss statements, costs\nfollow revenue—which is registered when generated or received—and this\nprovides a clear picture of net income. 22 In “unmatched” profit and loss\nstatements, revenue is registered when generated or received, and costs are\nregistered when incurred. 23 We noted that unmatched profit and loss\nstatements can “make it appear as if a claimant has suffered damages that he,\n\n\n\n\n 19 See In Re Deepwater Horizon, 858 F.3d 298, 300-01 (5th Cir. 2017) (“Policy 495\nDecision”).\n 20 732 F.3d 326 (5th Cir. 2013) (“Deepwater Horizon I”).\n 21 Id. at 339.\n 22 Policy 495 Decision, 858 F.3d at 301.\n 23 Id.\n\n\n\n 10\n\f No. 18-30147\nin fact, did not suffer.” 24 Policy 495 was created to address the problem of\nunmatched revenues. 25\n This court approved of a portion of Policy 495 in our Policy 495\nDecision. 26 Policy 495 had five different formulas for matching revenue with\nexpenses, and we upheld only the Annual Variable Margin Methodology\n(AVMM). 27 “The AVMM requires the Claims Administrator to match all\nunmatched profit and loss statements.” 28 We held the other methodologies\nwere impermissible because they required the Claims Administrator to “move,\nsmooth, or otherwise reallocate revenue for claimants,” contrary to the express\nterms of the Settlement Agreement that gives each claimant the right to choose\nits own Compensation Period. 29 We had assumed that “process[ing] claims in\naccordance with economic reality” would comport with the text of the\nSettlement Agreement, but recognized that will not always be true. 30\nAccordingly, when the text of the Settlement Agreement conflicts with\neconomic reality, the text controls. 31\n The Claims Administrator applied the AVMM to Claimant’s claims and\nmatched the unmatched profit and loss statements. BP is not satisfied with\nthat methodology in this case because, in its view, real matching would\ncorrelate any distributions from the $8.9 million donations back to the month\nin which the donations were generated. It argues, without support, that the\nClaims Administrator did not undertake the first step of making line-by-line\ncorrections to a claimant’s records. BP has not identified any errors that\n\n\n\n 24 Id.\n 25 Id. at 301-02.\n 26 Id. at 301.\n 27 Id. at 300-01.\n 28 Id. at 302.\n 29 Id. at 303.\n 30 See id. at 304 (quoting Deepwater Horizon I, 732 F.3d 326, 339 (5th Cir. 2013)).\n 31 Id.\n\n 11\n\f No. 18-30147\nshould have been corrected, except for its blanket assertion that the $8.9\nmillion was donated for the express purpose of granting those funds to other\norganizations.\n Policy 495 and the AVMM recognize that the Settlement Agreement does\nnot mandate that BEL claimants keep profit and loss statements under any\nparticular basis, so the Claims Administrator “will analyze the P&Ls under\nthe basis . . . of accounting used by the claimant in the normal course of\nbusiness.” The Claims Administrator analyzed Claimant’s profit and loss\nstatements under its usual accounting method, found that such statements\nwere not sufficiently matched, and then applied the AVMM to match them.\nThe Appeal Panel upheld the application of the AVMM. Claimant maintains\nthat it properly attributes expenses to the months in which it distributes funds\nand that the donations to which BP objects were not tied to any planned or\naccrued distribution. BP’s objection is limited to the individual factual\ndetermination of a specific claimant, and denying review was not an abuse of\ndiscretion. 32\n 3\n Finally, BP argues that the entire $8.9 million should not be recorded as\nrevenue in 2009. In BP’s view, because Claimant did not receive the entire\namount in cash in 2009, Claimant should have recorded its donations in the\nyears in which it received cash payments. Claimant records the entire value\nof unconditional promises to give in the year of the pledge, discounted to\npresent value, in accordance with Generally Accepted Accounting Principles\n(GAAP), and its auditors approved of this method. BP seeks to reallocate\n\n\n\n 32See Claimant ID 100236236 v. BP Expl. & Prod., Inc., 699 F. App’x 308, 310-11 (5th\nCir. 2017) (citing In re Deepwater (Sexton), 641 F. App’x 405, 410 (5th Cir. 2016)); Claimant\nID 100051301 v. BP Expl. & Prod., Inc., 694 F. App’x 236, 240 (5th Cir. 2017).\n\n 12\n\f No. 18-30147\nrevenue to a different time period. We disapproved of such a practice in the\nPolicy 495 Decision. 33 Requiring the Claims Administrator to take the\nrevenue, properly allocated under Claimant’s normal accounting procedures\nthat follow GAAP, and reallocate them to the month in which Claimant\nreceived the cash payment would deprive “claimant [of] the right to choose his\nor her Compensation Period.” 34 The Appeal Panel’s decision to apply the\nClaimant’s usual accounting procedure did not contradict the Settlement\nAgreement. Accordingly, the district court did not abuse its discretion in\ndenying review.\n * * *\n For the foregoing reasons, we AFFIRM the judgment of the district court.\n\n\n\n\n 33 858 F.3d 298, 304 (5th Cir. 2017).\n 34 Id.\n 13\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: BP EXPLORATION & PRODUCTION, INCORPORATED; BP America Production Company; BP, P.L.C., Requesting Parties-Appellants, v. CLAIMANT ID 100217946, Objecting Party-Appellee.\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-18\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nIN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n March 18, 2019\\n No. 18-30147\\n Lyle W. Cayce\\n Clerk\\nBP EXPLORATION & PRODUCTION, INCORPORATED; BP AMERICA\\nPRODUCTION COMPANY; BP, P.L.C.,\\n\\n Requesting Parties–Appellants,\\n\\nv.\\n\\nCLAIMANT ID 100217946,\\n\\n Objecting Party–Appellee.\\n\\n\\n\\n\\n Appeal from the United States District Court\\n for the Eastern District of Louisiana\\n\\n\\nBefore WIENER, DENNIS, and OWEN, Circuit Judges.\\nPER CURIAM:\\n This is an appeal from an award to Claimant ID 100217946 (Claimant)\\nunder the Settlement Program established following the Deepwater Horizon oil\\nspill. The Claims Administrator concluded that the non-profit Claimant is\\nentitled to compensation of nearly $15 million. An Appeal Panel within the\\nSettlement Program affirmed, and the district court denied discretionary\\nreview. BP appeals, arguing that two donations were improperly counted by\\nthe Claims Administrator and the district court was required to review the\\naward. We affirm the district court’s judgment.\\n\\f No. 18-30147\\n I\\n In April 2010, an explosion on the Deepwater Horizon, a mobile offshore\\ndrilling unit leased by BP Exploration & Production, Inc., BP America\\nProduction Company, and BP, P.L.C. (collectively, BP), caused the discharge\\nof millions of gallons of oil into the Gulf of Mexico. 1 Two years later, BP entered\\ninto the “Deepwater Horizon Economic and Property Damages Settlement\\nAgreement” with a class of individuals and entities allegedly injured by the\\nDeepwater Horizon oil spill. The Settlement Agreement created the Settlement\\nProgram under which claims for settlement benefits are reviewed by the\\nClaims Administrator, whose decisions may be appealed to an Appeal Panel.\\n Businesses seeking settlement benefits as compensation for economic\\nlosses “must establish that their loss was due to or resulting from the\\nDeepwater Horizon Incident” by meeting the applicable “causation\\nrequirement[].” The Settlement Agreement imposes different causation\\nrequirements on businesses located in different geographic “zones.”\\nBusinesses located in Zone A are not required to establish causation unless\\nthey fall into one of the agreed-upon exceptions. Claimant is located in Zone A\\nand is not one of the agreed-upon exceptions, so it was not required to establish\\ncausation.\\n Once causation is established or inferred, claimants must prove an\\neconomic loss using the methodology in Exhibit 4C. Under Step 1 of the\\nformula, claimants compare their Variable Profit in the Compensation\\nPeriod—a consecutive three-month period between May and December 2010—\\nto their Variable Profit during a Benchmark Period of the claimant’s choosing.\\nThe Variable Profit is calculated by considering the total monthly revenue over\\n\\n\\n\\n 1 Ctr. for Biological Diversity, Inc. v. BP Am. Prod. Co., 704 F.3d 413, 418 (5th Cir.\\n2013).\\n 2\\n\\f No. 18-30147\\nthe period and subtracting the corresponding variable expenses over the same\\ntime period, including “Variable Costs,” variable portions of salaries, and other\\nexpenses. If the Claimant has less Variable Profit in the Compensation Period\\nthan in the Benchmark period, it is entitled to compensation for that\\ndifference. Under Step 2 of the compensation formula, claimants are also\\ncompensated for incremental profits the claimant might have expected to\\ngenerate in 2010 in the absence of the spill, based on the claimant’s revenue\\ntrend before the spill. Claimants may also be entitled to a Risk Transfer\\nPremium (RTP) depending on where the business is located. The amount of\\nthe risk transfer premium is based on the total Step 1 and Step 2\\nCompensation multiplied by a variable found in Exhibit 15 of the Settlement\\nAgreement, the RTP Chart.\\n Claimant is a non-profit organization that solicits donations for its own\\nprogramming and distributes grants to other non-profit organizations.\\nClaimant submitted a Business Economic Loss (BEL) Claim to the Settlement\\nProgram. The Claims Administrator determined that Claimant was eligible\\nfor $5,814,307.79 at Step 1 Compensation by comparing its Variable Profit in\\nAugust through October 2010 with the same period in 2009. The Claims\\nAdministrator then determined that Claimant was entitled to an RTP of 1.5\\ntimes the amount of its losses, which was $8,721,461.69. In addition, the\\nClaims Administrator awarded $7,062.50 of Claimant Accounting support as\\nreimbursement for expenses that Claimant incurred in the claims process. All\\ntold, the Claims Administrator awarded $14,542,831.98 to Claimant.\\n BP appealed the award to a three-member Appeal Panel. It argued that\\ntwo large donations received by Claimant totaling $8.9 million were\\nimproperly included in the economic loss calculation, which resulted in an\\nexcessive award. The first donation was an unsecured non-negotiable\\npromissory note for $5,913,491.66 to be paid in eight equal annual installments\\n 3\\n\\f No. 18-30147\\nbeginning June 30, 2010, with interest accruing on the unpaid balance. The\\nother donation at issue was a $3,000,000 pledge to be paid over ten years in\\nannual installments of $300,000, with a check for the first $300,000 attached\\nto the pledge. BP argued there were four issues with the inclusion of these\\ndonations in the economic loss calculation: (1) The donations were not\\n“revenue,” (2) even if the payments were revenue, Claimant could only treat\\nthose payments that were actually received in 2009 as revenue for 2009, (3) if\\nthe entire $8.9 million could be properly treated as revenue, the Settlement\\nProgram failed to match the donations with corresponding distributions that\\nClaimant granted to other non-profits that should be treated as expenses, and\\n(4) awards made to entities that maintained funds with Claimant should offset\\nClaimant’s award to avoid impermissible double recovery.\\n BP requested that an en banc Appeal Panel review the award to\\n“promote and maintain uniformity and consistency of the Appeal Panel\\ndecisions,” contending that an Appeal Panel in another case involving a non-\\nprofit had ruled differently than the Claims Administrator. The Appeal Panel\\ninitially indicated that it would consider the appeal en banc. Before rendering\\na decision, the Appeal Panel decided not to address the issue en banc. An\\nAppeal Panel then reviewed the decision de novo and rejected each of BP’s\\narguments.\\n BP then requested discretionary review in the district court. BP\\nrepeated its arguments with one exception. It did not argue that the award\\nshould be offset by awards to other non-profits to whom it had made grants to\\nprevent double recovery. The district court denied discretionary review. BP\\nappeals the denial of discretionary review.\\n\\n\\n\\n\\n 4\\n\\f No. 18-30147\\n II\\n We review the district court’s denial of discretionary review for abuse of\\ndiscretion. 2 It is generally an abuse of discretion not to review a decision that\\n“actually contradicted or misapplied the Settlement Agreement, or had the\\nclear potential to” do so. 3 However, we have been careful to note that it is\\n“wrong to suggest that the district court must grant review of all claims that\\nraise a question about the proper interpretation of the Settlement\\nAgreement.” 4 It is not an abuse of discretion to deny a request for review that\\n“involve[s] no pressing question of how the Settlement Agreement should be\\ninterpreted or implemented, but simply raise[s] the correctness of a\\ndiscretionary administrative decision in the facts of a single claimant's case.” 5\\nIt may also be an abuse of discretion to deny a request for review that raises a\\nrecurring issue on which the Appeal Panels are split if “the resolution of the\\nquestion will substantially impact the administration of the Agreement.” 6\\n BP argues that the district court abused its discretion by failing (1) to\\nresolve a recurring issue on which the Appeal Panels are split, and (2) to review\\nan Appeal Panel’s decision that contradicts the Settlement Agreement. We\\naddress each argument.\\n A\\n BP argues that the treatment of grant-making entities like Claimant is\\n“a recurring and important issue in administering the Settlement\\n\\n\\n 2 Claimant ID 100212278 v. BP Expl. & Prod., Inc., 848 F.3d 407, 410 (5th Cir. 2017)\\n(citing Holmes Motors, Inc. v. BP Expl. & Prod., 829 F.3d 313, 315 (5th Cir. 2016)).\\n 3 Id. (quoting Holmes Motors, 829 F.3d at 315) (internal quotations omitted).\\n 4 Id. (quoting Holmes Motors, 829 F.3d at 316) (internal quotations omitted); see also\\n\\nIn re Deepwater Horizon, 785 F.3d 986, 999 (5th Cir. 2015) (“We do not intend any part of\\nthis opinion to turn the district court's discretionary review into a mandatory review. To do\\nso would frustrate the clear purpose of the Settlement Agreement to curtail litigation.”).\\n 5 Claimant ID 100212278, 848 F.3d at 410 (quoting In re Deepwater Horizon, 641 F.\\n\\nApp’x 405, 410 (5th Cir. 2016)) (alterations in original).\\n 6 Id. (quoting In re Deepwater Horizon, 632 F. App’x 199, 203-04 (5th Cir. 2015)).\\n\\n 5\\n\\f No. 18-30147\\n[Agreement].” It reasons that the award is significant because of (1) the\\namount involved, (2) the “unusually lengthy” analysis of the Appeal Panel, (3)\\nthe Panel’s reliance on contested characterization of precedent, (4) Claimant’s\\nadmission that donors play a role in determining how grants are made, and (5)\\nthe threat of double-recovery. BP additionally maintains that there is a “split”\\namong the Appeal Panels.\\n BP points to a decision of an Appeal Panel that excluded from “revenue”\\nfunds received by a non-profit that were immediately distributed to other non-\\nprofit affiliates. In that appeal, the claimant challenged the Claims\\nAdministrator’s decision to exclude a state-grant from revenue because the\\nClaims Administrator found the funds were a “pass-through” grant in which\\nthe state granted money to claimant and claimant distributed an identical\\namount to its affiliates. The Appeal Panel upheld the exclusion.\\n “For [a] ruling to create a conflict with the one now before us, it must\\nhave involved substantially identical claimants relying on substantially\\nidentical documentation.” 7 The one award identified by BP does not show a\\nsplit among the Appeal Panels. In that case, the receipt of funds coupled with\\nan exactly matching distribution in the same month supported the Claims\\nAdministrator’s decision to treat the funds as pass-through and not revenue.\\nHere, BP has not shown that Claimant is engaged in the same type of dollar-\\nfor-dollar distribution. Claimant does not dispute that it grants a large\\npercentage of funds it receives to other entities. However, Claimant contests\\nthe characterization of its funding as merely a pass-through, and the Appeal\\nPanel agreed. The question of what particular percentage of funds that a\\ncharity passes through will give rise to the characterization of the donations\\n\\n\\n\\n 7 Claimant ID 100128765 v. BP Expl. & Prod., Inc., 709 F. App’x 771, 773 (5th Cir.\\n2017) (per curiam).\\n 6\\n\\f No. 18-30147\\nas pass-throughs instead of revenue is a difficult one. But, we cannot say that\\nthe Appeal Panels are split. The Appeal Panel here explicitly rejected BP’s\\nargument that Claimant is primarily a pass-through organization because a\\nlarge part of its donations are passed through and donors are involved in the\\nultimate decision about where donated funds are spent. Rather than reflecting\\na split that must be resolved by the district court, the Appeal Panel’s decision\\nreflects that the Panels are conscious of factual differences that may\\ndistinguish claimants. 8\\n Nor can we agree with BP’s argument that the size of the award requires\\nappellate review. While any multi-million dollar award is “significant” in the\\nordinary sense, the size of the award alone does not make the issue significant\\nenough to require district court review. 9 Further, the “unusually lengthy”\\ndecision of the Appeal Panel is not a reason to doubt the Panel—it is an\\nindication that the Panel thoroughly considered all of BP’s arguments and\\nassessed the documentation provided by Claimant to apply the Settlement\\nAgreement. Finally, BP did not argue to the district court that it should have\\naddressed the specter of double recovery, so BP cannot rely on that argument\\nto show that the district court abused its discretion. 10\\n\\n\\n\\n\\n 8 See Claimant ID 100190818 v. BP Expl. & Prod., Inc., 718 F. App’x 220, 222 (5th Cir.\\n2018); Claimant ID 100051301 v. BP Expl. & Prod., Inc., 694 F. App’x 236, 240 (5th Cir. 2017)\\n(“[T]he fact that Appeal Panels have reached different conclusions for this issue depending\\non the circumstances of each case does not represent the type of Appeal Panel split that would\\nrequire the district court’s review.”).\\n 9 See In re Deepwater Horizon, 785 F.3d 1003, 1021 (5th Cir. 2015) (“Non-Profit\\n\\nDecision”) (“[D]enying this award because of its size would open the floodgates to a flurry of\\nchallenges to nonprofit awards, undermining the aims of the [settlement program].”)\\n 10 In re Deepwater Horizon, 814 F.3d 748, 752 (5th Cir. 2016) (citing Cent. Sw. Tex.\\n\\nDev., L.L.C. v. JPMorgan Chase Bank, Nat’l Ass’n, 780 F.3d 296, 300-01 (5th Cir. 2015))\\n(“Claimants did not make this argument in their memorandum in support of their motion\\nbefore the district court, and it is accordingly forfeited.”).\\n\\n 7\\n\\f No. 18-30147\\n B\\n BP also argues that the district court abused its discretion because the\\naward is contrary to the terms of the Settlement Agreement. BP argues three\\nways in which the award is contrary to “economic reality”: (1) The donations at\\nissue are not “revenue,” (2) if the donations are revenue, the Appeal Panel did\\nnot properly match expenses to revenue in the month earned, and (3) if the\\ndonations are revenue, the entire $8.9 million should not be recorded in 2009.\\n 1\\n BP’s contention that the $8.9 million donations are not “revenue” is\\ncontrary to this court’s Non-Profit Decision. 11 In that case, we were confronted\\nwith the argument that donations and grants to non-profits did not qualify as\\n“revenue” for purposes of Exhibit 4C’s compensation formula. 12 We recognized\\nthat “modern nonprofits are commercial entities that seek to generate cash\\nsurpluses,” and held that revenue includes donations and grants to non-\\nprofits. 13 We also addressed the work that non-profits do to raise funds, and\\nnoted that non-profits must do significant work to solicit donations and grants\\n“to keep their doors open.” 14 We rejected BP’s narrow view of the work that\\nnon-profits perform to “earn their revenue” and upheld the Claims\\nAdministrator’s reading of the Settlement Agreement that non-profit\\ndonations and grants are typically “revenue” under Exhibit 4C. 15\\n While acknowledging our Non-Profit Decision, BP nevertheless argues\\nthat these particular $8.9 million donations are not revenue. It insists that\\nthe donations are not made to Claimant, but that Claimant merely acts as a\\n“‘fiduciary’ for the ultimate beneficiaries.” BP likens Claimant to Western\\n\\n\\n 11 785 F.3d 1003 (5th Cir. 2015).\\n 12 Id. at 1012.\\n 13 Id.\\n 14 Id. at 1013.\\n 15 Id.\\n\\n 8\\n\\f No. 18-30147\\nUnion, arguing that none of the funds belong to Claimant and must be\\ndistributed according to the wishes of the donors. The basis of this argument\\nis that Claimant solicits donations for placement in donor-advised funds,\\nwhere the donor expresses how the donations are to be spent. Despite the fact\\nthat the Internal Revenue Code requires all charitable donations in donor-\\nadvised funds to be exclusively the funds of the non-profit, 16 BP argues that\\nClaimant is ultimately subject to the will of donors and therefore those\\ndonations cannot be considered Claimant’s revenue. The Appeal Panel\\ndisagreed and focused on the aspects of Claimant’s operations that cannot be\\nconsidered pass-through, such as the workshops it conducts, the series of\\nlectures and performances it presents, and the funding of a police perception\\nsurvey which was used in undertaking police reform in Claimant’s community.\\nThe Appeal Panel held that the contested donations were unrestricted\\ndonations made to Claimant, and thus fall squarely within the definition of\\n“revenue” we set forth in Non-Profit Decision. 17\\n BP argues that this factual determination was error and urges us to\\nremand to the district court for evidentiary hearings to determine whether the\\nparticular donations were of donor-advised funds. However, the district court\\ndid not abuse its discretion by deferring to the Claims Administrator’s\\ndiscretionary administrative decision regarding the documentation required to\\nsubstantiate a BEL claim. 18 The Settlement Agreement contemplates that the\\nClaims Administrator will review supporting documentation to process claims.\\nThe district court’s decision to defer to the Claims Administrator’s\\n\\n\\n\\n\\n 16 See 26 U.S.C. § 170(f)(18).\\n 17 785 F.3d 1003 (5th Cir. 2015).\\n 18 See Claimant ID 100212278 v. BP Expl. & Prod., Inc., 848 F.3d 407, 410 (5th Cir.\\n\\n2017) (quoting In re Deepwater Horizon, 641 F. App’x 405, 410 (5th Cir. 2016)) (alterations in\\noriginal).\\n 9\\n\\f No. 18-30147\\nsubstantiation requirements and factual finding that the two donations at\\nissue were unrestricted grants was not an abuse of discretion.\\n 2\\n BP also argues that, even if the donations are revenue, the Claims\\nAdministrator did not properly match the $8.9 million donations with\\nexpenses. In BP’s view, Claimant gave some or all of the donations at issue to\\nother non-profits and those grants should be considered “Variable Expenses”\\nthat must be matched to the month in which the donations were received. The\\nClaims Administrator determined the expenses of the claim were “not\\nsufficiently matched” and applied “Policy 495” to match the expenses. Policy\\n495 was created by the Claims Administrator and approved by the district\\ncourt in response to a decision of this court. 19 We first held in Deepwater\\nHorizon I 20 that the Settlement Agreement should be interpreted “in\\naccordance with economic reality” and remanded for the district court to\\ndetermine whether the agreement required the Claims Administrator to\\n“match” profits and losses. 21 In “matched” profit and loss statements, costs\\nfollow revenue—which is registered when generated or received—and this\\nprovides a clear picture of net income. 22 In “unmatched” profit and loss\\nstatements, revenue is registered when generated or received, and costs are\\nregistered when incurred. 23 We noted that unmatched profit and loss\\nstatements can “make it appear as if a claimant has suffered damages that he,\\n\\n\\n\\n\\n 19 See In Re Deepwater Horizon, 858 F.3d 298, 300-01 (5th Cir. 2017) (“Policy 495\\nDecision”).\\n 20 732 F.3d 326 (5th Cir. 2013) (“Deepwater Horizon I”).\\n 21 Id. at 339.\\n 22 Policy 495 Decision, 858 F.3d at 301.\\n 23 Id.\\n\\n\\n\\n 10\\n\\f No. 18-30147\\nin fact, did not suffer.” 24 Policy 495 was created to address the problem of\\nunmatched revenues. 25\\n This court approved of a portion of Policy 495 in our Policy 495\\nDecision. 26 Policy 495 had five different formulas for matching revenue with\\nexpenses, and we upheld only the Annual Variable Margin Methodology\\n(AVMM). 27 “The AVMM requires the Claims Administrator to match all\\nunmatched profit and loss statements.” 28 We held the other methodologies\\nwere impermissible because they required the Claims Administrator to “move,\\nsmooth, or otherwise reallocate revenue for claimants,” contrary to the express\\nterms of the Settlement Agreement that gives each claimant the right to choose\\nits own Compensation Period. 29 We had assumed that “process[ing] claims in\\naccordance with economic reality” would comport with the text of the\\nSettlement Agreement, but recognized that will not always be true. 30\\nAccordingly, when the text of the Settlement Agreement conflicts with\\neconomic reality, the text controls. 31\\n The Claims Administrator applied the AVMM to Claimant’s claims and\\nmatched the unmatched profit and loss statements. BP is not satisfied with\\nthat methodology in this case because, in its view, real matching would\\ncorrelate any distributions from the $8.9 million donations back to the month\\nin which the donations were generated. It argues, without support, that the\\nClaims Administrator did not undertake the first step of making line-by-line\\ncorrections to a claimant’s records. BP has not identified any errors that\\n\\n\\n\\n 24 Id.\\n 25 Id. at 301-02.\\n 26 Id. at 301.\\n 27 Id. at 300-01.\\n 28 Id. at 302.\\n 29 Id. at 303.\\n 30 See id. at 304 (quoting Deepwater Horizon I, 732 F.3d 326, 339 (5th Cir. 2013)).\\n 31 Id.\\n\\n 11\\n\\f No. 18-30147\\nshould have been corrected, except for its blanket assertion that the $8.9\\nmillion was donated for the express purpose of granting those funds to other\\norganizations.\\n Policy 495 and the AVMM recognize that the Settlement Agreement does\\nnot mandate that BEL claimants keep profit and loss statements under any\\nparticular basis, so the Claims Administrator “will analyze the P&Ls under\\nthe basis . . . of accounting used by the claimant in the normal course of\\nbusiness.” The Claims Administrator analyzed Claimant’s profit and loss\\nstatements under its usual accounting method, found that such statements\\nwere not sufficiently matched, and then applied the AVMM to match them.\\nThe Appeal Panel upheld the application of the AVMM. Claimant maintains\\nthat it properly attributes expenses to the months in which it distributes funds\\nand that the donations to which BP objects were not tied to any planned or\\naccrued distribution. BP’s objection is limited to the individual factual\\ndetermination of a specific claimant, and denying review was not an abuse of\\ndiscretion. 32\\n 3\\n Finally, BP argues that the entire $8.9 million should not be recorded as\\nrevenue in 2009. In BP’s view, because Claimant did not receive the entire\\namount in cash in 2009, Claimant should have recorded its donations in the\\nyears in which it received cash payments. Claimant records the entire value\\nof unconditional promises to give in the year of the pledge, discounted to\\npresent value, in accordance with Generally Accepted Accounting Principles\\n(GAAP), and its auditors approved of this method. BP seeks to reallocate\\n\\n\\n\\n 32See Claimant ID 100236236 v. BP Expl. & Prod., Inc., 699 F. App’x 308, 310-11 (5th\\nCir. 2017) (citing In re Deepwater (Sexton), 641 F. App’x 405, 410 (5th Cir. 2016)); Claimant\\nID 100051301 v. BP Expl. & Prod., Inc., 694 F. App’x 236, 240 (5th Cir. 2017).\\n\\n 12\\n\\f No. 18-30147\\nrevenue to a different time period. We disapproved of such a practice in the\\nPolicy 495 Decision. 33 Requiring the Claims Administrator to take the\\nrevenue, properly allocated under Claimant’s normal accounting procedures\\nthat follow GAAP, and reallocate them to the month in which Claimant\\nreceived the cash payment would deprive “claimant [of] the right to choose his\\nor her Compensation Period.” 34 The Appeal Panel’s decision to apply the\\nClaimant’s usual accounting procedure did not contradict the Settlement\\nAgreement. Accordingly, the district court did not abuse its discretion in\\ndenying review.\\n * * *\\n For the foregoing reasons, we AFFIRM the judgment of the district court.\\n\\n\\n\\n\\n 33 858 F.3d 298, 304 (5th Cir. 2017).\\n 34 Id.\\n 13\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1091,"cells":{"id":{"kind":"number","value":4601287,"string":"4,601,287"},"name":{"kind":"string","value":"ENCOMPASS OFFICE SOLUTIONS, INCORPORATED, Plaintiff-Appellee, v. LOUISIANA HEALTH SERVICE & INDEMNITY COMPANY, Doing Business as BlueCross BlueShield of Louisiana. Defendant-Appellant."},"name_abbreviation":{"kind":"string","value":"Encompass Office Solutions, Inc. v. La. Health Serv. & Indem. Co."},"decision_date":{"kind":"string","value":"2019-03-19"},"docket_number":{"kind":"string","value":"17-10736"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Jones, Barksdale, Willett\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"020lead\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/9824710/\", \"author_raw\": \"\"}, {\"author\": \"\", \"type\": \"040dissent\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/9824711/\", \"author_raw\": \"\"}, {\"author\": \"DON R. WILLETT, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 17-10736 Document: 00514879053 Page: 1 Date Filed: 03/19/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n No. 17-10736 March 19, 2019\\n Lyle W. Cayce\\nENCOMPASS OFFICE SOLUTIONS, INCORPORATED., Clerk\\n\\n\\n Plaintiff–Appellee,\\n\\nv.\\n\\nLOUISIANA HEALTH SERVICE & INDEMNITY COMPANY., doing\\nbusiness as BlueCross BlueShield of Louisiana.\\n\\n Defendant–Appellant.\\n\\n\\n Appeal from the United States District Court\\n for the Northern District of Texas\\n\\n\\nBefore JONES, BARKSDALE, and WILLETT, Circuit Judges.\\nDON R. WILLETT, Circuit Judge:\\n Encompass Office Solutions, Inc. provided equipment and staffing for\\ndoctors to perform surgery in their own offices. Doctors and patients took to\\nthis service; insurers did not. Blue Cross and Blue Shield of Louisiana\\n(BCBSLA) began denying Encompass’s claims for in-office surgery support.\\nBCBSLA instead paid a “Global Fee” to the doctor who performed the surgery,\\nas compensation for all related services.\\n Encompass sued BCBSLA for ERISA violations, breach of contract,\\ndefamation, and tortious interference with business relations. BCBSLA largely\\nprevailed at trial. But the district court granted a new trial because of error in\\nthe jury charge. At the second trial, Encompass won on all claims and obtained\\na judgment in its favor. On appeal BCBSLA says that the new trial should\\n\\n Case: 17-10736 Document: 00514879053 Page: 2 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\nnever have been granted, that no reasonable jury could have answered the\\ncontra non valentem (discovery rule) issue in favor of Encompass, and that\\nBCBSLA did not abuse its discretion in denying Encompass’s claims.\\n We AFFIRM the judgment of the district court.\\n\\n I. BACKGROUND\\nA. Factual\\n Encompass provided the equipment, drugs, supplies, and nursing staff\\nnecessary for a doctor to perform outpatient surgery in his own office, rather\\nthan in a hospital or ambulatory surgical center (ASC). This was a novel\\narrangement—at the time, neither Texas nor Louisiana licensed such mobile\\nproviders of ambulatory surgical care.\\n Generally, when a doctor performs surgery at a hospital or ASC, an\\ninsurer like BCBSLA receives three claims: one from the doctor for doing the\\nactual surgery; one from the anesthesiologist, if used; and one from the hospital\\nor ASC for services provided to assist the doctor. When a doctor performs\\nsurgery in his office, however, there is no facility claim because there is no\\nseparate facility. Instead, BCBSLA pays doctors a Global Fee for these in-office\\nsurgeries. The Global Fee is greater than the fee paid to doctors for performing\\nsurgery at a hospital or ASC and is intended to compensate for all overhead\\ncosts of an in-office procedure.\\n When Encompass entered the market, it expanded doctors’ ability to\\nperform in-office surgeries. Encompass sought compensation from insurers by\\nfiling separate claims for its services. At all relevant times, Encompass was an\\nout-of-network service provider for BCBSLA members. Because of this,\\nEncompass obtained an assignment of benefits from each of its BCBSLA-\\ninsured patients. BCBSLA paid Encompass’s claims for several months after\\nEncompass entered the Louisiana market.\\n\\n\\n 2\\n\\n Case: 17-10736 Document: 00514879053 Page: 3 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\n But in June 2010, BCBSLA received a tip that Encompass was\\nsubmitting claims for services it had not provided. On investigation, BCBSLA\\nfound that Encompass was submitting claims, and being paid, for the same in-\\noffice surgeries as the performing doctors. BCBSLA’s billing system would\\nnormally reject “duplicate” claims for surgery at a doctor’s office. But it had\\nbeen processing Encompass’s claims because they used a code modifier.\\nEncompass was using the “TC Modifier,” which stands for “technical\\ncomponent” and covers the equipment, staff, and services necessary for\\nsurgery.\\n BCBSLA began denying Encompass’s claims. BCBSLA also learned that\\nother insurance companies were doing the same. In August 2010, BCBSLA\\nVice President Dawn Cantrell sent a letter to in-network providers directing\\nthem not to use Encompass’s services. Because this letter is the basis for\\nEncompass’s defamation and tortious interference claims, we quote it at\\nlength:\\n Encompass is not eligible to participate in the BlueCross networks\\n and is considered an out-of-network provider. Please do not use\\n Encompass for services provided to BlueCross or [HMO Louisiana,\\n Inc.] members since the facility fees charged by Encompass are not\\n covered, even when they are billed by a network physician.\\n Encompass would have to be a Louisiana licensed [Department of\\n Health and Hospitals]-approved ambulatory surgery facility in\\n order to be eligible for payment of these facility charges.\\n\\n You should also accept your contracted allowable charge for any\\n eligible in-office surgeries you normally perform to be counted as\\n payment in full and not allow Encompass to submit claims to Blue\\n Cross. Please ensure your Blue Cross patients are able to\\n receive network benefits for the services they receive from\\n you by using participating providers.\\n\\n If we find that any network physician is repeatedly using\\n Encompass to deliver facility and procedure services that\\n are not eligible for benefits and our members are being\\n\\n 3\\n\\n Case: 17-10736 Document: 00514879053 Page: 4 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\n billed for these facility charges, the network physician will\\n be subject to termination from the Blue Cross networks.\\nEncompass obtained a copy of the Cantrell Letter and gave it to counsel.\\nEncompass sought clarification from BCBSLA by calling Cantrell three times\\nand leaving voicemail messages. It received no response. In October 2010,\\nBCBSLA Audit Consultant Alan Lofton sent Encompass a separate letter\\ndemanding repayment of nearly $110,000 in paid claims. A few months later,\\nEncompass sued.\\nB. Procedural\\n Encompass initially sued BCBSLA for payment on services provided to\\nBCBSLA insureds. 1 Encompass alleged that BCBSLA had abused its\\ndiscretion in denying Encompass’s claims on ERISA-covered plans and\\nbreached its insurance contracts under state law by denying claims on non-\\nERISA plans.\\n In response, BCBSLA pleaded that under its policy a non-facility\\nprovider must seek payment from the site-of-service owner, usually the doctor\\nwho orders the services, and that Encompass knew this. BCBSLA explained\\nthat for surgeries in a “non-facility setting,” the doctor’s (and any other\\nprofessional’s) reimbursement is all-inclusive. In other words, BCBSLA\\npleaded its Global Fee policy.\\n In February 2013, Encompass deposed Cantrell and Lofton. Cantrell and\\nLofton testified they were not aware of a BCBSLA policy or benefit plan that\\nsaid Encompass’s services were not covered. And they were similarly unaware\\nof a policy or plan permitting BCBSLA to terminate a physician for partnering\\nwith Encompass. This led Encompass to believe that the Cantrell Letter\\ncontained false statements. Because the Cantrell Letter damaged Encompass’s\\n\\n\\n 1 Encompass’s original complaint named only BlueCross BlueShield of Texas. The\\nsecond amended complaint added BCBSLA and a host of BlueCross entities from other states.\\n 4\\n\\n Case: 17-10736 Document: 00514879053 Page: 5 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\nLouisiana business, Encompass in April 2013 amended its complaint to add\\nclaims for defamation and tortious interference with business relations.\\n Both parties moved for summary judgment. The district court at first\\ngranted summary judgment to BCBSLA on Encompass’s defamation and\\ntortious interference claims because it held they were barred by Louisiana’s\\none-year prescriptive period. 2 But on a motion for reconsideration it reversed\\nthis decision. It held instead that a genuine dispute of material fact existed as\\nto whether Encompass was entitled to the benefit of a discovery rule—contra\\nnon valentem—that would suspend the prescriptive period. 3\\n Trial arrived. Encompass tried its tort claims and non-ERISA contract\\nclaims to a jury, and its ERISA claims to the district court. The jury found no\\nliability on the contract claims, and found that Encompass was not entitled to\\nthe benefit of contra non valentem on the tort claims. Because it resolved the\\nprescription issue in BCBSLA’s favor, the jury did not reach the merits of\\nEncompass’s tort claims.\\n Encompass moved for a new trial based on error in the jury charge, and\\nthe district court granted the motion. It held that the jury charge had imposed\\nan incorrect liability standard for the non-ERISA contract claims. The original\\ncharge for these claims required the jury to find that BCBSLA “capriciously\\nand arbitrarily” denied Encompass’s claims for benefits. But it should only\\nhave required them to find the elements for Louisiana breach of contract. And,\\nciting the potential for confusion, the court held that Encompass’s tort claims\\nmust also be retried: “A finding that no breach occurred would reasonably\\n\\n\\n 2 As the district court explained, “[t]he Louisiana Civil Code uses the term . . .\\n‘liberative prescription’ for statutes of limitation.” Encompass Office Sols., Inc. v. La. Health\\nServ. & Indem. Co., No. 3:11-CV-1471-P, 2013 WL 12310676, at *20 n.21 (N.D. Tex. Sept. 17,\\n2013) (citing Prescription, BLACK’S LAW DICTIONARY (9th ed. 2009)).\\n 3 “Contra non valentem non currit praescriptio means that prescription does not run\\n\\nagainst a person who could not bring his suit.” Wells v. Zadeck, 89 So. 3d 1145, 1150 (La.\\n2012) (citing Harvey v. Dixie Graphics, Inc., 593 So. 2d 351, 354 (La. 1992)).\\n 5\\n\\n Case: 17-10736 Document: 00514879053 Page: 6 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\ncause the jury to find that no tort liability existed because the breach of\\ncontract claim underpins the basis for the tort claims.” The district court did\\nnot rule on Encompass’s ERISA claims at this stage.\\n At the second trial the jury found for Encompass on both its contract and\\ntort claims, including finding that contra non valentem suspended prescription.\\nThe district court also found for Encompass on its ERISA claims. BCBSLA\\nrenewed its motion for judgment as a matter of law, moved for reconsideration,\\nand moved for a new trial—all of which the district court denied. The district\\ncourt entered judgment for Encompass, and BCBSLA appealed.\\n\\n II. JURISDICTION AND STANDARDS OF REVIEW\\nA. Jurisdiction\\n The district court had jurisdiction based on complete diversity, 28 U.S.C.\\n§ 1332; and under ERISA, 29 U.S.C. §§ 1001 et seq. This court has jurisdiction\\nunder 28 U.S.C. § 1291.\\nB. Standards of Review\\n 1. Grant of a New Trial\\n “We review the district court’s grant or denial of a new trial for abuse of\\ndiscretion.” 4 “A greater degree of scrutiny, however, is given to the grant of a\\nnew trial.” 5 “[W]e exercise broad review of a court’s grant of a new trial because\\nof our respect for the jury as an institution and our concern that the party who\\npersuaded the jury should not be stripped unfairly of a favorable decision.” 6\\n\\n\\n\\n\\n 4 Gutierrez v. Excel Corp., 106 F.3d 683, 687 (5th Cir. 1997) (citing Allied Bank–W.,\\nN.A. v. Stein, 996 F.2d 111, 115 (5th Cir. 1993)).\\n 5 Scott v. Monsanto Co., 868 F.2d 786, 789 (5th Cir. 1989) (citing Conway v. Chem.\\n\\nLeaman Tank Lines, Inc., 610 F.2d 360, 362–63 (5th Cir. 1980) (per curiam)).\\n 6 Gutierrez, 106 F.3d at 687 (alteration in original) (quoting Stein, 996 F.2d at 115).\\n\\n 6\\n\\n Case: 17-10736 Document: 00514879053 Page: 7 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\n 2. Judgment as a Matter of Law\\n “We review de novo the district court’s denial of a motion for judgment\\nas a matter of law, applying the same standards as the district court.” 7\\nJudgment as a matter of law is proper if “a party has been fully heard on an\\nissue during a jury trial and . . . a reasonable jury would not have a legally\\nsufficient evidentiary basis to find for the party on that issue.” 8\\n “We review all the evidence in the record in the light most favorable to\\nthe nonmoving party and draw all reasonable inferences in favor of the\\nnonmoving party; we do not make credibility determinations or weigh the\\nevidence.” 9 We “cannot reverse a denial of a motion for judgment as a matter\\nof law unless the jury’s factual findings are not supported by substantial\\nevidence, or if the legal conclusions implied from the jury’s verdict cannot in\\nlaw be supported by those findings.” 10 In other words, the party moving for\\njudgment as a matter of law can prevail only “if the facts and inferences point\\nso strongly and overwhelmingly in favor of the moving party that reasonable\\njurors could not have arrived at a contrary verdict.” 11 Although our review is\\nde novo, “[a]fter a jury trial, [the] standard of review is especially deferential.” 12\\n 3. ERISA § 502(a)(1)(B) Claims\\n “On appeal from a bench trial, this court review[s] the factual findings of\\nthe trial court for clear error and conclusions of law de novo,” applying the\\n\\n\\n\\n\\n 7 Abraham v. Alpha Chi Omega, 708 F.3d 614, 620 (5th Cir. 2013) (citing Ill. Cent.\\nR.R. Co. v. Guy, 682 F.3d 381, 392–93 (5th Cir. 2012)).\\n 8 FED R. CIV. P. 50(a).\\n 9 Homoki v. Conversion Servs., Inc., 717 F.3d 388, 395 (5th Cir. 2013) (citing Poliner\\n\\nv. Tex. Health Sys., 537 F.3d 368, 376 (5th Cir. 2008)).\\n 10 OneBeacon Ins. Co. v. T. Wade Welch & Assocs., 841 F.3d 669, 676 (5th Cir. 2016)\\n\\n(quoting Am. Home Assurance Co. v. United Space All., LLC, 378 F.3d 482, 488 (5th Cir.\\n2004)).\\n 11 Homoki, 717 F.3d at 395 (citing Poliner, 537 F.3d at 376).\\n 12 Abraham, 708 F.3d at 620 (second alteration in original) (quoting Brown v.\\n\\nSudduth, 675 F.3d 472, 477 (5th Cir. 2012)).\\n 7\\n\\n Case: 17-10736 Document: 00514879053 Page: 8 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\nsame standard as the district court. 13 Because the plans at issue grant\\nBCBSLA discretion to determine eligibility for plan benefits and construe the\\nterms of the plans, we apply the abuse of discretion standard. 14 Thus, if\\nBCBSLA’s “decision is supported by substantial evidence and is not arbitrary\\nand capricious, it must prevail.” 15\\n\\n III. DISCUSSION\\nA. District Court’s Grant of a New Trial\\n In the first trial, the court instructed the jury that BCBSLA was liable\\non Encompass’s non-ERISA claims if it had arbitrarily and capriciously denied\\nclaims for benefits:\\n The burden is on Encompass to prove that BCBS Louisiana had\\n sufficient proof that payment on a claim was due and that the\\n claim was capriciously and arbitrarily denied by BCBS Louisiana.\\n An insurer is arbitrary and capricious when it does not act in a\\n reasonable manner based on the facts known at the time of the\\n decision.\\nIn its motion for a new trial, Encompass successfully argued that this charge\\nhad erroneously imported the arbitrary-and-capricious standard and should,\\ninstead, have simply stated the Louisiana elements of contract.\\n 1. New Trial on the Contract Claims\\n BCBSLA contends that the original charge was correct, and the second\\ntrial should never have happened. It says that the Louisiana Prompt Payment\\nStatute, 16 not the general contract statute, governs an insurer’s breach of a\\n\\n\\n\\n 13 Conn. Gen. Life Ins. Co. v. Humble Surgical Hosp., L.L.C., 878 F.3d 478, 483 (5th\\nCir. 2017) (alteration in original) (quoting George v. Reliance Standard Life Ins. Co., 776 F.3d\\n349, 352 (5th Cir. 2015)).\\n 14 Id. (citing Vega v. Nat’l Life Ins. Servs., Inc., 188 F.3d 287, 295 (5th Cir. 1999) (en\\n\\nbanc), overruled on other grounds by Metro. Life Ins. Co. v. Glenn, 554 U.S. 105, 115–19\\n(2008)).\\n 15 Singletary v. United Parcel Serv., Inc., 828 F.3d 342, 347 (5th Cir. 2016) (quoting\\n\\nCorry v. Liberty Life Assurance Co. of Boston, 499 F.3d 389, 397 (5th Cir. 2007)).\\n 16 LA. STAT. ANN. § 22:1821.\\n\\n 8\\n\\n Case: 17-10736 Document: 00514879053 Page: 9 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\nhealth insurance contract. The Prompt Payment Statute imposes penalties on\\ninsurers who do not, within 30 days, pay any claim that does not present\\nreasonable grounds for denial:\\n All claims arising under the terms of health and accident contracts\\n issued in this state, except as provided in Subsection B of this\\n Section, shall be paid not more than thirty days from the date upon\\n which written notice and proof of claim, in the form required by\\n the terms of the policy, are furnished to the insurer unless just and\\n reasonable grounds, such as would put a reasonable and prudent\\n businessman on his guard, exist. . . . Failure to comply with the\\n provisions of this Section shall subject the insurer to a penalty . . .\\n together with attorney fees to be determined by the court. 17\\nAlthough the words “arbitrary and capricious” do not appear in this section,\\nLouisiana courts have adopted that standard for insurer liability. 18 This is\\nbecause the statute is “penal in nature” and must be “strictly construed.” 19\\nBCBSLA says that because the statute governs “[a]ll claims arising under the\\nterms of health and accident contracts issued in this state,” 20 and specific\\nstatutes trump general ones, 21 this section provides the appropriate standard\\nof liability for Encompass’s contract claims.\\n BCBSLA also contends that Encompass itself invoked the Prompt\\nPayment Statute for its non-ERISA contract claims. Besides contract damages,\\nEncompass’s operative complaint demanded attorney’s fees, costs, and\\n“statutory penalties under Texas and Louisiana law requiring the prompt\\npayment of claims by insurance carriers.” And in its submission for the joint\\n\\n\\n\\n\\n 17 Id. § 22:1821(A).\\n 18 Stewart v. Calcasieu Par. Sch. Bd., 933 So. 2d 797, 801 (La. Ct. App. 2006)\\n(interpreting predecessor LA. STAT. ANN. § 22:657).\\n 19 Id. (quoting Marien v. Gen. Ins. Co. of Am., 836 So. 2d 239, 249 (La. Ct. App. 2002)).\\n 20 LA. STAT. ANN. § 22:1821.\\n 21 Cf., e.g., Pumphrey v. City of New Orleans, 925 So. 2d 1202, 1210 (La. 2006) (“[T]he\\n\\nstatute specifically directed to the matter at issue must prevail as an exception to the statute\\nmore general in character.” (citing Kennedy v. Kennedy, 699 So. 2d 351, 358 (La. 1996))).\\n 9\\n\\n Case: 17-10736 Document: 00514879053 Page: 10 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\npretrial order, Encompass listed “[w]hether BCBSLA abused its discretion by\\ndenying Encompass’s claims” as a contested legal issue.\\n Neither of these theories can rehabilitate the first jury charge. Louisiana\\ncontract law governs Encompass’s claims for benefits under non-ERISA plans\\nbecause, although it is true that the Prompt Payment Statute applies to all\\nLouisiana health insurance contracts, “[u]nder Louisiana law, the cause of\\naction under [§ 22:1821] is separate and distinct from the cause of action for\\nthe breach of the insurance contract.” 22 Encompass alleged a Louisiana\\ncontract claim. So even if it also alleged a Prompt Payment Statute claim, it\\nhad the right to a correct jury instruction on the contract claim. 23 This is\\nparticularly true where, as here, it is easier to prove that the defendant\\nbreached a contract than that it did so arbitrarily and capriciously.\\n BCBSLA has another independent argument. It contends that the first\\njury charge was correct because the insurance plans, by their terms, granted\\nBCBSLA discretion in choosing whether to allow or deny a claim. And in\\nanalogous contexts, “abuse of discretion” and “arbitrary and capricious” are\\nlegally equivalent. 24 Thus, BCBSLA says that the jury was properly instructed\\nto find contract liability only if BCBSLA had arbitrarily and capriciously\\ndenied a claim.\\n\\n\\n 22 Hymel v. HMO of La., Inc., 951 So. 2d 187, 199 (La. Ct. App. 2006) (citing Cramer\\nv. Ass’n Life Ins. Co., Inc., 563 So. 2d 267, 275 (La. Ct. App.), rev’d on other grounds, 569 So.\\n2d 533 (La. 1990)) (interpreting predecessor LA. STAT. ANN. § 22:657); see Cantrelle Fence &\\nSupply Co., Inc. v. Allstate Ins. Co., 515 So. 2d 1074, 1079 (La. 1987) (holding that cause of\\naction under analogous insurance penalty statute was “separate and distinct from the\\nobligation arising out of the contractual relationship under the insurance policy”).\\n 23 See Aero Int’l, Inc. v. U.S. Fire Ins. Co., 713 F.2d 1106, 1113 (5th Cir. 1983) (“[The\\n\\nparty] was entitled to have the critical issues bearing upon its liability ‘submitted to and\\nanswered by the jury upon a clear and proper charge.’” (quoting NMS Indus., Inc. v. Premium\\nCorp. of Am., 451 F.2d 542, 545 (5th Cir. 1971))).\\n 24 See Anderson v. Cytec Indus., Inc., 619 F.3d 505, 512 (5th Cir. 2010) (“[T]here is only\\n\\na semantic, not a substantive, difference between the arbitrary and capricious and the abuse\\nof discretion standards in the ERISA benefits review context.” (quoting Meditrust Fin. Servs.\\nCorp. v. Sterling Chems., Inc., 168 F.3d 211, 214 (5th Cir. 1999))).\\n 10\\n\\n Case: 17-10736 Document: 00514879053 Page: 11 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\n This theory is not quite correct. BCBSLA argues that the first jury\\ncharge properly included an interpretation of the contracts. But the district\\ncourt rejected this argument when it granted a new trial, holding in effect that\\nthe interpretation was not supported by Louisiana law. 25 We agree. No cited\\nLouisiana authority supports an arbitrary and capricious standard for breach\\nof health insurance contracts—even those that grant discretion to the insurer.\\nAnd the district court has discretion of its own to either interpret contract\\nterms as a matter of law or leave them to the factfinder. 26 “Although the\\ninterpretation of a contract is normally a question of law for the Court, that\\ninterpretation frequently depends heavily on the resolution of factual disputes.\\nAnd it is the function of the trier of fact to resolve such factual disputes.” 27\\n In short, charging the jury with an incorrect standard of liability\\nsupports granting a new trial. 28 And the jury indicated confusion from the\\nimproper instruction. 29 Its note to the court shows that the erroneous legal\\nstandard was front and center in deliberations: “Can you clearly define\\nArbitrary and Capricious in the eyes of the court[?]” 30 The district court did not\\nabuse its discretion when it granted a new trial on Encompass’s contract\\nclaims.\\n\\n\\n\\n 25 See Hymel, 951 So. 2d at 199 (affirming general contract law jury instruction for\\ncontract claim and separate instruction for Prompt Payment Statute claim).\\n 26 See Cook Indus., Inc. v. Cmty. Grain, Inc., 614 F.2d 978, 980 (5th Cir. 1980)\\n\\n(affirming district court’s decision not to interpret contract as matter of law).\\n 27 Id. (citing Gen. Wholesale Beer Co. v. Theodore Hamm Co., 567 F.2d 311, 313 (5th\\n\\nCir. 1978)).\\n 28 See Pinkerton v. Spellings, 529 F.3d 513, 519 (5th Cir. 2008) (granting new trial\\n\\nbecause jury instruction wrongly imposed elevated standard for liability); Aero, 713 F.2d at\\n1113 (“A new trial is the appropriate remedy for prejudicial errors in jury instructions.”\\n(citing NMS Indus., Inc. v. Premium Corp. of Am., Inc., 451 F.2d 542, 545 (5th Cir. 1971);\\nPhillips v. State Farm Mut. Auto. Ins. Co., 437 F.2d 365 (5th Cir. 1971))).\\n 29 See, e.g., Aero, 713 F.2d at 1113 n.6 (citing jury note as indication of jury confusion).\\n 30 The court responded by identifying this sentence in the jury charge: “An insurer is\\n\\narbitrary and capricious when it does not act in a reasonable manner based on the facts\\nknown at the time of the decision.”\\n 11\\n\\n Case: 17-10736 Document: 00514879053 Page: 12 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\n 2. New Trial on the Tort Claims\\n The district court held that Encompass’s tort claims should also be\\nretried because they were related to the mischarged contract claims. In the\\ndistrict court’s view, breach of the contracts was a basis of the tort claims.\\nBCBSLA disputes this. It contends that the jury could not possibly have been\\nconfused by overlap of tort and contract issues because it never reached the\\nmerits of the tort claims. Indeed, the jury answered “no” to whether Encompass\\ncould invoke contra non valentem to toll prescription for the tort claims,\\npreventing it from reaching the tort merits questions on the verdict form.\\n Under Federal Rule of Civil Procedure 59(a), the district court may\\n“grant a new trial on all or some of the issues.” “[P]artial new trials should not\\nbe resorted to unless it appears that the issue to be retried is so distinct and\\nseparable from the others that a trial of it alone may be had without\\ninjustice.” 31 “Therefore, when the issues subject to retrial are so interwoven\\nwith other issues in the case that they ‘cannot be submitted to the jury\\nindependently . . . without confusion and uncertainty, which would amount to\\na denial of a fair trial,’ then it is proper to grant a new trial on all of the issues\\nraised.” 32 In addition to considering “interdependence of [the] issues,” we also\\nconsider “an overlapping of proof” relevant to those issues. 33\\n Under this standard, the district court did not abuse its discretion by\\ngranting a new trial on the tort claims. Whether Encompass’s claims for\\nbenefits should have been paid was a common issue between the contract and\\ntort claims—it affects the tort claims because it affects the truth or falsity of\\n\\n\\n\\n\\n 31Anderson v. Siemens Corp., 335 F.3d 466, 475 (5th Cir. 2003) (quoting Colonial\\nLeasing of New England, Inc. v. Logistics Control Int’l, 770 F.2d 479, 481 (5th Cir. 1985)).\\n 32 Colonial Leasing, 770 F.2d at 481 (ellipsis in original) (quoting Gasoline Prods. Co.\\n\\nv. Champlin Ref. Co., 283 U.S. 494, 500 (1931)).\\n 33 Id.\\n\\n 12\\n\\n Case: 17-10736 Document: 00514879053 Page: 13 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\nthe Cantrell letter. 34 And proof of BCBSLA’s internal decision making may be\\nrelevant to both whether it performed its contractual duties and whether it\\ndefamed or tortiously interfered with Encompass. 35\\nB. Judgment as a Matter of Law on Encompass’s Tort Claims—\\n Prescription and Contra Non Valentem\\n BCBSLA says that the district court should have granted its renewed\\nmotion for judgment as a matter of law based on prescription. It is undisputed\\nthat the applicable prescriptive period for Encompass’s tort claims is one year,\\nand that over a year passed between Encompass receiving the Cantrell letter\\nand first claiming defamation and tortious interference. But the jury in the\\nsecond trial found that prescription was suspended under the doctrine of contra\\nnon valentem.\\n Under Louisiana law, “[t]he defendant has the initial burden of proving\\nthat a tort claim has prescribed, but if the defendant shows that one year has\\npassed between the tortious acts and the filing of the lawsuit, then the burden\\nshifts to the plaintiff to prove an exception to prescription.” 36 “[C]ontra non\\nvalentem prevents the running of liberative prescription . . . where the cause\\nof action is neither known nor reasonably knowable by the plaintiff even\\nthough plaintiff’s ignorance is not induced by the defendant.” 37 Under this\\nstandard, “[c]onstructive knowledge is whatever notice is enough to excite\\nattention and put the injured party on guard and call for inquiry.” 38 “[T]his\\nprinciple will not exempt the plaintiff’s claim from the running of prescription\\n\\n\\n\\n 34 See Anderson, 335 F.3d at 475.\\n 35 See Colonial Leasing, 770 F.2d at 481.\\n 36 Terrebonne Par. Sch. Bd. v. Columbia Gulf Transmission Co., 290 F.3d 303, 320\\n\\n(5th Cir. 2002) (citing Miley v. Consol. Gravity Drainage Dist. No. 1, 642 So. 2d 693, 696 (La.\\nCt. App. 1994); Dixon v. Houck, 466 So. 2d 57, 59 (La. Ct. App. 1985)).\\n 37 Marin v. Exxon Mobil Corp., 48 So. 3d 234, 245 (La. 2010) (citing Plaquemines Par.\\n\\nComm’n Council v. Delta Dev. Co., 502 So. 2d 1034 (La. 1987)).\\n 38 Id. at 246 n.12 (quoting Campo v. Correa, 828 So.2d 502, 510–11 (La. 2002)).\\n\\n 13\\n\\n Case: 17-10736 Document: 00514879053 Page: 14 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\nif his ignorance is attributable to his own wilfulness or neglect; that is, a\\nplaintiff will be deemed to know what he could by reasonable diligence have\\nlearned.” 39\\n The Supreme Court of Louisiana has not evaluated contra non valentem\\nfor a defamation or false-statement claim. So “we must make an ‘Erie guess’\\nand determine as best we can what the highest court of the state would be most\\nlikely to decide.” 40 We may look to the decisions of intermediate state courts\\nfor guidance. “Indeed, ‘a decision by an intermediate appellate state court is a\\ndatum for ascertaining state law which is not to be disregarded by a federal\\ncourt unless it is convinced by other persuasive data that the highest court of\\nthe state would decide otherwise.’” 41\\n BCBSLA maintains that contra non valentem does not apply as a matter\\nof law. Encompass had a copy of the Cantrell Letter in 2010. The letter\\nimmediately caused Encompass to confer with counsel and seek clarification\\nfrom BCBSLA. But Encompass waited until 2013 to allege tort claims. And in\\nBCBSLA’s view, Encompass is in a dilemma: Encompass’s contract theory,\\nwhich it was pursuing around the same time it received the Cantrell Letter,\\nrequires the letter to be wrong about coverage. But Encompass’s contra non\\nvalentem theory only works if Encompass was ignorant of the letter’s falsity.\\n Encompass contends that the Cantrell Letter falsified BCBSLA internal\\npolicies, which it could not discover until 2013 despite diligent inquiry.\\nAlthough some statements in the letter were independently verifiable,\\nEncompass says others were simultaneously false, damaging, and opaque to\\n\\n\\n\\n 39 Id. at 246 (quoting Renfroe v. State ex rel. Dep’t of Transp. & Dev., 809 So. 2d 947,\\n953 (La. 2002)).\\n 40 Terrebonne Par., 290 F.3d at 317 (citing Barfield v. Madison County, 212 F.3d 269,\\n\\n271–72 (5th Cir. 2000)).\\n 41 Id. (quoting First Nat’l Bank of Durant v. Trans Terra Corp., 142 F.3d 802, 809 (5th\\n\\nCir. 1998)).\\n 14\\n\\n Case: 17-10736 Document: 00514879053 Page: 15 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\noutsiders. Encompass argued that the letter misrepresented Encompass’s\\n“eligib[ility] to participate in the Blue Cross networks” and “eligib[ility] for\\nbenefit payment.” Eligibility to be in the network, as distinct from present\\nnetwork status or plan coverage for a service, was a matter of BCBSLA policy.\\nAnd according to Encompass, “eligib[ility]” for payment was too. Encompass\\nsays these statements damaged its business by discouraging doctors from\\nworking with it. Encompass also says its diligence to investigate the letter—\\ncalling Cantrell three times in 2010 and leaving messages without response—\\nwas reasonable under the circumstances.\\n We believe the Supreme Court of Louisiana would hold that contra non\\nvalentem was supported by the evidence here. The issue is close and we are\\nmindful of the “especially deferential” standard of review for the jury verdict. 42\\nBCBSLA challenges only the sufficiency of the evidence, not the jury\\ninstruction. The district court rejected BCBSLA’s argument when it denied\\njudgment as a matter of law. We do so as well. Our dissenting colleague takes\\na broader view of constructive notice and a stricter one of the required\\ndiligence. But, in this instance, we find no Louisiana case standing directly\\nagainst contra non valentem and some cases that support it, especially given\\nour standard of review.\\n Louisiana intermediate appellate court decisions show that contra non\\nvalentem suspends prescription for defamation and other false-statement\\nclaims if a reasonably diligent plaintiff knows about the adverse statement but\\nhas not discovered it is false. In Quixx, for example, the insurer plaintiff\\nreceived applications containing false statements, but prescription did not\\nbegin to run until it discovered facts inconsistent with those statements. 43 (The\\n\\n\\n\\n 42Abraham, 708 F.3d at 620 (quoting Brown, 675 F.3d at 477).\\n 43Nat’l Council on Comp. Ins. v. Quixx Temp. Servs., Inc., 665 So. 2d 120, 123–24 (La.\\nCt. App. 1995).\\n 15\\n\\n Case: 17-10736 Document: 00514879053 Page: 16 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\nclaims were prescribed anyway because the insurer waited more than a year\\nto file suit. 44) In another case, Simmons, the plaintiffs argued that contra non\\nvalentem suspended prescription of a tortious interference claim until they\\ndiscovered that the defendant’s financial statements were falsified. 45 The court\\nagreed. The plaintiffs did not have constructive knowledge of falsity until\\nreceiving disclosures during litigation, even though their dispute with the\\ndefendants began over a year earlier. 46 These cases show that a plaintiff can\\nbe aware of a statement without having constructive knowledge of its falsity.\\nThey also show that a plaintiff need not file suit just because an adverse party\\npublicizes unfavorable statements that are not immediately verifiable.\\n Cases setting a stricter diligence bar are distinguishable. In Rozas the\\nplaintiff, a doctor, argued that contra non valentem suspended prescription as\\nlong as his former employer withheld a personnel file that defamed him as\\nclinically incompetent. 47 The court disagreed, because the plaintiff’s own lack\\nof diligence kept him from getting the file. The court said he should have taken\\nmeasures “beyond making one telephone call to a secretary.” 48 This initially\\nseems comparable to Encompass’s diligence. But Rozas was in a different\\nposition. He already knew the defamatory statements’ general content and\\nfalsity: The defendant had rated him clinically incompetent. 49 This weighed\\nheavily in the court’s analysis that he had constructive knowledge of a cause\\nof action. “[P]laintiff had sufficient facts to make him aware that he potentially\\nhad a claim against L.S.U. in 1980 when he learned that L.S.U. had given him\\n\\n\\n\\n\\n 44 Id.\\n 45 Simmons v. Templeton, 723 So. 2d 1009, 1012 (La. Ct. App. 1998).\\n 46 Id. at 1011–12.\\n 47 Rozas v. Dep’t of Health & Human Res., 522 So. 2d 1195, 1196–97 (La. Ct. App.\\n\\n1988).\\n 48 Id. at 1197.\\n 49 Id.\\n 16\\n\\n Case: 17-10736 Document: 00514879053 Page: 17 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\na poor clinical evaluation.” 50 But here the falsity concerned BCBSLA’s internal\\npolicies, and Encompass did not discover it until 2013.\\n And the appellate cases Greenblatt and Neyrey are distinguishable\\nbecause the plaintiffs exercised no diligence at all. 51 These are easier cases\\nwhere the plaintiffs would have known about a cause of action if they took any\\ntimely action to obtain the defendants’ adverse statements. The federal district\\ncourt case Safford is similar. 52 Here, in contrast, Encompass sought\\nclarification about the Cantrell Letter multiple times.\\n Cases stating that consulting with counsel shows constructive\\nknowledge of a claim are also distinguishable. These cases generally involved\\npersonal injuries where consulting counsel logically showed awareness of the\\ncause of action. 53 But here the parties were in a business dispute with many\\npotential legal theories. Consulting counsel about one legal injury does not\\nshow that a party knew or should have known about other legal injuries that\\nare based on different facts. 54 This is especially so given Encompass’s position\\nthat the falsity was known only to BCBSLA.\\n Encompass can escape the posited tort-contract dilemma without\\ncontradiction. Encompass says that BCBSLA breached contracts by refusing\\nto pay covered benefits and committed torts by spreading related statements\\n\\n\\n 50 Id.\\n 51 Greenblatt v. Payne, 929 So. 2d 193, 196 (La. Ct. App. 2006); Neyrey v. Lebrun, 309\\nSo. 2d 722, 723 (La. Ct. App. 1975).\\n 52 Safford v. PaineWebber, Inc., 730 F. Supp. 15, 18 (E.D. La. 1990) (holding contra\\n\\nnon valentem inapplicable because defamatory statements were available at plaintiff’s\\nrequest).\\n 53 See Med. Review Panel Proceeding of Williams v. Lewis, 17 So. 3d 26, 30 (La. Ct.\\n\\nApp. 2009) (medical malpractice for surgery complication); Derrick v. Yamaha Power Sports\\nof New Orleans, 850 So. 2d 829, 833 (La. Ct. App. 2003) (workers compensation for gunshot\\nwound to hand); Clofer v. Celotex Corp., 528 So. 2d 1074, 1076 (La. Ct. App. 1988) (suit against\\nformer employer for lung damage).\\n 54 See, e.g., Simmons, 723 So. 2d at 1011–12 (explaining that transaction was in 1986,\\n\\nlitigation began in November 1987, falsity was discovered in March 1989, and prescription\\ndid not begin to run until March 1989).\\n 17\\n\\n Case: 17-10736 Document: 00514879053 Page: 18 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\nthat were false. 55 It is not implausible that Encompass immediately considered\\nthe Cantrell Letter a breach of contract but only later knew the other\\nstatements might be false. Not every anticipatory breach of contract is tortious.\\nConsider: In a garden-variety defamation case, the truth or falsity of the\\nstatement is readily knowable to the plaintiff—because it is about the\\nplaintiff. 56 Here, in contrast, Encompass says that BCBSLA defamed it by\\nmaking false statements about Encompass’s status under BCBSLA’s own\\npolicies. These policies were opaque to Encompass when it received the letter.\\nAnd Encompass’s inquiries to BCBSLA do not show constructive knowledge\\neither. There is no inconsistency in investigating the letter for the ongoing\\ncoverage dispute but not knowing it contained false statements.\\n Encompass’s status as a sophisticated corporation does not change this.\\nThe Supreme Court of Louisiana teaches that the proper “blueprint” to\\nevaluate reasonable delay for contra non valentem is “looking to the record for\\nevidence of facts within plaintiff’s knowledge and then examining the\\nreasonableness of plaintiff’s inaction in light of those facts, considering\\nplaintiff’s education, intelligence and the nature of defendant’s conduct.” 57 The\\ncircumstances of each case determine the applicability of the doctrine. 58 Here\\nthe jury heard evidence of each blueprint factor.\\n Some evidence showed that in 2010 Encompass knew the Cantrell Letter\\nstated unfavorable BCBSLA policies but not that those statements were false.\\nSome evidence also showed that BCBSLA’s conduct included misstating its\\n\\n\\n\\n 55 Cf. Marshall Invs. Corp. v. R.P. Carbone Co., No. 05-6486, 2006 WL 2644959, at *5\\n(E.D. La. Sept. 13, 2006) (malicious statement as element of tortious interference with\\nbusiness relations); Costello v. Hardy, 864 So. 2d 129, 139 (La. 2004) (false statement as\\nelement of defamation).\\n 56 See, e.g., Safford, 730 F. Supp. at 16–17 (evaluating alleged defamatory statement\\n\\nthat plaintiff engaged in sexual misconduct).\\n 57 Wells, 89 So. 3d at 1151.\\n 58 Id. at 1154.\\n\\n 18\\n\\n Case: 17-10736 Document: 00514879053 Page: 19 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\npolicies and refusing to clarify things. And some evidence showed that\\nEncompass was a corporation advised by counsel. So the jury had sufficient\\nevidence to assess all the factors that Louisiana law considers. 59 It reached a\\n“Yes” verdict on whether contra non valentem applied. In reviewing denial of\\njudgment as a matter of law, we may not reweigh the evidence. 60 Drawing all\\ninferences in favor of Encompass, as we must, the application of contra non\\nvalentem was not wrong as a matter of law. 61\\nC. Encompass’s ERISA Claims\\n ERISA aims to promote the interests of plan participants and their\\nbeneficiaries and to “protect contractually defined benefits.” 62 ERISA\\nenshrines a patient’s right to the “full and fair review” of her claim. 63 As a\\nresult, § 502(a)(1)(B) permits a plan participant to sue to “recover benefits due\\nto him under the terms of his plan, to enforce his rights under the terms of the\\nplan, or to clarify his rights to future benefits under the terms of the plan.” 64\\nHere, Encompass contends that it is an assignee entitled to enforce patients’\\nrights to benefits under BCBSLA plans. BCBSLA challenges Encompass’s\\nright to advance claims for benefits, as well as the district court’s ultimate\\nconclusion that BCBSLA abused its discretion in administering the plans.\\n 1. Anti-Assignment Provisions\\n BCBSLA says that, under the plans’ anti-assignment provisions,\\nEncompass lacked derivative standing to sue for benefits. The district court\\nfound that BCBSLA waived the anti-assignment provisions because it made\\n\\n\\n\\n 59 Id. at 1151.\\n 60 See Homoki, 717 F.3d at 395.\\n 61 See id.\\n 62 N. Cypress Med. Ctr. Operating Co., Ltd. v. Cigna Healthcare (NCMC), 781 F.3d\\n\\n182, 194 (5th Cir. 2015) (quoting Firestone Tire & Rubber Co. v. Bruch, 489 U.S. 101, 113–14\\n(1989)).\\n 63 29 U.S.C. § 1133(2).\\n 64 Id. § 1132(a)(1)(B).\\n\\n 19\\n\\n Case: 17-10736 Document: 00514879053 Page: 20 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\npayments to, and communicated with, Encompass on at least some claims.\\nBCBSLA’s only direct challenge to this conclusion is that Encompass did not\\noffer a jury charge on waiver. To the extent BCBSLA argues that waiver could\\nonly have been found by the jury, we disagree. It is well known that ERISA\\nclaims are the statutory cousins of equitable actions and so are tried to the\\ncourt. 65 Waiver of the anti-assignment clauses—a related issue that is itself\\nequitable—was here also properly decided by the district court. 66 So the anti-\\nassignment clauses do not frustrate Encompass’s recovery on ERISA claims.\\n 2. Contractual Limitations Periods\\n BCBSLA also contends that the plans’ 15-month limitations provisions\\nbar some of Encompass’s claims. 67 ERISA § 502(a)(1)(B) contains no statute of\\nlimitations, but the parties are free to agree to a reasonable limitations\\nperiod. 68 The district court held that the contractual limitations provisions\\nhere were unenforceable across the board because BCBSLA never gave notice\\nof them to Encompass. It cited decisions from other circuits holding that, based\\non ERISA’s implementing regulations, notice is required for similar provisions\\nto be enforceable. 69 BCBSLA does not appear to dispute this notice theory. As\\n\\n\\n 65 Calamia v. Spivey, 632 F.2d 1235, 1237 (5th Cir. Unit A 1980) (“[S]imilar claims\\nwere previously considered equitable and . . . the kind of determination required—whether\\nthe pension fund acted arbitrarily and capriciously—was one traditionally performed by\\njudges.” (citing Wardle v. Cent. States, Se. & Sw. Areas Pension Fund, 627 F.2d 820, 829–30\\n(7th Cir. 1980))).\\n 66 See FED. R. CIV. P. 39(a) (“The trial on all issues so demanded must be by jury\\n\\nunless: . . . the court, on motion or on its own, finds that on some or all of those issues there\\nis no federal right to a jury trial.”); Austin v. Shalala, 994 F.2d 1170, 1177 n.7 (5th Cir. 1993)\\n(explaining that an equitable defense—even to a legal claim—is tried to the court); Reg’l\\nProps., Inc. v. Fin. & Real Estate Consulting Co., 752 F.2d 178, 182–83 (5th Cir. 1985)\\n(holding under Texas law that waiver is equitable defense).\\n 67 BCBSLA maintains that its October 4, 2010 demand letter placed Encompass on\\n\\nnotice that its claims would be denied. Encompass waited over 15 months from this date to\\nfile suit. So BCBSLA contends that all Encompass claims submitted before October 4, 2010\\nare barred by limitations.\\n 68 Heimeshoff v. Hartford Life & Accident Ins. Co., 571 U.S. 99, 105–06 (2013).\\n 69 See Santana-Diaz v. Metro. Life Ins. Co., 816 F.3d 172, 179–82 (1st Cir. 2016) (citing\\n\\n29 C.F.R. § 2560.503–1(g)(1)(iv) for proposition that administrator must provide notice of\\n 20\\n\\n Case: 17-10736 Document: 00514879053 Page: 21 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\na result, we do not disturb the district court’s conclusion that the contractual\\nlimitations provisions are unenforceable.\\n 3. Abuse of Discretion\\n We now review the merits of Encompass’s ERISA claims. To determine\\nwhether an administrator abused its discretion in construing a plan’s terms,\\nwe analyze its plan interpretation in two steps. 70 First, was BCBSLA’s reading\\n“legally correct”? 71 ERISA plans must be written “to be understood by the\\naverage plan participant,” 72 so plans “are interpreted in their ordinary and\\npopular sense as would a person of average intelligence and experience.” 73 The\\n“most important factor to consider” is whether BCBSLA’s “interpretation is\\nconsistent with a fair reading of the plan[s].” 74 If so, the inquiry ends, and there\\nwas no abuse of discretion. 75 Otherwise, the court “must then determine\\nwhether [BCBSLA’s] decision was an abuse of discretion.” 76 “[T]his court may\\nbypass, without deciding, the issue whether the Plan Administrator’s denial\\nwas legally correct, reviewing only whether the Plan Administrator abused its\\ndiscretion in denying the claim if that can be more readily determined.” 77\\n In the second step—deciding whether BCBSLA abused its discretion—\\nthe court considers “(1) the internal consistency of the plan under the\\nadministrator’s interpretation, (2) any relevant regulations formulated by the\\n\\n\\nlimitations period when denying benefits); Mirza v. Ins. Adm’r of Am., Inc., 800 F.3d 129,\\n137–38 (3d Cir. 2015) (same); Moyer v. Metro. Life Ins. Co., 762 F.3d 503, 507 (6th Cir. 2014)\\n(same).\\n 70 Humble Surgical Hosp., 878 F.3d at 483; NCMC, 781 F.3d at 195 (citing Stone v.\\n\\nUNOCAL Termination Allowance Plan, 570 F.3d 252, 257 (5th Cir. 2009)).\\n 71 Humble Surgical Hosp., 878 F.3d at 483 (quoting NCMC, 781 F.3d at 195).\\n 72 29 U.S.C. § 1022(a).\\n 73 NCMC, 781 F.3d at 195 (quoting Stone, 570 F.3d at 260).\\n 74 Id. at 195 (alteration in original) (quoting Crowell v. Shell Oil Co., 541 F.3d 295,\\n\\n313 (5th Cir. 2008)).\\n 75 Humble Surgical Hosp., 878 F.3d at 483.\\n 76 Id. (quoting Stone, 570 F.3d at 257).\\n 77 McCorkle v. Metro. Life Ins. Co., 757 F.3d 452, 457 n.10 (5th Cir. 2014) (alterations\\n\\nand internal quotation marks omitted).\\n 21\\n\\n Case: 17-10736 Document: 00514879053 Page: 22 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\nappropriate administrative agencies, and (3) the factual background of the\\ndetermination and any inferences of lack of good faith.” 78 “In applying the\\nabuse of discretion standard, we analyze whether the plan administrator acted\\narbitrarily or capriciously.” 79\\n Here, the district court only addressed the second step—whether\\nBCBSLA abused its discretion. We take the same approach. 80 This is\\nappropriate because all agree that Encompass’s services were covered under\\nthe plans, and the only dispute is whether Encompass’s claims are\\n“duplicative” of other providers.\\n BCBSLA paid doctors a Global Fee for all services related to surgeries\\nperformed at their offices. The Global Fee compensated a doctor for both his\\nprofessional services and the use of his facility. But when surgery was done at\\na hospital or ASC, BCBSLA made separate payments to those providers to\\ncompensate for use of their facilities and services. In BCBSLA’s view,\\nEncompass is distinguishable from hospitals and ASCs because it is only a\\nservice provider, not a physical facility. And for surgery at a doctor’s office,\\nBCBSLA’s fee already included compensation for both his professional services\\nand a facility. Thus, according to BCBSLA, any other payment would be\\nduplicative.\\n This approach is not internally consistent. BCBSLA admits that the\\nplans cover services like Encompass’s, but cites no plan language authorizing\\nit to limit payment based on who provided the service. 81 Nor does BCBSLA\\n\\n\\n 78 Wildbur v. ARCO Chem. Co., 974 F.2d 631, 638 (5th Cir. 1992) (citing Batchelor v.\\nInt’l Bhd. of Elec. Workers Local 861 Pension & Ret. Fund, 877 F.2d 441, 445–48 (5th Cir.\\n1989)).\\n 79 Bellaire Gen. Hosp. v. Blue Cross Blue Shield of Mich., 97 F.3d 822, 829 (5th Cir.\\n\\n1996) (citing Sweatman v. Commercial Union Ins. Co., 39 F.3d 594, 601 (5th Cir. 1994)).\\n 80 See, e.g., McCorkle, 757 F.3d at 457 n.10; Bellaire, 97 F.3d at 829 (finding abuse of\\n\\ndiscretion without deciding legal correctness).\\n 81 See Vega, 188 F.3d at 302 (“[W]e will not countenance a denial of a claim solely\\n\\nbecause an administrator suspects something may be awry. Although we owe deference to an\\n 22\\n\\n Case: 17-10736 Document: 00514879053 Page: 23 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\nexplain—in terms of the plan—why it may insist on a Global Fee when surgery\\nis done at a doctor’s office, but make separate payments when it is done at a\\nhospital or ASC. 82 And when BCBSLA denied Encompass’s claims, this\\narrangement was not set out in any written internal policy.\\n As for the other two abuse-of-discretion factors, we first note that the\\nfactual background of BCBSLA’s decision shows equivocation over whether to\\ndo business with Encompass, rather than a clear understanding that its claims\\nwere improper. 83 As one BCBSLA executive emailed internally, “Quite\\nhonestly, I’m not one hundred percent sure why we are not contracting with\\nthem, because I don’t believe we have a concrete policy on this provider type or\\nmaybe I missed that somewhere.” Finally, neither party cites regulations that\\nmaterially affect whether Encompass’s claims should have been paid. 84\\n In sum, BCBSLA abused its discretion by arbitrarily denying\\nEncompass’s claims for covered services, as shown by its inconsistent\\ntreatment of similar providers.\\n\\n IV. CONCLUSION\\n We AFFIRM the judgment of the district court.\\n\\n\\n\\n\\nadministrator’s reasoned decision, we owe no deference to the administrator’s unsupported\\nsuspicions.”).\\n 82 See Lain v. UNUM Life Ins. Co. of Am., 279 F.3d 337, 347 (5th Cir. 2002) (“lack of\\n\\nobjectivity” suggests abuse of discretion), overruled on other grounds by Glenn, 554 U.S. at\\n115–19.\\n 83 See Wildbur, 974 F.2d at 638.\\n 84 See id.\\n\\n 23\\n\\n Case: 17-10736 Document: 00514879053 Page: 24 Date Filed: 03/19/2019\\n\\n\\n\\n\\n No. 17-10736\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4378540/\", \"author_raw\": \"DON R. WILLETT, Circuit Judge:\"}, {\"author\": \"EDITH H. JONES, Circuit Judge, dissenting\", \"type\": \"dissent\", \"text\": \"EDITH H. JONES, Circuit Judge, dissenting:\\n I respectfully dissent from the majority’s conclusion upholding the contra\\nnon valentem exception to prescription for this sophisticated medical services\\ncompany that was fully represented by counsel from virtually the moment it\\nreviewed the Cantrell letter. This is not an issue on which deference to the\\njury verdict is required. The facts are plain and undisputed. Encompass and\\nits counsel were on more than “inquiry notice” from the terms of the letter—\\nthey had actual knowledge of the alleged false and defamatory statements in\\nthat letter. Encompass’s counsel explained the company’s position succinctly\\nin closing argument. According to him, the letter contained three “false\\nstatements”: Encompass was not “eligible to participate” in the Blue Cross\\nnetworks; facility fees charged by Encompass “are not covered” even when\\nbilled by the network physician; and Encompass had to be state-licensed to be\\n“eligible” for reimbursement.\\n Encompass sued BlueCross BlueShield of Louisiana (“BCBSLA”) not\\nlong thereafter, following its related suit against Texas Blue Cross, on a theory\\nof breach of contract arising from this letter and BCBSLA’s failure to pay\\nEncompass for its services on behalf of insureds. Encompass knew from the\\noutset it was “eligible,” and it knew there was no “state license” requirement.\\nAs for the third falsehood, it knew quite enough, that BCBSLA was not\\nreimbursing it for in-office surgical assistance because of the claimed scope of\\ninsurance coverage. Whether coverage denial was because of the policy\\nlanguage or internal company policies, or both, or neither, is precisely the kind\\nof nuance a lawyer should investigate. But it took Encompass three years after\\nfiling suit to add this intimately related claim for falsehood and defamation.\\n\\n\\n\\n 24\\n\\n Case: 17-10736 Document: 00514879053 Page: 25 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n “Louisiana courts have held in regard to contra non valentem that a\\ncause of action becomes reasonably knowable to a plaintiff at the time legal\\ncounsel is sought.” Derrick v. Yamaha Power Sports of New Orleans, 850 So.2d\\n829, 833 (La. Ct. App. 2003). Moreover, a defendant’s refusal to provide a\\ndocument that a plaintiff believes to contain information adverse to his\\ninterests does not excuse the plaintiff’s lack of diligence in obtaining the\\ndocument. Rozas v. Dep’t Health & Human Res., 522 So.2d 1195, 1197 (La. Ct.\\nApp. 1988). See also Greenblatt v. Payne, 929 So.2d 193, 195 (La. Ct. App. 2006)\\n(“[Plaintiff] does not allege any facts indicating the reason for the passage of\\ntime between April of 2000, when she learned of the adverse nature of the\\nletter, and July 2003 when her discovery request was granted by [Defendant’s]\\ncounsel.”); Safford v. PaineWebber, Inc., 730 F. Supp. 15, 17 (E.D. La. 1990)\\n(“[P]rescription in this case commenced to run when plaintiff received notice\\nthat documents had been filed by defendant.”).\\n Importantly, misleading conduct by a defendant does not lift the burden\\nof diligence from a sophisticated plaintiff who knows or reasonably should\\nknow that further inquiry would reveal a cause of action. Marin v. Exxon Mobil\\nCorp., 48 So.3d 234, 252 (La. 2010). Add to this the insurer’s refusal to respond\\nto three telephoned requests by Encompass for an explanation of coverage\\ndenial. Such stonewalling should have heightened Encompass’s and its\\nlawyers’ diligence rather than provide an excuse for non-discovery of a new\\nclaim.\\n Although my colleagues have diligently reviewed Louisiana law on\\ncontra non valentem, I respectfully disagree with their application of those\\ncases to these facts. I would reverse the judgment for extracontractual and\\npunitive damages.\\n\\n\\n\\n 25\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4378540/\", \"author_raw\": \"EDITH H. JONES, Circuit Judge, dissenting\"}]}"},"judge1":{"kind":"string","value":"JONES"},"judge2":{"kind":"string","value":"BARKSDALE"},"judge3":{"kind":"string","value":"WILLETT"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":4,"string":"4"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":2,"string":"2"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":2,"string":"2"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4601287/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":1,"string":"1"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":1,"string":"1"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: ENCOMPASS OFFICE SOLUTIONS, INCORPORATED, Plaintiff-Appellee, v. LOUISIANA HEALTH SERVICE & INDEMNITY COMPANY, Doing Business as BlueCross BlueShield of Louisiana. Defendant-Appellant.\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-19\nOpinion type: majority\nHas dissenting opinion: Yes\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 17-10736 Document: 00514879053 Page: 1 Date Filed: 03/19/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\n United States Court of Appeals\n Fifth Circuit\n\n FILED\n No. 17-10736 March 19, 2019\n Lyle W. Cayce\nENCOMPASS OFFICE SOLUTIONS, INCORPORATED., Clerk\n\n\n Plaintiff–Appellee,\n\nv.\n\nLOUISIANA HEALTH SERVICE & INDEMNITY COMPANY., doing\nbusiness as BlueCross BlueShield of Louisiana.\n\n Defendant–Appellant.\n\n\n Appeal from the United States District Court\n for the Northern District of Texas\n\n\nBefore JONES, BARKSDALE, and WILLETT, Circuit Judges.\nDON R. WILLETT, Circuit Judge:\n Encompass Office Solutions, Inc. provided equipment and staffing for\ndoctors to perform surgery in their own offices. Doctors and patients took to\nthis service; insurers did not. Blue Cross and Blue Shield of Louisiana\n(BCBSLA) began denying Encompass’s claims for in-office surgery support.\nBCBSLA instead paid a “Global Fee” to the doctor who performed the surgery,\nas compensation for all related services.\n Encompass sued BCBSLA for ERISA violations, breach of contract,\ndefamation, and tortious interference with business relations. BCBSLA largely\nprevailed at trial. But the district court granted a new trial because of error in\nthe jury charge. At the second trial, Encompass won on all claims and obtained\na judgment in its favor. On appeal BCBSLA says that the new trial should\n\n Case: 17-10736 Document: 00514879053 Page: 2 Date Filed: 03/19/2019\n\n\n No. 17-10736\n\nnever have been granted, that no reasonable jury could have answered the\ncontra non valentem (discovery rule) issue in favor of Encompass, and that\nBCBSLA did not abuse its discretion in denying Encompass’s claims.\n We AFFIRM the judgment of the district court.\n\n I. BACKGROUND\nA. Factual\n Encompass provided the equipment, drugs, supplies, and nursing staff\nnecessary for a doctor to perform outpatient surgery in his own office, rather\nthan in a hospital or ambulatory surgical center (ASC). This was a novel\narrangement—at the time, neither Texas nor Louisiana licensed such mobile\nproviders of ambulatory surgical care.\n Generally, when a doctor performs surgery at a hospital or ASC, an\ninsurer like BCBSLA receives three claims: one from the doctor for doing the\nactual surgery; one from the anesthesiologist, if used; and one from the hospital\nor ASC for services provided to assist the doctor. When a doctor performs\nsurgery in his office, however, there is no facility claim because there is no\nseparate facility. Instead, BCBSLA pays doctors a Global Fee for these in-office\nsurgeries. The Global Fee is greater than the fee paid to doctors for performing\nsurgery at a hospital or ASC and is intended to compensate for all overhead\ncosts of an in-office procedure.\n When Encompass entered the market, it expanded doctors’ ability to\nperform in-office surgeries. Encompass sought compensation from insurers by\nfiling separate claims for its services. At all relevant times, Encompass was an\nout-of-network service provider for BCBSLA members. Because of this,\nEncompass obtained an assignment of benefits from each of its BCBSLA-\ninsured patients. BCBSLA paid Encompass’s claims for several months after\nEncompass entered the Louisiana market.\n\n\n 2\n\n Case: 17-10736 Document: 00514879053 Page: 3 Date Filed: 03/19/2019\n\n\n No. 17-10736\n\n But in June 2010, BCBSLA received a tip that Encompass was\nsubmitting claims for services it had not provided. On investigation, BCBSLA\nfound that Encompass was submitting claims, and being paid, for the same in-\noffice surgeries as the performing doctors. BCBSLA’s billing system would\nnormally reject “duplicate” claims for surgery at a doctor’s office. But it had\nbeen processing Encompass’s claims because they used a code modifier.\nEncompass was using the “TC Modifier,” which stands for “technical\ncomponent” and covers the equipment, staff, and services necessary for\nsurgery.\n BCBSLA began denying Encompass’s claims. BCBSLA also learned that\nother insurance companies were doing the same. In August 2010, BCBSLA\nVice President Dawn Cantrell sent a letter to in-network providers directing\nthem not to use Encompass’s services. Because this letter is the basis for\nEncompass’s defamation and tortious interference claims, we quote it at\nlength:\n Encompass is not eligible to participate in the BlueCross networks\n and is considered an out-of-network provider. Please do not use\n Encompass for services provided to BlueCross or [HMO Louisiana,\n Inc.] members since the facility fees charged by Encompass are not\n covered, even when they are billed by a network physician.\n Encompass would have to be a Louisiana licensed [Department of\n Health and Hospitals]-approved ambulatory surgery facility in\n order to be eligible for payment of these facility charges.\n\n You should also accept your contracted allowable charge for any\n eligible in-office surgeries you normally perform to be counted as\n payment in full and not allow Encompass to submit claims to Blue\n Cross. Please ensure your Blue Cross patients are able to\n receive network benefits for the services they receive from\n you by using participating providers.\n\n If we find that any network physician is repeatedly using\n Encompass to deliver facility and procedure services that\n are not eligible for benefits and our members are being\n\n 3\n\n Case: 17-10736 Document: 00514879053 Page: 4 Date Filed: 03/19/2019\n\n\n No. 17-10736\n\n billed for these facility charges, the network physician will\n be subject to termination from the Blue Cross networks.\nEncompass obtained a copy of the Cantrell Letter and gave it to counsel.\nEncompass sought clarification from BCBSLA by calling Cantrell three times\nand leaving voicemail messages. It received no response. In October 2010,\nBCBSLA Audit Consultant Alan Lofton sent Encompass a separate letter\ndemanding repayment of nearly $110,000 in paid claims. A few months later,\nEncompass sued.\nB. Procedural\n Encompass initially sued BCBSLA for payment on services provided to\nBCBSLA insureds. 1 Encompass alleged that BCBSLA had abused its\ndiscretion in denying Encompass’s claims on ERISA-covered plans and\nbreached its insurance contracts under state law by denying claims on non-\nERISA plans.\n In response, BCBSLA pleaded that under its policy a non-facility\nprovider must seek payment from the site-of-service owner, usually the doctor\nwho orders the services, and that Encompass knew this. BCBSLA explained\nthat for surgeries in a “non-facility setting,” the doctor’s (and any other\nprofessional’s) reimbursement is all-inclusive. In other words, BCBSLA\npleaded its Global Fee policy.\n In February 2013, Encompass deposed Cantrell and Lofton. Cantrell and\nLofton testified they were not aware of a BCBSLA policy or benefit plan that\nsaid Encompass’s services were not covered. And they were similarly unaware\nof a policy or plan permitting BCBSLA to terminate a physician for partnering\nwith Encompass. This led Encompass to believe that the Cantrell Letter\ncontained false statements. Because the Cantrell Letter damaged Encompass’s\n\n\n 1 Encompass’s original complaint named only BlueCross BlueShield of Texas. The\nsecond amended complaint added BCBSLA and a host of BlueCross entities from other states.\n 4\n\n Case: 17-10736 Document: 00514879053 Page: 5 Date Filed: 03/19/2019\n\n\n No. 17-10736\n\nLouisiana business, Encompass in April 2013 amended its complaint to add\nclaims for defamation and tortious interference with business relations.\n Both parties moved for summary judgment. The district court at first\ngranted summary judgment to BCBSLA on Encompass’s defamation and\ntortious interference claims because it held they were barred by Louisiana’s\none-year prescriptive period. 2 But on a motion for reconsideration it reversed\nthis decision. It held instead that a genuine dispute of material fact existed as\nto whether Encompass was entitled to the benefit of a discovery rule—contra\nnon valentem—that would suspend the prescriptive period. 3\n Trial arrived. Encompass tried its tort claims and non-ERISA contract\nclaims to a jury, and its ERISA claims to the district court. The jury found no\nliability on the contract claims, and found that Encompass was not entitled to\nthe benefit of contra non valentem on the tort claims. Because it resolved the\nprescription issue in BCBSLA’s favor, the jury did not reach the merits of\nEncompass’s tort claims.\n Encompass moved for a new trial based on error in the jury charge, and\nthe district court granted the motion. It held that the jury charge had imposed\nan incorrect liability standard for the non-ERISA contract claims. The original\ncharge for these claims required the jury to find that BCBSLA “capriciously\nand arbitrarily” denied Encompass’s claims for benefits. But it should only\nhave required them to find the elements for Louisiana breach of contract. And,\nciting the potential for confusion, the court held that Encompass’s tort claims\nmust also be retried: “A finding that no breach occurred would reasonably\n\n\n 2 As the district court explained, “[t]he Louisiana Civil Code uses the term . . .\n‘liberative prescription’ for statutes of limitation.” Encompass Office Sols., Inc. v. La. Health\nServ. & Indem. Co., No. 3:11-CV-1471-P, 2013 WL 12310676, at *20 n.21 (N.D. Tex. Sept. 17,\n2013) (citing Prescription, BLACK’S LAW DICTIONARY (9th ed. 2009)).\n 3 “Contra non valentem non currit praescriptio means that prescription does not run\n\nagainst a person who could not bring his suit.” Wells v. Zadeck, 89 So. 3d 1145, 1150 (La.\n2012) (citing Harvey v. Dixie Graphics, Inc., 593 So. 2d 351, 354 (La. 1992)).\n 5\n\n Case: 17-10736 Document: 00514879053 Page: 6 Date Filed: 03/19/2019\n\n\n No. 17-10736\n\ncause the jury to find that no tort liability existed because the breach of\ncontract claim underpins the basis for the tort claims.” The district court did\nnot rule on Encompass’s ERISA claims at this stage.\n At the second trial the jury found for Encompass on both its contract and\ntort claims, including finding that contra non valentem suspended prescription.\nThe district court also found for Encompass on its ERISA claims. BCBSLA\nrenewed its motion for judgment as a matter of law, moved for reconsideration,\nand moved for a new trial—all of which the district court denied. The district\ncourt entered judgment for Encompass, and BCBSLA appealed.\n\n II. JURISDICTION AND STANDARDS OF REVIEW\nA. Jurisdiction\n The district court had jurisdiction based on complete diversity, 28 U.S.C.\n§ 1332; and under ERISA, 29 U.S.C. §§ 1001 et seq. This court has jurisdiction\nunder 28 U.S.C. § 1291.\nB. Standards of Review\n 1. Grant of a New Trial\n “We review the district court’s grant or denial of a new trial for abuse of\ndiscretion.” 4 “A greater degree of scrutiny, however, is given to the grant of a\nnew trial.” 5 “[W]e exercise broad review of a court’s grant of a new trial because\nof our respect for the jury as an institution and our concern that the party who\npersuaded the jury should not be stripped unfairly of a favorable decision.” 6\n\n\n\n\n 4 Gutierrez v. Excel Corp., 106 F.3d 683, 687 (5th Cir. 1997) (citing Allied Bank–W.,\nN.A. v. Stein, 996 F.2d 111, 115 (5th Cir. 1993)).\n 5 Scott v. Monsanto Co., 868 F.2d 786, 789 (5th Cir. 1989) (citing Conway v. Chem.\n\nLeaman Tank Lines, Inc., 610 F.2d 360, 362–63 (5th Cir. 1980) (per curiam)).\n 6 Gutierrez, 106 F.3d at 687 (alteration in original) (quoting Stein, 996 F.2d at 115).\n\n 6\n\n Case: 17-10736 Document: 00514879053 Page: 7 Date Filed: 03/19/2019\n\n\n No. 17-10736\n\n 2. Judgment as a Matter of Law\n “We review de novo the district court’s denial of a motion for judgment\nas a matter of law, applying the same standards as the district court.” 7\nJudgment as a matter of law is proper if “a party has been fully heard on an\nissue during a jury trial and . . . a reasonable jury would not have a legally\nsufficient evidentiary basis to find for the party on that issue.” 8\n “We review all the evidence in the record in the light most favorable to\nthe nonmoving party and draw all reasonable inferences in favor of the\nnonmoving party; we do not make credibility determinations or weigh the\nevidence.” 9 We “cannot reverse a denial of a motion for judgment as a matter\nof law unless the jury’s factual findings are not supported by substantial\nevidence, or if the legal conclusions implied from the jury’s verdict cannot in\nlaw be supported by those findings.” 10 In other words, the party moving for\njudgment as a matter of law can prevail only “if the facts and inferences point\nso strongly and overwhelmingly in favor of the moving party that reasonable\njurors could not have arrived at a contrary verdict.” 11 Although our review is\nde novo, “[a]fter a jury trial, [the] standard of review is especially deferential.” 12\n 3. ERISA § 502(a)(1)(B) Claims\n “On appeal from a bench trial, this court review[s] the factual findings of\nthe trial court for clear error and conclusions of law de novo,” applying the\n\n\n\n\n 7 Abraham v. Alpha Chi Omega, 708 F.3d 614, 620 (5th Cir. 2013) (citing Ill. Cent.\nR.R. Co. v. Guy, 682 F.3d 381, 392–93 (5th Cir. 2012)).\n 8 FED R. CIV. P. 50(a).\n 9 Homoki v. Conversion Servs., Inc., 717 F.3d 388, 395 (5th Cir. 2013) (citing Poliner\n\nv. Tex. Health Sys., 537 F.3d 368, 376 (5th Cir. 2008)).\n 10 OneBeacon Ins. Co. v. T. Wade Welch & Assocs., 841 F.3d 669, 676 (5th Cir. 2016)\n\n(quoting Am. Home Assurance Co. v. United Space All., LLC, 378 F.3d 482, 488 (5th Cir.\n2004)).\n 11 Homoki, 717 F.3d at 395 (citing Poliner, 537 F.3d at 376).\n 12 Abraham, 708 F.3d at 620 (second alteration in original) (quoting Brown v.\n\nSudduth, 675 F.3d 472, 477 (5th Cir. 2012)).\n 7\n\n Case: 17-10736 Document: 00514879053 Page: 8 Date Filed: 03/19/2019\n\n\n No. 17-10736\n\nsame standard as the district court. 13 Because the plans at issue grant\nBCBSLA discretion to determine eligibility for plan benefits and construe the\nterms of the plans, we apply the abuse of discretion standard. 14 Thus, if\nBCBSLA’s “decision is supported by substantial evidence and is not arbitrary\nand capricious, it must prevail.” 15\n\n III. DISCUSSION\nA. District Court’s Grant of a New Trial\n In the first trial, the court instructed the jury that BCBSLA was liable\non Encompass’s non-ERISA claims if it had arbitrarily and capriciously denied\nclaims for benefits:\n The burden is on Encompass to prove that BCBS Louisiana had\n sufficient proof that payment on a claim was due and that the\n claim was capriciously and arbitrarily denied by BCBS Louisiana.\n An insurer is arbitrary and capricious when it does not act in a\n reasonable manner based on the facts known at the time of the\n decision.\nIn its motion for a new trial, Encompass successfully argued that this charge\nhad erroneously imported the arbitrary-and-capricious standard and should,\ninstead, have simply stated the Louisiana elements of contract.\n 1. New Trial on the Contract Claims\n BCBSLA contends that the original charge was correct, and the second\ntrial should never have happened. It says that the Louisiana Prompt Payment\nStatute, 16 not the general contract statute, governs an insurer’s breach of a\n\n\n\n 13 Conn. Gen. Life Ins. Co. v. Humble Surgical Hosp., L.L.C., 878 F.3d 478, 483 (5th\nCir. 2017) (alteration in original) (quoting George v. Reliance Standard Life Ins. Co., 776 F.3d\n349, 352 (5th Cir. 2015)).\n 14 Id. (citing Vega v. Nat’l Life Ins. Servs., Inc., 188 F.3d 287, 295 (5th Cir. 1999) (en\n\nbanc), overruled on other grounds by Metro. Life Ins. Co. v. Glenn, 554 U.S. 105, 115–19\n(2008)).\n 15 Singletary v. United Parcel Serv., Inc., 828 F.3d 342, 347 (5th Cir. 2016) (quoting\n\nCorry v. Liberty Life Assurance Co. of Boston, 499 F.3d 389, 397 (5th Cir. 2007)).\n 16 LA. STAT. ANN. § 22:1821.\n\n 8\n\n Case: 17-10736 Document: 00514879053 Page: 9 Date Filed: 03/19/2019\n\n\n No. 17-10736\n\nhealth insurance contract. The Prompt Payment Statute imposes penalties on\ninsurers who do not, within 30 days, pay any claim that does not present\nreasonable grounds for denial:\n All claims arising under the terms of health and accident contracts\n issued in this state, except as provided in Subsection B of this\n Section, shall be paid not more than thirty days from the date upon\n which written notice and proof of claim, in the form required by\n the terms of the policy, are furnished to the insurer unless just and\n reasonable grounds, such as would put a reasonable and prudent\n businessman on his guard, exist. . . . Failure to comply with the\n provisions of this Section shall subject the insurer to a penalty . . .\n together with attorney fees to be determined by the court. 17\nAlthough the words “arbitrary and capricious” do not appear in this section,\nLouisiana courts have adopted that standard for insurer liability. 18 This is\nbecause the statute is “penal in nature” and must be “strictly construed.” 19\nBCBSLA says that because the statute governs “[a]ll claims arising under the\nterms of health and accident contracts issued in this state,” 20 and specific\nstatutes trump general ones, 21 this section provides the appropriate standard\nof liability for Encompass’s contract claims.\n BCBSLA also contends that Encompass itself invoked the Prompt\nPayment Statute for its non-ERISA contract claims. Besides contract damages,\nEncompass’s operative complaint demanded attorney’s fees, costs, and\n“statutory penalties under Texas and Louisiana law requiring the prompt\npayment of claims by insurance carriers.” And in its submission for the joint\n\n\n\n\n 17 Id. § 22:1821(A).\n 18 Stewart v. Calcasieu Par. Sch. Bd., 933 So. 2d 797, 801 (La. Ct. App. 2006)\n(interpreting predecessor LA. STAT. ANN. § 22:657).\n 19 Id. (quoting Marien v. Gen. Ins. Co. of Am., 836 So. 2d 239, 249 (La. Ct. App. 2002)).\n 20 LA. STAT. ANN. § 22:1821.\n 21 Cf., e.g., Pumphrey v. City of New Orleans, 925 So. 2d 1202, 1210 (La. 2006) (“[T]he\n\nstatute specifically directed to the matter at issue must prevail as an exception to the statute\nmore general in character.” (citing Kennedy v. Kennedy, 699 So. 2d 351, 358 (La. 1996))).\n 9\n\n Case: 17-10736 Document: 00514879053 Page: 10 Date Filed: 03/19/2019\n\n\n No. 17-10736\n\npretrial order, Encompass listed “[w]hether BCBSLA abused its discretion by\ndenying Encompass’s claims” as a contested legal issue.\n Neither of these theories can rehabilitate the first jury charge. Louisiana\ncontract law governs Encompass’s claims for benefits under non-ERISA plans\nbecause, although it is true that the Prompt Payment Statute applies to all\nLouisiana health insurance contracts, “[u]nder Louisiana law, the cause of\naction under [§ 22:1821] is separate and distinct from the cause of action for\nthe breach of the insurance contract.” 22 Encompass alleged a Louisiana\ncontract claim. So even if it also alleged a Prompt Payment Statute claim, it\nhad the right to a correct jury instruction on the contract claim. 23 This is\nparticularly true where, as here, it is easier to prove that the defendant\nbreached a contract than that it did so arbitrarily and capriciously.\n BCBSLA has another independent argument. It contends that the first\njury charge was correct because the insurance plans, by their terms, granted\nBCBSLA discretion in choosing whether to allow or deny a claim. And in\nanalogous contexts, “abuse of discretion” and “arbitrary and capricious” are\nlegally equivalent. 24 Thus, BCBSLA says that the jury was properly instructed\nto find contract liability only if BCBSLA had arbitrarily and capriciously\ndenied a claim.\n\n\n 22 Hymel v. HMO of La., Inc., 951 So. 2d 187, 199 (La. Ct. App. 2006) (citing Cramer\nv. Ass’n Life Ins. Co., Inc., 563 So. 2d 267, 275 (La. Ct. App.), rev’d on other grounds, 569 So.\n2d 533 (La. 1990)) (interpreting predecessor LA. STAT. ANN. § 22:657); see Cantrelle Fence &\nSupply Co., Inc. v. Allstate Ins. Co., 515 So. 2d 1074, 1079 (La. 1987) (holding that cause of\naction under analogous insurance penalty statute was “separate and distinct from the\nobligation arising out of the contractual relationship under the insurance policy”).\n 23 See Aero Int’l, Inc. v. U.S. Fire Ins. Co., 713 F.2d 1106, 1113 (5th Cir. 1983) (“[The\n\nparty] was entitled to have the critical issues bearing upon its liability ‘submitted to and\nanswered by the jury upon a clear and proper charge.’” (quoting NMS Indus., Inc. v. Premium\nCorp. of Am., 451 F.2d 542, 545 (5th Cir. 1971))).\n 24 See Anderson v. Cytec Indus., Inc., 619 F.3d 505, 512 (5th Cir. 2010) (“[T]here is only\n\na semantic, not a substantive, difference between the arbitrary and capricious and the abuse\nof discretion standards in the ERISA benefits review context.” (quoting Meditrust Fin. Servs.\nCorp. v. Sterling Chems., Inc., 168 F.3d 211, 214 (5th Cir. 1999))).\n 10\n\n Case: 17-10736 Document: 00514879053 Page: 11 Date Filed: 03/19/2019\n\n\n No. 17-10736\n\n This theory is not quite correct. BCBSLA argues that the first jury\ncharge properly included an interpretation of the contracts. But the district\ncourt rejected this argument when it granted a new trial, holding in effect that\nthe interpretation was not supported by Louisiana law. 25 We agree. No cited\nLouisiana authority supports an arbitrary and capricious standard for breach\nof health insurance contracts—even those that grant discretion to the insurer.\nAnd the district court has discretion of its own to either interpret contract\nterms as a matter of law or leave them to the factfinder. 26 “Although the\ninterpretation of a contract is normally a question of law for the Court, that\ninterpretation frequently depends heavily on the resolution of factual disputes.\nAnd it is the function of the trier of fact to resolve such factual disputes.” 27\n In short, charging the jury with an incorrect standard of liability\nsupports granting a new trial. 28 And the jury indicated confusion from the\nimproper instruction. 29 Its note to the court shows that the erroneous legal\nstandard was front and center in deliberations: “Can you clearly define\nArbitrary and Capricious in the eyes of the court[?]” 30 The district court did not\nabuse its discretion when it granted a new trial on Encompass’s contract\nclaims.\n\n\n\n 25 See Hymel, 951 So. 2d at 199 (affirming general contract law jury instruction for\ncontract claim and separate instruction for Prompt Payment Statute claim).\n 26 See Cook Indus., Inc. v. Cmty. Grain, Inc., 614 F.2d 978, 980 (5th Cir. 1980)\n\n(affirming district court’s decision not to interpret contract as matter of law).\n 27 Id. (citing Gen. Wholesale Beer Co. v. Theodore Hamm Co., 567 F.2d 311, 313 (5th\n\nCir. 1978)).\n 28 See Pinkerton v. Spellings, 529 F.3d 513, 519 (5th Cir. 2008) (granting new trial\n\nbecause jury instruction wrongly imposed elevated standard for liability); Aero, 713 F.2d at\n1113 (“A new trial is the appropriate remedy for prejudicial errors in jury instructions.”\n(citing NMS Indus., Inc. v. Premium Corp. of Am., Inc., 451 F.2d 542, 545 (5th Cir. 1971);\nPhillips v. State Farm Mut. Auto. Ins. Co., 437 F.2d 365 (5th Cir. 1971))).\n 29 See, e.g., Aero, 713 F.2d at 1113 n.6 (citing jury note as indication of jury confusion).\n 30 The court responded by identifying this sentence in the jury charge: “An insurer is\n\narbitrary and capricious when it does not act in a reasonable manner based on the facts\nknown at the time of the decision.”\n 11\n\n Case: 17-10736 Document: 00514879053 Page: 12 Date Filed: 03/19/2019\n\n\n No. 17-10736\n\n 2. New Trial on the Tort Claims\n The district court held that Encompass’s tort claims should also be\nretried because they were related to the mischarged contract claims. In the\ndistrict court’s view, breach of the contracts was a basis of the tort claims.\nBCBSLA disputes this. It contends that the jury could not possibly have been\nconfused by overlap of tort and contract issues because it never reached the\nmerits of the tort claims. Indeed, the jury answered “no” to whether Encompass\ncould invoke contra non valentem to toll prescription for the tort claims,\npreventing it from reaching the tort merits questions on the verdict form.\n Under Federal Rule of Civil Procedure 59(a), the district court may\n“grant a new trial on all or some of the issues.” “[P]artial new trials should not\nbe resorted to unless it appears that the issue to be retried is so distinct and\nseparable from the others that a trial of it alone may be had without\ninjustice.” 31 “Therefore, when the issues subject to retrial are so interwoven\nwith other issues in the case that they ‘cannot be submitted to the jury\nindependently . . . without confusion and uncertainty, which would amount to\na denial of a fair trial,’ then it is proper to grant a new trial on all of the issues\nraised.” 32 In addition to considering “interdependence of [the] issues,” we also\nconsider “an overlapping of proof” relevant to those issues. 33\n Under this standard, the district court did not abuse its discretion by\ngranting a new trial on the tort claims. Whether Encompass’s claims for\nbenefits should have been paid was a common issue between the contract and\ntort claims—it affects the tort claims because it affects the truth or falsity of\n\n\n\n\n 31Anderson v. Siemens Corp., 335 F.3d 466, 475 (5th Cir. 2003) (quoting Colonial\nLeasing of New England, Inc. v. Logistics Control Int’l, 770 F.2d 479, 481 (5th Cir. 1985)).\n 32 Colonial Leasing, 770 F.2d at 481 (ellipsis in original) (quoting Gasoline Prods. Co.\n\nv. Champlin Ref. Co., 283 U.S. 494, 500 (1931)).\n 33 Id.\n\n 12\n\n Case: 17-10736 Document: 00514879053 Page: 13 Date Filed: 03/19/2019\n\n\n No. 17-10736\n\nthe Cantrell letter. 34 And proof of BCBSLA’s internal decision making may be\nrelevant to both whether it performed its contractual duties and whether it\ndefamed or tortiously interfered with Encompass. 35\nB. Judgment as a Matter of Law on Encompass’s Tort Claims—\n Prescription and Contra Non Valentem\n BCBSLA says that the district court should have granted its renewed\nmotion for judgment as a matter of law based on prescription. It is undisputed\nthat the applicable prescriptive period for Encompass’s tort claims is one year,\nand that over a year passed between Encompass receiving the Cantrell letter\nand first claiming defamation and tortious interference. But the jury in the\nsecond trial found that prescription was suspended under the doctrine of contra\nnon valentem.\n Under Louisiana law, “[t]he defendant has the initial burden of proving\nthat a tort claim has prescribed, but if the defendant shows that one year has\npassed between the tortious acts and the filing of the lawsuit, then the burden\nshifts to the plaintiff to prove an exception to prescription.” 36 “[C]ontra non\nvalentem prevents the running of liberative prescription . . . where the cause\nof action is neither known nor reasonably knowable by the plaintiff even\nthough plaintiff’s ignorance is not induced by the defendant.” 37 Under this\nstandard, “[c]onstructive knowledge is whatever notice is enough to excite\nattention and put the injured party on guard and call for inquiry.” 38 “[T]his\nprinciple will not exempt the plaintiff’s claim from the running of prescription\n\n\n\n 34 See Anderson, 335 F.3d at 475.\n 35 See Colonial Leasing, 770 F.2d at 481.\n 36 Terrebonne Par. Sch. Bd. v. Columbia Gulf Transmission Co., 290 F.3d 303, 320\n\n(5th Cir. 2002) (citing Miley v. Consol. Gravity Drainage Dist. No. 1, 642 So. 2d 693, 696 (La.\nCt. App. 1994); Dixon v. Houck, 466 So. 2d 57, 59 (La. Ct. App. 1985)).\n 37 Marin v. Exxon Mobil Corp., 48 So. 3d 234, 245 (La. 2010) (citing Plaquemines Par.\n\nComm’n Council v. Delta Dev. Co., 502 So. 2d 1034 (La. 1987)).\n 38 Id. at 246 n.12 (quoting Campo v. Correa, 828 So.2d 502, 510–11 (La. 2002)).\n\n 13\n\n Case: 17-10736 Document: 00514879053 Page: 14 Date Filed: 03/19/2019\n\n\n No. 17-10736\n\nif his ignorance is attributable to his own wilfulness or neglect; that is, a\nplaintiff will be deemed to know what he could by reasonable diligence have\nlearned.” 39\n The Supreme Court of Louisiana has not evaluated contra non valentem\nfor a defamation or false-statement claim. So “we must make an ‘Erie guess’\nand determine as best we can what the highest court of the state would be most\nlikely to decide.” 40 We may look to the decisions of intermediate state courts\nfor guidance. “Indeed, ‘a decision by an intermediate appellate state court is a\ndatum for ascertaining state law which is not to be disregarded by a federal\ncourt unless it is convinced by other persuasive data that the highest court of\nthe state would decide otherwise.’” 41\n BCBSLA maintains that contra non valentem does not apply as a matter\nof law. Encompass had a copy of the Cantrell Letter in 2010. The letter\nimmediately caused Encompass to confer with counsel and seek clarification\nfrom BCBSLA. But Encompass waited until 2013 to allege tort claims. And in\nBCBSLA’s view, Encompass is in a dilemma: Encompass’s contract theory,\nwhich it was pursuing around the same time it received the Cantrell Letter,\nrequires the letter to be wrong about coverage. But Encompass’s contra non\nvalentem theory only works if Encompass was ignorant of the letter’s falsity.\n Encompass contends that the Cantrell Letter falsified BCBSLA internal\npolicies, which it could not discover until 2013 despite diligent inquiry.\nAlthough some statements in the letter were independently verifiable,\nEncompass says others were simultaneously false, damaging, and opaque to\n\n\n\n 39 Id. at 246 (quoting Renfroe v. State ex rel. Dep’t of Transp. & Dev., 809 So. 2d 947,\n953 (La. 2002)).\n 40 Terrebonne Par., 290 F.3d at 317 (citing Barfield v. Madison County, 212 F.3d 269,\n\n271–72 (5th Cir. 2000)).\n 41 Id. (quoting First Nat’l Bank of Durant v. Trans Terra Corp., 142 F.3d 802, 809 (5th\n\nCir. 1998)).\n 14\n\n Case: 17-10736 Document: 00514879053 Page: 15 Date Filed: 03/19/2019\n\n\n No. 17-10736\n\noutsiders. Encompass argued that the letter misrepresented Encompass’s\n“eligib[ility] to participate in the Blue Cross networks” and “eligib[ility] for\nbenefit payment.” Eligibility to be in the network, as distinct from present\nnetwork status or plan coverage for a service, was a matter of BCBSLA policy.\nAnd according to Encompass, “eligib[ility]” for payment was too. Encompass\nsays these statements damaged its business by discouraging doctors from\nworking with it. Encompass also says its diligence to investigate the letter—\ncalling Cantrell three times in 2010 and leaving messages without response—\nwas reasonable under the circumstances.\n We believe the Supreme Court of Louisiana would hold that contra non\nvalentem was supported by the evidence here. The issue is close and we are\nmindful of the “especially deferential” standard of review for the jury verdict. 42\nBCBSLA challenges only the sufficiency of the evidence, not the jury\ninstruction. The district court rejected BCBSLA’s argument when it denied\njudgment as a matter of law. We do so as well. Our dissenting colleague takes\na broader view of constructive notice and a stricter one of the required\ndiligence. But, in this instance, we find no Louisiana case standing directly\nagainst contra non valentem and some cases that support it, especially given\nour standard of review.\n Louisiana intermediate appellate court decisions show that contra non\nvalentem suspends prescription for defamation and other false-statement\nclaims if a reasonably diligent plaintiff knows about the adverse statement but\nhas not discovered it is false. In Quixx, for example, the insurer plaintiff\nreceived applications containing false statements, but prescription did not\nbegin to run until it discovered facts inconsistent with those statements. 43 (The\n\n\n\n 42Abraham, 708 F.3d at 620 (quoting Brown, 675 F.3d at 477).\n 43Nat’l Council on Comp. Ins. v. Quixx Temp. Servs., Inc., 665 So. 2d 120, 123–24 (La.\nCt. App. 1995).\n 15\n\n Case: 17-10736 Document: 00514879053 Page: 16 Date Filed: 03/19/2019\n\n\n No. 17-10736\n\nclaims were prescribed anyway because the insurer waited more than a year\nto file suit. 44) In another case, Simmons, the plaintiffs argued that contra non\nvalentem suspended prescription of a tortious interference claim until they\ndiscovered that the defendant’s financial statements were falsified. 45 The court\nagreed. The plaintiffs did not have constructive knowledge of falsity until\nreceiving disclosures during litigation, even though their dispute with the\ndefendants began over a year earlier. 46 These cases show that a plaintiff can\nbe aware of a statement without having constructive knowledge of its falsity.\nThey also show that a plaintiff need not file suit just because an adverse party\npublicizes unfavorable statements that are not immediately verifiable.\n Cases setting a stricter diligence bar are distinguishable. In Rozas the\nplaintiff, a doctor, argued that contra non valentem suspended prescription as\nlong as his former employer withheld a personnel file that defamed him as\nclinically incompetent. 47 The court disagreed, because the plaintiff’s own lack\nof diligence kept him from getting the file. The court said he should have taken\nmeasures “beyond making one telephone call to a secretary.” 48 This initially\nseems comparable to Encompass’s diligence. But Rozas was in a different\nposition. He already knew the defamatory statements’ general content and\nfalsity: The defendant had rated him clinically incompetent. 49 This weighed\nheavily in the court’s analysis that he had constructive knowledge of a cause\nof action. “[P]laintiff had sufficient facts to make him aware that he potentially\nhad a claim against L.S.U. in 1980 when he learned that L.S.U. had given him\n\n\n\n\n 44 Id.\n 45 Simmons v. Templeton, 723 So. 2d 1009, 1012 (La. Ct. App. 1998).\n 46 Id. at 1011–12.\n 47 Rozas v. Dep’t of Health & Human Res., 522 So. 2d 1195, 1196–97 (La. Ct. App.\n\n1988).\n 48 Id. at 1197.\n 49 Id.\n 16\n\n Case: 17-10736 Document: 00514879053 Page: 17 Date Filed: 03/19/2019\n\n\n No. 17-10736\n\na poor clinical evaluation.” 50 But here the falsity concerned BCBSLA’s internal\npolicies, and Encompass did not discover it until 2013.\n And the appellate cases Greenblatt and Neyrey are distinguishable\nbecause the plaintiffs exercised no diligence at all. 51 These are easier cases\nwhere the plaintiffs would have known about a cause of action if they took any\ntimely action to obtain the defendants’ adverse statements. The federal district\ncourt case Safford is similar. 52 Here, in contrast, Encompass sought\nclarification about the Cantrell Letter multiple times.\n Cases stating that consulting with counsel shows constructive\nknowledge of a claim are also distinguishable. These cases generally involved\npersonal injuries where consulting counsel logically showed awareness of the\ncause of action. 53 But here the parties were in a business dispute with many\npotential legal theories. Consulting counsel about one legal injury does not\nshow that a party knew or should have known about other legal injuries that\nare based on different facts. 54 This is especially so given Encompass’s position\nthat the falsity was known only to BCBSLA.\n Encompass can escape the posited tort-contract dilemma without\ncontradiction. Encompass says that BCBSLA breached contracts by refusing\nto pay covered benefits and committed torts by spreading related statements\n\n\n 50 Id.\n 51 Greenblatt v. Payne, 929 So. 2d 193, 196 (La. Ct. App. 2006); Neyrey v. Lebrun, 309\nSo. 2d 722, 723 (La. Ct. App. 1975).\n 52 Safford v. PaineWebber, Inc., 730 F. Supp. 15, 18 (E.D. La. 1990) (holding contra\n\nnon valentem inapplicable because defamatory statements were available at plaintiff’s\nrequest).\n 53 See Med. Review Panel Proceeding of Williams v. Lewis, 17 So. 3d 26, 30 (La. Ct.\n\nApp. 2009) (medical malpractice for surgery complication); Derrick v. Yamaha Power Sports\nof New Orleans, 850 So. 2d 829, 833 (La. Ct. App. 2003) (workers compensation for gunshot\nwound to hand); Clofer v. Celotex Corp., 528 So. 2d 1074, 1076 (La. Ct. App. 1988) (suit against\nformer employer for lung damage).\n 54 See, e.g., Simmons, 723 So. 2d at 1011–12 (explaining that transaction was in 1986,\n\nlitigation began in November 1987, falsity was discovered in March 1989, and prescription\ndid not begin to run until March 1989).\n 17\n\n Case: 17-10736 Document: 00514879053 Page: 18 Date Filed: 03/19/2019\n\n\n No. 17-10736\n\nthat were false. 55 It is not implausible that Encompass immediately considered\nthe Cantrell Letter a breach of contract but only later knew the other\nstatements might be false. Not every anticipatory breach of contract is tortious.\nConsider: In a garden-variety defamation case, the truth or falsity of the\nstatement is readily knowable to the plaintiff—because it is about the\nplaintiff. 56 Here, in contrast, Encompass says that BCBSLA defamed it by\nmaking false statements about Encompass’s status under BCBSLA’s own\npolicies. These policies were opaque to Encompass when it received the letter.\nAnd Encompass’s inquiries to BCBSLA do not show constructive knowledge\neither. There is no inconsistency in investigating the letter for the ongoing\ncoverage dispute but not knowing it contained false statements.\n Encompass’s status as a sophisticated corporation does not change this.\nThe Supreme Court of Louisiana teaches that the proper “blueprint” to\nevaluate reasonable delay for contra non valentem is “looking to the record for\nevidence of facts within plaintiff’s knowledge and then examining the\nreasonableness of plaintiff’s inaction in light of those facts, considering\nplaintiff’s education, intelligence and the nature of defendant’s conduct.” 57 The\ncircumstances of each case determine the applicability of the doctrine. 58 Here\nthe jury heard evidence of each blueprint factor.\n Some evidence showed that in 2010 Encompass knew the Cantrell Letter\nstated unfavorable BCBSLA policies but not that those statements were false.\nSome evidence also showed that BCBSLA’s conduct included misstating its\n\n\n\n 55 Cf. Marshall Invs. Corp. v. R.P. Carbone Co., No. 05-6486, 2006 WL 2644959, at *5\n(E.D. La. Sept. 13, 2006) (malicious statement as element of tortious interference with\nbusiness relations); Costello v. Hardy, 864 So. 2d 129, 139 (La. 2004) (false statement as\nelement of defamation).\n 56 See, e.g., Safford, 730 F. Supp. at 16–17 (evaluating alleged defamatory statement\n\nthat plaintiff engaged in sexual misconduct).\n 57 Wells, 89 So. 3d at 1151.\n 58 Id. at 1154.\n\n 18\n\n Case: 17-10736 Document: 00514879053 Page: 19 Date Filed: 03/19/2019\n\n\n No. 17-10736\n\npolicies and refusing to clarify things. And some evidence showed that\nEncompass was a corporation advised by counsel. So the jury had sufficient\nevidence to assess all the factors that Louisiana law considers. 59 It reached a\n“Yes” verdict on whether contra non valentem applied. In reviewing denial of\njudgment as a matter of law, we may not reweigh the evidence. 60 Drawing all\ninferences in favor of Encompass, as we must, the application of contra non\nvalentem was not wrong as a matter of law. 61\nC. Encompass’s ERISA Claims\n ERISA aims to promote the interests of plan participants and their\nbeneficiaries and to “protect contractually defined benefits.” 62 ERISA\nenshrines a patient’s right to the “full and fair review” of her claim. 63 As a\nresult, § 502(a)(1)(B) permits a plan participant to sue to “recover benefits due\nto him under the terms of his plan, to enforce his rights under the terms of the\nplan, or to clarify his rights to future benefits under the terms of the plan.” 64\nHere, Encompass contends that it is an assignee entitled to enforce patients’\nrights to benefits under BCBSLA plans. BCBSLA challenges Encompass’s\nright to advance claims for benefits, as well as the district court’s ultimate\nconclusion that BCBSLA abused its discretion in administering the plans.\n 1. Anti-Assignment Provisions\n BCBSLA says that, under the plans’ anti-assignment provisions,\nEncompass lacked derivative standing to sue for benefits. The district court\nfound that BCBSLA waived the anti-assignment provisions because it made\n\n\n\n 59 Id. at 1151.\n 60 See Homoki, 717 F.3d at 395.\n 61 See id.\n 62 N. Cypress Med. Ctr. Operating Co., Ltd. v. Cigna Healthcare (NCMC), 781 F.3d\n\n182, 194 (5th Cir. 2015) (quoting Firestone Tire & Rubber Co. v. Bruch, 489 U.S. 101, 113–14\n(1989)).\n 63 29 U.S.C. § 1133(2).\n 64 Id. § 1132(a)(1)(B).\n\n 19\n\n Case: 17-10736 Document: 00514879053 Page: 20 Date Filed: 03/19/2019\n\n\n No. 17-10736\n\npayments to, and communicated with, Encompass on at least some claims.\nBCBSLA’s only direct challenge to this conclusion is that Encompass did not\noffer a jury charge on waiver. To the extent BCBSLA argues that waiver could\nonly have been found by the jury, we disagree. It is well known that ERISA\nclaims are the statutory cousins of equitable actions and so are tried to the\ncourt. 65 Waiver of the anti-assignment clauses—a related issue that is itself\nequitable—was here also properly decided by the district court. 66 So the anti-\nassignment clauses do not frustrate Encompass’s recovery on ERISA claims.\n 2. Contractual Limitations Periods\n BCBSLA also contends that the plans’ 15-month limitations provisions\nbar some of Encompass’s claims. 67 ERISA § 502(a)(1)(B) contains no statute of\nlimitations, but the parties are free to agree to a reasonable limitations\nperiod. 68 The district court held that the contractual limitations provisions\nhere were unenforceable across the board because BCBSLA never gave notice\nof them to Encompass. It cited decisions from other circuits holding that, based\non ERISA’s implementing regulations, notice is required for similar provisions\nto be enforceable. 69 BCBSLA does not appear to dispute this notice theory. As\n\n\n 65 Calamia v. Spivey, 632 F.2d 1235, 1237 (5th Cir. Unit A 1980) (“[S]imilar claims\nwere previously considered equitable and . . . the kind of determination required—whether\nthe pension fund acted arbitrarily and capriciously—was one traditionally performed by\njudges.” (citing Wardle v. Cent. States, Se. & Sw. Areas Pension Fund, 627 F.2d 820, 829–30\n(7th Cir. 1980))).\n 66 See FED. R. CIV. P. 39(a) (“The trial on all issues so demanded must be by jury\n\nunless: . . . the court, on motion or on its own, finds that on some or all of those issues there\nis no federal right to a jury trial.”); Austin v. Shalala, 994 F.2d 1170, 1177 n.7 (5th Cir. 1993)\n(explaining that an equitable defense—even to a legal claim—is tried to the court); Reg’l\nProps., Inc. v. Fin. & Real Estate Consulting Co., 752 F.2d 178, 182–83 (5th Cir. 1985)\n(holding under Texas law that waiver is equitable defense).\n 67 BCBSLA maintains that its October 4, 2010 demand letter placed Encompass on\n\nnotice that its claims would be denied. Encompass waited over 15 months from this date to\nfile suit. So BCBSLA contends that all Encompass claims submitted before October 4, 2010\nare barred by limitations.\n 68 Heimeshoff v. Hartford Life & Accident Ins. Co., 571 U.S. 99, 105–06 (2013).\n 69 See Santana-Diaz v. Metro. Life Ins. Co., 816 F.3d 172, 179–82 (1st Cir. 2016) (citing\n\n29 C.F.R. § 2560.503–1(g)(1)(iv) for proposition that administrator must provide notice of\n 20\n\n Case: 17-10736 Document: 00514879053 Page: 21 Date Filed: 03/19/2019\n\n\n No. 17-10736\n\na result, we do not disturb the district court’s conclusion that the contractual\nlimitations provisions are unenforceable.\n 3. Abuse of Discretion\n We now review the merits of Encompass’s ERISA claims. To determine\nwhether an administrator abused its discretion in construing a plan’s terms,\nwe analyze its plan interpretation in two steps. 70 First, was BCBSLA’s reading\n“legally correct”? 71 ERISA plans must be written “to be understood by the\naverage plan participant,” 72 so plans “are interpreted in their ordinary and\npopular sense as would a person of average intelligence and experience.” 73 The\n“most important factor to consider” is whether BCBSLA’s “interpretation is\nconsistent with a fair reading of the plan[s].” 74 If so, the inquiry ends, and there\nwas no abuse of discretion. 75 Otherwise, the court “must then determine\nwhether [BCBSLA’s] decision was an abuse of discretion.” 76 “[T]his court may\nbypass, without deciding, the issue whether the Plan Administrator’s denial\nwas legally correct, reviewing only whether the Plan Administrator abused its\ndiscretion in denying the claim if that can be more readily determined.” 77\n In the second step—deciding whether BCBSLA abused its discretion—\nthe court considers “(1) the internal consistency of the plan under the\nadministrator’s interpretation, (2) any relevant regulations formulated by the\n\n\nlimitations period when denying benefits); Mirza v. Ins. Adm’r of Am., Inc., 800 F.3d 129,\n137–38 (3d Cir. 2015) (same); Moyer v. Metro. Life Ins. Co., 762 F.3d 503, 507 (6th Cir. 2014)\n(same).\n 70 Humble Surgical Hosp., 878 F.3d at 483; NCMC, 781 F.3d at 195 (citing Stone v.\n\nUNOCAL Termination Allowance Plan, 570 F.3d 252, 257 (5th Cir. 2009)).\n 71 Humble Surgical Hosp., 878 F.3d at 483 (quoting NCMC, 781 F.3d at 195).\n 72 29 U.S.C. § 1022(a).\n 73 NCMC, 781 F.3d at 195 (quoting Stone, 570 F.3d at 260).\n 74 Id. at 195 (alteration in original) (quoting Crowell v. Shell Oil Co., 541 F.3d 295,\n\n313 (5th Cir. 2008)).\n 75 Humble Surgical Hosp., 878 F.3d at 483.\n 76 Id. (quoting Stone, 570 F.3d at 257).\n 77 McCorkle v. Metro. Life Ins. Co., 757 F.3d 452, 457 n.10 (5th Cir. 2014) (alterations\n\nand internal quotation marks omitted).\n 21\n\n Case: 17-10736 Document: 00514879053 Page: 22 Date Filed: 03/19/2019\n\n\n No. 17-10736\n\nappropriate administrative agencies, and (3) the factual background of the\ndetermination and any inferences of lack of good faith.” 78 “In applying the\nabuse of discretion standard, we analyze whether the plan administrator acted\narbitrarily or capriciously.” 79\n Here, the district court only addressed the second step—whether\nBCBSLA abused its discretion. We take the same approach. 80 This is\nappropriate because all agree that Encompass’s services were covered under\nthe plans, and the only dispute is whether Encompass’s claims are\n“duplicative” of other providers.\n BCBSLA paid doctors a Global Fee for all services related to surgeries\nperformed at their offices. The Global Fee compensated a doctor for both his\nprofessional services and the use of his facility. But when surgery was done at\na hospital or ASC, BCBSLA made separate payments to those providers to\ncompensate for use of their facilities and services. In BCBSLA’s view,\nEncompass is distinguishable from hospitals and ASCs because it is only a\nservice provider, not a physical facility. And for surgery at a doctor’s office,\nBCBSLA’s fee already included compensation for both his professional services\nand a facility. Thus, according to BCBSLA, any other payment would be\nduplicative.\n This approach is not internally consistent. BCBSLA admits that the\nplans cover services like Encompass’s, but cites no plan language authorizing\nit to limit payment based on who provided the service. 81 Nor does BCBSLA\n\n\n 78 Wildbur v. ARCO Chem. Co., 974 F.2d 631, 638 (5th Cir. 1992) (citing Batchelor v.\nInt’l Bhd. of Elec. Workers Local 861 Pension & Ret. Fund, 877 F.2d 441, 445–48 (5th Cir.\n1989)).\n 79 Bellaire Gen. Hosp. v. Blue Cross Blue Shield of Mich., 97 F.3d 822, 829 (5th Cir.\n\n1996) (citing Sweatman v. Commercial Union Ins. Co., 39 F.3d 594, 601 (5th Cir. 1994)).\n 80 See, e.g., McCorkle, 757 F.3d at 457 n.10; Bellaire, 97 F.3d at 829 (finding abuse of\n\ndiscretion without deciding legal correctness).\n 81 See Vega, 188 F.3d at 302 (“[W]e will not countenance a denial of a claim solely\n\nbecause an administrator suspects something may be awry. Although we owe deference to an\n 22\n\n Case: 17-10736 Document: 00514879053 Page: 23 Date Filed: 03/19/2019\n\n\n No. 17-10736\n\nexplain—in terms of the plan—why it may insist on a Global Fee when surgery\nis done at a doctor’s office, but make separate payments when it is done at a\nhospital or ASC. 82 And when BCBSLA denied Encompass’s claims, this\narrangement was not set out in any written internal policy.\n As for the other two abuse-of-discretion factors, we first note that the\nfactual background of BCBSLA’s decision shows equivocation over whether to\ndo business with Encompass, rather than a clear understanding that its claims\nwere improper. 83 As one BCBSLA executive emailed internally, “Quite\nhonestly, I’m not one hundred percent sure why we are not contracting with\nthem, because I don’t believe we have a concrete policy on this provider type or\nmaybe I missed that somewhere.” Finally, neither party cites regulations that\nmaterially affect whether Encompass’s claims should have been paid. 84\n In sum, BCBSLA abused its discretion by arbitrarily denying\nEncompass’s claims for covered services, as shown by its inconsistent\ntreatment of similar providers.\n\n IV. CONCLUSION\n We AFFIRM the judgment of the district court.\n\n\n\n\nadministrator’s reasoned decision, we owe no deference to the administrator’s unsupported\nsuspicions.”).\n 82 See Lain v. UNUM Life Ins. Co. of Am., 279 F.3d 337, 347 (5th Cir. 2002) (“lack of\n\nobjectivity” suggests abuse of discretion), overruled on other grounds by Glenn, 554 U.S. at\n115–19.\n 83 See Wildbur, 974 F.2d at 638.\n 84 See id.\n\n 23\n\n Case: 17-10736 Document: 00514879053 Page: 24 Date Filed: 03/19/2019\n\n\n\n\n No. 17-10736\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: ENCOMPASS OFFICE SOLUTIONS, INCORPORATED, Plaintiff-Appellee, v. LOUISIANA HEALTH SERVICE & INDEMNITY COMPANY, Doing Business as BlueCross BlueShield of Louisiana. Defendant-Appellant.\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-19\\nOpinion type: majority\\nHas dissenting opinion: Yes\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 17-10736 Document: 00514879053 Page: 1 Date Filed: 03/19/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n No. 17-10736 March 19, 2019\\n Lyle W. Cayce\\nENCOMPASS OFFICE SOLUTIONS, INCORPORATED., Clerk\\n\\n\\n Plaintiff–Appellee,\\n\\nv.\\n\\nLOUISIANA HEALTH SERVICE & INDEMNITY COMPANY., doing\\nbusiness as BlueCross BlueShield of Louisiana.\\n\\n Defendant–Appellant.\\n\\n\\n Appeal from the United States District Court\\n for the Northern District of Texas\\n\\n\\nBefore JONES, BARKSDALE, and WILLETT, Circuit Judges.\\nDON R. WILLETT, Circuit Judge:\\n Encompass Office Solutions, Inc. provided equipment and staffing for\\ndoctors to perform surgery in their own offices. Doctors and patients took to\\nthis service; insurers did not. Blue Cross and Blue Shield of Louisiana\\n(BCBSLA) began denying Encompass’s claims for in-office surgery support.\\nBCBSLA instead paid a “Global Fee” to the doctor who performed the surgery,\\nas compensation for all related services.\\n Encompass sued BCBSLA for ERISA violations, breach of contract,\\ndefamation, and tortious interference with business relations. BCBSLA largely\\nprevailed at trial. But the district court granted a new trial because of error in\\nthe jury charge. At the second trial, Encompass won on all claims and obtained\\na judgment in its favor. On appeal BCBSLA says that the new trial should\\n\\n Case: 17-10736 Document: 00514879053 Page: 2 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\nnever have been granted, that no reasonable jury could have answered the\\ncontra non valentem (discovery rule) issue in favor of Encompass, and that\\nBCBSLA did not abuse its discretion in denying Encompass’s claims.\\n We AFFIRM the judgment of the district court.\\n\\n I. BACKGROUND\\nA. Factual\\n Encompass provided the equipment, drugs, supplies, and nursing staff\\nnecessary for a doctor to perform outpatient surgery in his own office, rather\\nthan in a hospital or ambulatory surgical center (ASC). This was a novel\\narrangement—at the time, neither Texas nor Louisiana licensed such mobile\\nproviders of ambulatory surgical care.\\n Generally, when a doctor performs surgery at a hospital or ASC, an\\ninsurer like BCBSLA receives three claims: one from the doctor for doing the\\nactual surgery; one from the anesthesiologist, if used; and one from the hospital\\nor ASC for services provided to assist the doctor. When a doctor performs\\nsurgery in his office, however, there is no facility claim because there is no\\nseparate facility. Instead, BCBSLA pays doctors a Global Fee for these in-office\\nsurgeries. The Global Fee is greater than the fee paid to doctors for performing\\nsurgery at a hospital or ASC and is intended to compensate for all overhead\\ncosts of an in-office procedure.\\n When Encompass entered the market, it expanded doctors’ ability to\\nperform in-office surgeries. Encompass sought compensation from insurers by\\nfiling separate claims for its services. At all relevant times, Encompass was an\\nout-of-network service provider for BCBSLA members. Because of this,\\nEncompass obtained an assignment of benefits from each of its BCBSLA-\\ninsured patients. BCBSLA paid Encompass’s claims for several months after\\nEncompass entered the Louisiana market.\\n\\n\\n 2\\n\\n Case: 17-10736 Document: 00514879053 Page: 3 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\n But in June 2010, BCBSLA received a tip that Encompass was\\nsubmitting claims for services it had not provided. On investigation, BCBSLA\\nfound that Encompass was submitting claims, and being paid, for the same in-\\noffice surgeries as the performing doctors. BCBSLA’s billing system would\\nnormally reject “duplicate” claims for surgery at a doctor’s office. But it had\\nbeen processing Encompass’s claims because they used a code modifier.\\nEncompass was using the “TC Modifier,” which stands for “technical\\ncomponent” and covers the equipment, staff, and services necessary for\\nsurgery.\\n BCBSLA began denying Encompass’s claims. BCBSLA also learned that\\nother insurance companies were doing the same. In August 2010, BCBSLA\\nVice President Dawn Cantrell sent a letter to in-network providers directing\\nthem not to use Encompass’s services. Because this letter is the basis for\\nEncompass’s defamation and tortious interference claims, we quote it at\\nlength:\\n Encompass is not eligible to participate in the BlueCross networks\\n and is considered an out-of-network provider. Please do not use\\n Encompass for services provided to BlueCross or [HMO Louisiana,\\n Inc.] members since the facility fees charged by Encompass are not\\n covered, even when they are billed by a network physician.\\n Encompass would have to be a Louisiana licensed [Department of\\n Health and Hospitals]-approved ambulatory surgery facility in\\n order to be eligible for payment of these facility charges.\\n\\n You should also accept your contracted allowable charge for any\\n eligible in-office surgeries you normally perform to be counted as\\n payment in full and not allow Encompass to submit claims to Blue\\n Cross. Please ensure your Blue Cross patients are able to\\n receive network benefits for the services they receive from\\n you by using participating providers.\\n\\n If we find that any network physician is repeatedly using\\n Encompass to deliver facility and procedure services that\\n are not eligible for benefits and our members are being\\n\\n 3\\n\\n Case: 17-10736 Document: 00514879053 Page: 4 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\n billed for these facility charges, the network physician will\\n be subject to termination from the Blue Cross networks.\\nEncompass obtained a copy of the Cantrell Letter and gave it to counsel.\\nEncompass sought clarification from BCBSLA by calling Cantrell three times\\nand leaving voicemail messages. It received no response. In October 2010,\\nBCBSLA Audit Consultant Alan Lofton sent Encompass a separate letter\\ndemanding repayment of nearly $110,000 in paid claims. A few months later,\\nEncompass sued.\\nB. Procedural\\n Encompass initially sued BCBSLA for payment on services provided to\\nBCBSLA insureds. 1 Encompass alleged that BCBSLA had abused its\\ndiscretion in denying Encompass’s claims on ERISA-covered plans and\\nbreached its insurance contracts under state law by denying claims on non-\\nERISA plans.\\n In response, BCBSLA pleaded that under its policy a non-facility\\nprovider must seek payment from the site-of-service owner, usually the doctor\\nwho orders the services, and that Encompass knew this. BCBSLA explained\\nthat for surgeries in a “non-facility setting,” the doctor’s (and any other\\nprofessional’s) reimbursement is all-inclusive. In other words, BCBSLA\\npleaded its Global Fee policy.\\n In February 2013, Encompass deposed Cantrell and Lofton. Cantrell and\\nLofton testified they were not aware of a BCBSLA policy or benefit plan that\\nsaid Encompass’s services were not covered. And they were similarly unaware\\nof a policy or plan permitting BCBSLA to terminate a physician for partnering\\nwith Encompass. This led Encompass to believe that the Cantrell Letter\\ncontained false statements. Because the Cantrell Letter damaged Encompass’s\\n\\n\\n 1 Encompass’s original complaint named only BlueCross BlueShield of Texas. The\\nsecond amended complaint added BCBSLA and a host of BlueCross entities from other states.\\n 4\\n\\n Case: 17-10736 Document: 00514879053 Page: 5 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\nLouisiana business, Encompass in April 2013 amended its complaint to add\\nclaims for defamation and tortious interference with business relations.\\n Both parties moved for summary judgment. The district court at first\\ngranted summary judgment to BCBSLA on Encompass’s defamation and\\ntortious interference claims because it held they were barred by Louisiana’s\\none-year prescriptive period. 2 But on a motion for reconsideration it reversed\\nthis decision. It held instead that a genuine dispute of material fact existed as\\nto whether Encompass was entitled to the benefit of a discovery rule—contra\\nnon valentem—that would suspend the prescriptive period. 3\\n Trial arrived. Encompass tried its tort claims and non-ERISA contract\\nclaims to a jury, and its ERISA claims to the district court. The jury found no\\nliability on the contract claims, and found that Encompass was not entitled to\\nthe benefit of contra non valentem on the tort claims. Because it resolved the\\nprescription issue in BCBSLA’s favor, the jury did not reach the merits of\\nEncompass’s tort claims.\\n Encompass moved for a new trial based on error in the jury charge, and\\nthe district court granted the motion. It held that the jury charge had imposed\\nan incorrect liability standard for the non-ERISA contract claims. The original\\ncharge for these claims required the jury to find that BCBSLA “capriciously\\nand arbitrarily” denied Encompass’s claims for benefits. But it should only\\nhave required them to find the elements for Louisiana breach of contract. And,\\nciting the potential for confusion, the court held that Encompass’s tort claims\\nmust also be retried: “A finding that no breach occurred would reasonably\\n\\n\\n 2 As the district court explained, “[t]he Louisiana Civil Code uses the term . . .\\n‘liberative prescription’ for statutes of limitation.” Encompass Office Sols., Inc. v. La. Health\\nServ. & Indem. Co., No. 3:11-CV-1471-P, 2013 WL 12310676, at *20 n.21 (N.D. Tex. Sept. 17,\\n2013) (citing Prescription, BLACK’S LAW DICTIONARY (9th ed. 2009)).\\n 3 “Contra non valentem non currit praescriptio means that prescription does not run\\n\\nagainst a person who could not bring his suit.” Wells v. Zadeck, 89 So. 3d 1145, 1150 (La.\\n2012) (citing Harvey v. Dixie Graphics, Inc., 593 So. 2d 351, 354 (La. 1992)).\\n 5\\n\\n Case: 17-10736 Document: 00514879053 Page: 6 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\ncause the jury to find that no tort liability existed because the breach of\\ncontract claim underpins the basis for the tort claims.” The district court did\\nnot rule on Encompass’s ERISA claims at this stage.\\n At the second trial the jury found for Encompass on both its contract and\\ntort claims, including finding that contra non valentem suspended prescription.\\nThe district court also found for Encompass on its ERISA claims. BCBSLA\\nrenewed its motion for judgment as a matter of law, moved for reconsideration,\\nand moved for a new trial—all of which the district court denied. The district\\ncourt entered judgment for Encompass, and BCBSLA appealed.\\n\\n II. JURISDICTION AND STANDARDS OF REVIEW\\nA. Jurisdiction\\n The district court had jurisdiction based on complete diversity, 28 U.S.C.\\n§ 1332; and under ERISA, 29 U.S.C. §§ 1001 et seq. This court has jurisdiction\\nunder 28 U.S.C. § 1291.\\nB. Standards of Review\\n 1. Grant of a New Trial\\n “We review the district court’s grant or denial of a new trial for abuse of\\ndiscretion.” 4 “A greater degree of scrutiny, however, is given to the grant of a\\nnew trial.” 5 “[W]e exercise broad review of a court’s grant of a new trial because\\nof our respect for the jury as an institution and our concern that the party who\\npersuaded the jury should not be stripped unfairly of a favorable decision.” 6\\n\\n\\n\\n\\n 4 Gutierrez v. Excel Corp., 106 F.3d 683, 687 (5th Cir. 1997) (citing Allied Bank–W.,\\nN.A. v. Stein, 996 F.2d 111, 115 (5th Cir. 1993)).\\n 5 Scott v. Monsanto Co., 868 F.2d 786, 789 (5th Cir. 1989) (citing Conway v. Chem.\\n\\nLeaman Tank Lines, Inc., 610 F.2d 360, 362–63 (5th Cir. 1980) (per curiam)).\\n 6 Gutierrez, 106 F.3d at 687 (alteration in original) (quoting Stein, 996 F.2d at 115).\\n\\n 6\\n\\n Case: 17-10736 Document: 00514879053 Page: 7 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\n 2. Judgment as a Matter of Law\\n “We review de novo the district court’s denial of a motion for judgment\\nas a matter of law, applying the same standards as the district court.” 7\\nJudgment as a matter of law is proper if “a party has been fully heard on an\\nissue during a jury trial and . . . a reasonable jury would not have a legally\\nsufficient evidentiary basis to find for the party on that issue.” 8\\n “We review all the evidence in the record in the light most favorable to\\nthe nonmoving party and draw all reasonable inferences in favor of the\\nnonmoving party; we do not make credibility determinations or weigh the\\nevidence.” 9 We “cannot reverse a denial of a motion for judgment as a matter\\nof law unless the jury’s factual findings are not supported by substantial\\nevidence, or if the legal conclusions implied from the jury’s verdict cannot in\\nlaw be supported by those findings.” 10 In other words, the party moving for\\njudgment as a matter of law can prevail only “if the facts and inferences point\\nso strongly and overwhelmingly in favor of the moving party that reasonable\\njurors could not have arrived at a contrary verdict.” 11 Although our review is\\nde novo, “[a]fter a jury trial, [the] standard of review is especially deferential.” 12\\n 3. ERISA § 502(a)(1)(B) Claims\\n “On appeal from a bench trial, this court review[s] the factual findings of\\nthe trial court for clear error and conclusions of law de novo,” applying the\\n\\n\\n\\n\\n 7 Abraham v. Alpha Chi Omega, 708 F.3d 614, 620 (5th Cir. 2013) (citing Ill. Cent.\\nR.R. Co. v. Guy, 682 F.3d 381, 392–93 (5th Cir. 2012)).\\n 8 FED R. CIV. P. 50(a).\\n 9 Homoki v. Conversion Servs., Inc., 717 F.3d 388, 395 (5th Cir. 2013) (citing Poliner\\n\\nv. Tex. Health Sys., 537 F.3d 368, 376 (5th Cir. 2008)).\\n 10 OneBeacon Ins. Co. v. T. Wade Welch & Assocs., 841 F.3d 669, 676 (5th Cir. 2016)\\n\\n(quoting Am. Home Assurance Co. v. United Space All., LLC, 378 F.3d 482, 488 (5th Cir.\\n2004)).\\n 11 Homoki, 717 F.3d at 395 (citing Poliner, 537 F.3d at 376).\\n 12 Abraham, 708 F.3d at 620 (second alteration in original) (quoting Brown v.\\n\\nSudduth, 675 F.3d 472, 477 (5th Cir. 2012)).\\n 7\\n\\n Case: 17-10736 Document: 00514879053 Page: 8 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\nsame standard as the district court. 13 Because the plans at issue grant\\nBCBSLA discretion to determine eligibility for plan benefits and construe the\\nterms of the plans, we apply the abuse of discretion standard. 14 Thus, if\\nBCBSLA’s “decision is supported by substantial evidence and is not arbitrary\\nand capricious, it must prevail.” 15\\n\\n III. DISCUSSION\\nA. District Court’s Grant of a New Trial\\n In the first trial, the court instructed the jury that BCBSLA was liable\\non Encompass’s non-ERISA claims if it had arbitrarily and capriciously denied\\nclaims for benefits:\\n The burden is on Encompass to prove that BCBS Louisiana had\\n sufficient proof that payment on a claim was due and that the\\n claim was capriciously and arbitrarily denied by BCBS Louisiana.\\n An insurer is arbitrary and capricious when it does not act in a\\n reasonable manner based on the facts known at the time of the\\n decision.\\nIn its motion for a new trial, Encompass successfully argued that this charge\\nhad erroneously imported the arbitrary-and-capricious standard and should,\\ninstead, have simply stated the Louisiana elements of contract.\\n 1. New Trial on the Contract Claims\\n BCBSLA contends that the original charge was correct, and the second\\ntrial should never have happened. It says that the Louisiana Prompt Payment\\nStatute, 16 not the general contract statute, governs an insurer’s breach of a\\n\\n\\n\\n 13 Conn. Gen. Life Ins. Co. v. Humble Surgical Hosp., L.L.C., 878 F.3d 478, 483 (5th\\nCir. 2017) (alteration in original) (quoting George v. Reliance Standard Life Ins. Co., 776 F.3d\\n349, 352 (5th Cir. 2015)).\\n 14 Id. (citing Vega v. Nat’l Life Ins. Servs., Inc., 188 F.3d 287, 295 (5th Cir. 1999) (en\\n\\nbanc), overruled on other grounds by Metro. Life Ins. Co. v. Glenn, 554 U.S. 105, 115–19\\n(2008)).\\n 15 Singletary v. United Parcel Serv., Inc., 828 F.3d 342, 347 (5th Cir. 2016) (quoting\\n\\nCorry v. Liberty Life Assurance Co. of Boston, 499 F.3d 389, 397 (5th Cir. 2007)).\\n 16 LA. STAT. ANN. § 22:1821.\\n\\n 8\\n\\n Case: 17-10736 Document: 00514879053 Page: 9 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\nhealth insurance contract. The Prompt Payment Statute imposes penalties on\\ninsurers who do not, within 30 days, pay any claim that does not present\\nreasonable grounds for denial:\\n All claims arising under the terms of health and accident contracts\\n issued in this state, except as provided in Subsection B of this\\n Section, shall be paid not more than thirty days from the date upon\\n which written notice and proof of claim, in the form required by\\n the terms of the policy, are furnished to the insurer unless just and\\n reasonable grounds, such as would put a reasonable and prudent\\n businessman on his guard, exist. . . . Failure to comply with the\\n provisions of this Section shall subject the insurer to a penalty . . .\\n together with attorney fees to be determined by the court. 17\\nAlthough the words “arbitrary and capricious” do not appear in this section,\\nLouisiana courts have adopted that standard for insurer liability. 18 This is\\nbecause the statute is “penal in nature” and must be “strictly construed.” 19\\nBCBSLA says that because the statute governs “[a]ll claims arising under the\\nterms of health and accident contracts issued in this state,” 20 and specific\\nstatutes trump general ones, 21 this section provides the appropriate standard\\nof liability for Encompass’s contract claims.\\n BCBSLA also contends that Encompass itself invoked the Prompt\\nPayment Statute for its non-ERISA contract claims. Besides contract damages,\\nEncompass’s operative complaint demanded attorney’s fees, costs, and\\n“statutory penalties under Texas and Louisiana law requiring the prompt\\npayment of claims by insurance carriers.” And in its submission for the joint\\n\\n\\n\\n\\n 17 Id. § 22:1821(A).\\n 18 Stewart v. Calcasieu Par. Sch. Bd., 933 So. 2d 797, 801 (La. Ct. App. 2006)\\n(interpreting predecessor LA. STAT. ANN. § 22:657).\\n 19 Id. (quoting Marien v. Gen. Ins. Co. of Am., 836 So. 2d 239, 249 (La. Ct. App. 2002)).\\n 20 LA. STAT. ANN. § 22:1821.\\n 21 Cf., e.g., Pumphrey v. City of New Orleans, 925 So. 2d 1202, 1210 (La. 2006) (“[T]he\\n\\nstatute specifically directed to the matter at issue must prevail as an exception to the statute\\nmore general in character.” (citing Kennedy v. Kennedy, 699 So. 2d 351, 358 (La. 1996))).\\n 9\\n\\n Case: 17-10736 Document: 00514879053 Page: 10 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\npretrial order, Encompass listed “[w]hether BCBSLA abused its discretion by\\ndenying Encompass’s claims” as a contested legal issue.\\n Neither of these theories can rehabilitate the first jury charge. Louisiana\\ncontract law governs Encompass’s claims for benefits under non-ERISA plans\\nbecause, although it is true that the Prompt Payment Statute applies to all\\nLouisiana health insurance contracts, “[u]nder Louisiana law, the cause of\\naction under [§ 22:1821] is separate and distinct from the cause of action for\\nthe breach of the insurance contract.” 22 Encompass alleged a Louisiana\\ncontract claim. So even if it also alleged a Prompt Payment Statute claim, it\\nhad the right to a correct jury instruction on the contract claim. 23 This is\\nparticularly true where, as here, it is easier to prove that the defendant\\nbreached a contract than that it did so arbitrarily and capriciously.\\n BCBSLA has another independent argument. It contends that the first\\njury charge was correct because the insurance plans, by their terms, granted\\nBCBSLA discretion in choosing whether to allow or deny a claim. And in\\nanalogous contexts, “abuse of discretion” and “arbitrary and capricious” are\\nlegally equivalent. 24 Thus, BCBSLA says that the jury was properly instructed\\nto find contract liability only if BCBSLA had arbitrarily and capriciously\\ndenied a claim.\\n\\n\\n 22 Hymel v. HMO of La., Inc., 951 So. 2d 187, 199 (La. Ct. App. 2006) (citing Cramer\\nv. Ass’n Life Ins. Co., Inc., 563 So. 2d 267, 275 (La. Ct. App.), rev’d on other grounds, 569 So.\\n2d 533 (La. 1990)) (interpreting predecessor LA. STAT. ANN. § 22:657); see Cantrelle Fence &\\nSupply Co., Inc. v. Allstate Ins. Co., 515 So. 2d 1074, 1079 (La. 1987) (holding that cause of\\naction under analogous insurance penalty statute was “separate and distinct from the\\nobligation arising out of the contractual relationship under the insurance policy”).\\n 23 See Aero Int’l, Inc. v. U.S. Fire Ins. Co., 713 F.2d 1106, 1113 (5th Cir. 1983) (“[The\\n\\nparty] was entitled to have the critical issues bearing upon its liability ‘submitted to and\\nanswered by the jury upon a clear and proper charge.’” (quoting NMS Indus., Inc. v. Premium\\nCorp. of Am., 451 F.2d 542, 545 (5th Cir. 1971))).\\n 24 See Anderson v. Cytec Indus., Inc., 619 F.3d 505, 512 (5th Cir. 2010) (“[T]here is only\\n\\na semantic, not a substantive, difference between the arbitrary and capricious and the abuse\\nof discretion standards in the ERISA benefits review context.” (quoting Meditrust Fin. Servs.\\nCorp. v. Sterling Chems., Inc., 168 F.3d 211, 214 (5th Cir. 1999))).\\n 10\\n\\n Case: 17-10736 Document: 00514879053 Page: 11 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\n This theory is not quite correct. BCBSLA argues that the first jury\\ncharge properly included an interpretation of the contracts. But the district\\ncourt rejected this argument when it granted a new trial, holding in effect that\\nthe interpretation was not supported by Louisiana law. 25 We agree. No cited\\nLouisiana authority supports an arbitrary and capricious standard for breach\\nof health insurance contracts—even those that grant discretion to the insurer.\\nAnd the district court has discretion of its own to either interpret contract\\nterms as a matter of law or leave them to the factfinder. 26 “Although the\\ninterpretation of a contract is normally a question of law for the Court, that\\ninterpretation frequently depends heavily on the resolution of factual disputes.\\nAnd it is the function of the trier of fact to resolve such factual disputes.” 27\\n In short, charging the jury with an incorrect standard of liability\\nsupports granting a new trial. 28 And the jury indicated confusion from the\\nimproper instruction. 29 Its note to the court shows that the erroneous legal\\nstandard was front and center in deliberations: “Can you clearly define\\nArbitrary and Capricious in the eyes of the court[?]” 30 The district court did not\\nabuse its discretion when it granted a new trial on Encompass’s contract\\nclaims.\\n\\n\\n\\n 25 See Hymel, 951 So. 2d at 199 (affirming general contract law jury instruction for\\ncontract claim and separate instruction for Prompt Payment Statute claim).\\n 26 See Cook Indus., Inc. v. Cmty. Grain, Inc., 614 F.2d 978, 980 (5th Cir. 1980)\\n\\n(affirming district court’s decision not to interpret contract as matter of law).\\n 27 Id. (citing Gen. Wholesale Beer Co. v. Theodore Hamm Co., 567 F.2d 311, 313 (5th\\n\\nCir. 1978)).\\n 28 See Pinkerton v. Spellings, 529 F.3d 513, 519 (5th Cir. 2008) (granting new trial\\n\\nbecause jury instruction wrongly imposed elevated standard for liability); Aero, 713 F.2d at\\n1113 (“A new trial is the appropriate remedy for prejudicial errors in jury instructions.”\\n(citing NMS Indus., Inc. v. Premium Corp. of Am., Inc., 451 F.2d 542, 545 (5th Cir. 1971);\\nPhillips v. State Farm Mut. Auto. Ins. Co., 437 F.2d 365 (5th Cir. 1971))).\\n 29 See, e.g., Aero, 713 F.2d at 1113 n.6 (citing jury note as indication of jury confusion).\\n 30 The court responded by identifying this sentence in the jury charge: “An insurer is\\n\\narbitrary and capricious when it does not act in a reasonable manner based on the facts\\nknown at the time of the decision.”\\n 11\\n\\n Case: 17-10736 Document: 00514879053 Page: 12 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\n 2. New Trial on the Tort Claims\\n The district court held that Encompass’s tort claims should also be\\nretried because they were related to the mischarged contract claims. In the\\ndistrict court’s view, breach of the contracts was a basis of the tort claims.\\nBCBSLA disputes this. It contends that the jury could not possibly have been\\nconfused by overlap of tort and contract issues because it never reached the\\nmerits of the tort claims. Indeed, the jury answered “no” to whether Encompass\\ncould invoke contra non valentem to toll prescription for the tort claims,\\npreventing it from reaching the tort merits questions on the verdict form.\\n Under Federal Rule of Civil Procedure 59(a), the district court may\\n“grant a new trial on all or some of the issues.” “[P]artial new trials should not\\nbe resorted to unless it appears that the issue to be retried is so distinct and\\nseparable from the others that a trial of it alone may be had without\\ninjustice.” 31 “Therefore, when the issues subject to retrial are so interwoven\\nwith other issues in the case that they ‘cannot be submitted to the jury\\nindependently . . . without confusion and uncertainty, which would amount to\\na denial of a fair trial,’ then it is proper to grant a new trial on all of the issues\\nraised.” 32 In addition to considering “interdependence of [the] issues,” we also\\nconsider “an overlapping of proof” relevant to those issues. 33\\n Under this standard, the district court did not abuse its discretion by\\ngranting a new trial on the tort claims. Whether Encompass’s claims for\\nbenefits should have been paid was a common issue between the contract and\\ntort claims—it affects the tort claims because it affects the truth or falsity of\\n\\n\\n\\n\\n 31Anderson v. Siemens Corp., 335 F.3d 466, 475 (5th Cir. 2003) (quoting Colonial\\nLeasing of New England, Inc. v. Logistics Control Int’l, 770 F.2d 479, 481 (5th Cir. 1985)).\\n 32 Colonial Leasing, 770 F.2d at 481 (ellipsis in original) (quoting Gasoline Prods. Co.\\n\\nv. Champlin Ref. Co., 283 U.S. 494, 500 (1931)).\\n 33 Id.\\n\\n 12\\n\\n Case: 17-10736 Document: 00514879053 Page: 13 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\nthe Cantrell letter. 34 And proof of BCBSLA’s internal decision making may be\\nrelevant to both whether it performed its contractual duties and whether it\\ndefamed or tortiously interfered with Encompass. 35\\nB. Judgment as a Matter of Law on Encompass’s Tort Claims—\\n Prescription and Contra Non Valentem\\n BCBSLA says that the district court should have granted its renewed\\nmotion for judgment as a matter of law based on prescription. It is undisputed\\nthat the applicable prescriptive period for Encompass’s tort claims is one year,\\nand that over a year passed between Encompass receiving the Cantrell letter\\nand first claiming defamation and tortious interference. But the jury in the\\nsecond trial found that prescription was suspended under the doctrine of contra\\nnon valentem.\\n Under Louisiana law, “[t]he defendant has the initial burden of proving\\nthat a tort claim has prescribed, but if the defendant shows that one year has\\npassed between the tortious acts and the filing of the lawsuit, then the burden\\nshifts to the plaintiff to prove an exception to prescription.” 36 “[C]ontra non\\nvalentem prevents the running of liberative prescription . . . where the cause\\nof action is neither known nor reasonably knowable by the plaintiff even\\nthough plaintiff’s ignorance is not induced by the defendant.” 37 Under this\\nstandard, “[c]onstructive knowledge is whatever notice is enough to excite\\nattention and put the injured party on guard and call for inquiry.” 38 “[T]his\\nprinciple will not exempt the plaintiff’s claim from the running of prescription\\n\\n\\n\\n 34 See Anderson, 335 F.3d at 475.\\n 35 See Colonial Leasing, 770 F.2d at 481.\\n 36 Terrebonne Par. Sch. Bd. v. Columbia Gulf Transmission Co., 290 F.3d 303, 320\\n\\n(5th Cir. 2002) (citing Miley v. Consol. Gravity Drainage Dist. No. 1, 642 So. 2d 693, 696 (La.\\nCt. App. 1994); Dixon v. Houck, 466 So. 2d 57, 59 (La. Ct. App. 1985)).\\n 37 Marin v. Exxon Mobil Corp., 48 So. 3d 234, 245 (La. 2010) (citing Plaquemines Par.\\n\\nComm’n Council v. Delta Dev. Co., 502 So. 2d 1034 (La. 1987)).\\n 38 Id. at 246 n.12 (quoting Campo v. Correa, 828 So.2d 502, 510–11 (La. 2002)).\\n\\n 13\\n\\n Case: 17-10736 Document: 00514879053 Page: 14 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\nif his ignorance is attributable to his own wilfulness or neglect; that is, a\\nplaintiff will be deemed to know what he could by reasonable diligence have\\nlearned.” 39\\n The Supreme Court of Louisiana has not evaluated contra non valentem\\nfor a defamation or false-statement claim. So “we must make an ‘Erie guess’\\nand determine as best we can what the highest court of the state would be most\\nlikely to decide.” 40 We may look to the decisions of intermediate state courts\\nfor guidance. “Indeed, ‘a decision by an intermediate appellate state court is a\\ndatum for ascertaining state law which is not to be disregarded by a federal\\ncourt unless it is convinced by other persuasive data that the highest court of\\nthe state would decide otherwise.’” 41\\n BCBSLA maintains that contra non valentem does not apply as a matter\\nof law. Encompass had a copy of the Cantrell Letter in 2010. The letter\\nimmediately caused Encompass to confer with counsel and seek clarification\\nfrom BCBSLA. But Encompass waited until 2013 to allege tort claims. And in\\nBCBSLA’s view, Encompass is in a dilemma: Encompass’s contract theory,\\nwhich it was pursuing around the same time it received the Cantrell Letter,\\nrequires the letter to be wrong about coverage. But Encompass’s contra non\\nvalentem theory only works if Encompass was ignorant of the letter’s falsity.\\n Encompass contends that the Cantrell Letter falsified BCBSLA internal\\npolicies, which it could not discover until 2013 despite diligent inquiry.\\nAlthough some statements in the letter were independently verifiable,\\nEncompass says others were simultaneously false, damaging, and opaque to\\n\\n\\n\\n 39 Id. at 246 (quoting Renfroe v. State ex rel. Dep’t of Transp. & Dev., 809 So. 2d 947,\\n953 (La. 2002)).\\n 40 Terrebonne Par., 290 F.3d at 317 (citing Barfield v. Madison County, 212 F.3d 269,\\n\\n271–72 (5th Cir. 2000)).\\n 41 Id. (quoting First Nat’l Bank of Durant v. Trans Terra Corp., 142 F.3d 802, 809 (5th\\n\\nCir. 1998)).\\n 14\\n\\n Case: 17-10736 Document: 00514879053 Page: 15 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\noutsiders. Encompass argued that the letter misrepresented Encompass’s\\n“eligib[ility] to participate in the Blue Cross networks” and “eligib[ility] for\\nbenefit payment.” Eligibility to be in the network, as distinct from present\\nnetwork status or plan coverage for a service, was a matter of BCBSLA policy.\\nAnd according to Encompass, “eligib[ility]” for payment was too. Encompass\\nsays these statements damaged its business by discouraging doctors from\\nworking with it. Encompass also says its diligence to investigate the letter—\\ncalling Cantrell three times in 2010 and leaving messages without response—\\nwas reasonable under the circumstances.\\n We believe the Supreme Court of Louisiana would hold that contra non\\nvalentem was supported by the evidence here. The issue is close and we are\\nmindful of the “especially deferential” standard of review for the jury verdict. 42\\nBCBSLA challenges only the sufficiency of the evidence, not the jury\\ninstruction. The district court rejected BCBSLA’s argument when it denied\\njudgment as a matter of law. We do so as well. Our dissenting colleague takes\\na broader view of constructive notice and a stricter one of the required\\ndiligence. But, in this instance, we find no Louisiana case standing directly\\nagainst contra non valentem and some cases that support it, especially given\\nour standard of review.\\n Louisiana intermediate appellate court decisions show that contra non\\nvalentem suspends prescription for defamation and other false-statement\\nclaims if a reasonably diligent plaintiff knows about the adverse statement but\\nhas not discovered it is false. In Quixx, for example, the insurer plaintiff\\nreceived applications containing false statements, but prescription did not\\nbegin to run until it discovered facts inconsistent with those statements. 43 (The\\n\\n\\n\\n 42Abraham, 708 F.3d at 620 (quoting Brown, 675 F.3d at 477).\\n 43Nat’l Council on Comp. Ins. v. Quixx Temp. Servs., Inc., 665 So. 2d 120, 123–24 (La.\\nCt. App. 1995).\\n 15\\n\\n Case: 17-10736 Document: 00514879053 Page: 16 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\nclaims were prescribed anyway because the insurer waited more than a year\\nto file suit. 44) In another case, Simmons, the plaintiffs argued that contra non\\nvalentem suspended prescription of a tortious interference claim until they\\ndiscovered that the defendant’s financial statements were falsified. 45 The court\\nagreed. The plaintiffs did not have constructive knowledge of falsity until\\nreceiving disclosures during litigation, even though their dispute with the\\ndefendants began over a year earlier. 46 These cases show that a plaintiff can\\nbe aware of a statement without having constructive knowledge of its falsity.\\nThey also show that a plaintiff need not file suit just because an adverse party\\npublicizes unfavorable statements that are not immediately verifiable.\\n Cases setting a stricter diligence bar are distinguishable. In Rozas the\\nplaintiff, a doctor, argued that contra non valentem suspended prescription as\\nlong as his former employer withheld a personnel file that defamed him as\\nclinically incompetent. 47 The court disagreed, because the plaintiff’s own lack\\nof diligence kept him from getting the file. The court said he should have taken\\nmeasures “beyond making one telephone call to a secretary.” 48 This initially\\nseems comparable to Encompass’s diligence. But Rozas was in a different\\nposition. He already knew the defamatory statements’ general content and\\nfalsity: The defendant had rated him clinically incompetent. 49 This weighed\\nheavily in the court’s analysis that he had constructive knowledge of a cause\\nof action. “[P]laintiff had sufficient facts to make him aware that he potentially\\nhad a claim against L.S.U. in 1980 when he learned that L.S.U. had given him\\n\\n\\n\\n\\n 44 Id.\\n 45 Simmons v. Templeton, 723 So. 2d 1009, 1012 (La. Ct. App. 1998).\\n 46 Id. at 1011–12.\\n 47 Rozas v. Dep’t of Health & Human Res., 522 So. 2d 1195, 1196–97 (La. Ct. App.\\n\\n1988).\\n 48 Id. at 1197.\\n 49 Id.\\n 16\\n\\n Case: 17-10736 Document: 00514879053 Page: 17 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\na poor clinical evaluation.” 50 But here the falsity concerned BCBSLA’s internal\\npolicies, and Encompass did not discover it until 2013.\\n And the appellate cases Greenblatt and Neyrey are distinguishable\\nbecause the plaintiffs exercised no diligence at all. 51 These are easier cases\\nwhere the plaintiffs would have known about a cause of action if they took any\\ntimely action to obtain the defendants’ adverse statements. The federal district\\ncourt case Safford is similar. 52 Here, in contrast, Encompass sought\\nclarification about the Cantrell Letter multiple times.\\n Cases stating that consulting with counsel shows constructive\\nknowledge of a claim are also distinguishable. These cases generally involved\\npersonal injuries where consulting counsel logically showed awareness of the\\ncause of action. 53 But here the parties were in a business dispute with many\\npotential legal theories. Consulting counsel about one legal injury does not\\nshow that a party knew or should have known about other legal injuries that\\nare based on different facts. 54 This is especially so given Encompass’s position\\nthat the falsity was known only to BCBSLA.\\n Encompass can escape the posited tort-contract dilemma without\\ncontradiction. Encompass says that BCBSLA breached contracts by refusing\\nto pay covered benefits and committed torts by spreading related statements\\n\\n\\n 50 Id.\\n 51 Greenblatt v. Payne, 929 So. 2d 193, 196 (La. Ct. App. 2006); Neyrey v. Lebrun, 309\\nSo. 2d 722, 723 (La. Ct. App. 1975).\\n 52 Safford v. PaineWebber, Inc., 730 F. Supp. 15, 18 (E.D. La. 1990) (holding contra\\n\\nnon valentem inapplicable because defamatory statements were available at plaintiff’s\\nrequest).\\n 53 See Med. Review Panel Proceeding of Williams v. Lewis, 17 So. 3d 26, 30 (La. Ct.\\n\\nApp. 2009) (medical malpractice for surgery complication); Derrick v. Yamaha Power Sports\\nof New Orleans, 850 So. 2d 829, 833 (La. Ct. App. 2003) (workers compensation for gunshot\\nwound to hand); Clofer v. Celotex Corp., 528 So. 2d 1074, 1076 (La. Ct. App. 1988) (suit against\\nformer employer for lung damage).\\n 54 See, e.g., Simmons, 723 So. 2d at 1011–12 (explaining that transaction was in 1986,\\n\\nlitigation began in November 1987, falsity was discovered in March 1989, and prescription\\ndid not begin to run until March 1989).\\n 17\\n\\n Case: 17-10736 Document: 00514879053 Page: 18 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\nthat were false. 55 It is not implausible that Encompass immediately considered\\nthe Cantrell Letter a breach of contract but only later knew the other\\nstatements might be false. Not every anticipatory breach of contract is tortious.\\nConsider: In a garden-variety defamation case, the truth or falsity of the\\nstatement is readily knowable to the plaintiff—because it is about the\\nplaintiff. 56 Here, in contrast, Encompass says that BCBSLA defamed it by\\nmaking false statements about Encompass’s status under BCBSLA’s own\\npolicies. These policies were opaque to Encompass when it received the letter.\\nAnd Encompass’s inquiries to BCBSLA do not show constructive knowledge\\neither. There is no inconsistency in investigating the letter for the ongoing\\ncoverage dispute but not knowing it contained false statements.\\n Encompass’s status as a sophisticated corporation does not change this.\\nThe Supreme Court of Louisiana teaches that the proper “blueprint” to\\nevaluate reasonable delay for contra non valentem is “looking to the record for\\nevidence of facts within plaintiff’s knowledge and then examining the\\nreasonableness of plaintiff’s inaction in light of those facts, considering\\nplaintiff’s education, intelligence and the nature of defendant’s conduct.” 57 The\\ncircumstances of each case determine the applicability of the doctrine. 58 Here\\nthe jury heard evidence of each blueprint factor.\\n Some evidence showed that in 2010 Encompass knew the Cantrell Letter\\nstated unfavorable BCBSLA policies but not that those statements were false.\\nSome evidence also showed that BCBSLA’s conduct included misstating its\\n\\n\\n\\n 55 Cf. Marshall Invs. Corp. v. R.P. Carbone Co., No. 05-6486, 2006 WL 2644959, at *5\\n(E.D. La. Sept. 13, 2006) (malicious statement as element of tortious interference with\\nbusiness relations); Costello v. Hardy, 864 So. 2d 129, 139 (La. 2004) (false statement as\\nelement of defamation).\\n 56 See, e.g., Safford, 730 F. Supp. at 16–17 (evaluating alleged defamatory statement\\n\\nthat plaintiff engaged in sexual misconduct).\\n 57 Wells, 89 So. 3d at 1151.\\n 58 Id. at 1154.\\n\\n 18\\n\\n Case: 17-10736 Document: 00514879053 Page: 19 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\npolicies and refusing to clarify things. And some evidence showed that\\nEncompass was a corporation advised by counsel. So the jury had sufficient\\nevidence to assess all the factors that Louisiana law considers. 59 It reached a\\n“Yes” verdict on whether contra non valentem applied. In reviewing denial of\\njudgment as a matter of law, we may not reweigh the evidence. 60 Drawing all\\ninferences in favor of Encompass, as we must, the application of contra non\\nvalentem was not wrong as a matter of law. 61\\nC. Encompass’s ERISA Claims\\n ERISA aims to promote the interests of plan participants and their\\nbeneficiaries and to “protect contractually defined benefits.” 62 ERISA\\nenshrines a patient’s right to the “full and fair review” of her claim. 63 As a\\nresult, § 502(a)(1)(B) permits a plan participant to sue to “recover benefits due\\nto him under the terms of his plan, to enforce his rights under the terms of the\\nplan, or to clarify his rights to future benefits under the terms of the plan.” 64\\nHere, Encompass contends that it is an assignee entitled to enforce patients’\\nrights to benefits under BCBSLA plans. BCBSLA challenges Encompass’s\\nright to advance claims for benefits, as well as the district court’s ultimate\\nconclusion that BCBSLA abused its discretion in administering the plans.\\n 1. Anti-Assignment Provisions\\n BCBSLA says that, under the plans’ anti-assignment provisions,\\nEncompass lacked derivative standing to sue for benefits. The district court\\nfound that BCBSLA waived the anti-assignment provisions because it made\\n\\n\\n\\n 59 Id. at 1151.\\n 60 See Homoki, 717 F.3d at 395.\\n 61 See id.\\n 62 N. Cypress Med. Ctr. Operating Co., Ltd. v. Cigna Healthcare (NCMC), 781 F.3d\\n\\n182, 194 (5th Cir. 2015) (quoting Firestone Tire & Rubber Co. v. Bruch, 489 U.S. 101, 113–14\\n(1989)).\\n 63 29 U.S.C. § 1133(2).\\n 64 Id. § 1132(a)(1)(B).\\n\\n 19\\n\\n Case: 17-10736 Document: 00514879053 Page: 20 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\npayments to, and communicated with, Encompass on at least some claims.\\nBCBSLA’s only direct challenge to this conclusion is that Encompass did not\\noffer a jury charge on waiver. To the extent BCBSLA argues that waiver could\\nonly have been found by the jury, we disagree. It is well known that ERISA\\nclaims are the statutory cousins of equitable actions and so are tried to the\\ncourt. 65 Waiver of the anti-assignment clauses—a related issue that is itself\\nequitable—was here also properly decided by the district court. 66 So the anti-\\nassignment clauses do not frustrate Encompass’s recovery on ERISA claims.\\n 2. Contractual Limitations Periods\\n BCBSLA also contends that the plans’ 15-month limitations provisions\\nbar some of Encompass’s claims. 67 ERISA § 502(a)(1)(B) contains no statute of\\nlimitations, but the parties are free to agree to a reasonable limitations\\nperiod. 68 The district court held that the contractual limitations provisions\\nhere were unenforceable across the board because BCBSLA never gave notice\\nof them to Encompass. It cited decisions from other circuits holding that, based\\non ERISA’s implementing regulations, notice is required for similar provisions\\nto be enforceable. 69 BCBSLA does not appear to dispute this notice theory. As\\n\\n\\n 65 Calamia v. Spivey, 632 F.2d 1235, 1237 (5th Cir. Unit A 1980) (“[S]imilar claims\\nwere previously considered equitable and . . . the kind of determination required—whether\\nthe pension fund acted arbitrarily and capriciously—was one traditionally performed by\\njudges.” (citing Wardle v. Cent. States, Se. & Sw. Areas Pension Fund, 627 F.2d 820, 829–30\\n(7th Cir. 1980))).\\n 66 See FED. R. CIV. P. 39(a) (“The trial on all issues so demanded must be by jury\\n\\nunless: . . . the court, on motion or on its own, finds that on some or all of those issues there\\nis no federal right to a jury trial.”); Austin v. Shalala, 994 F.2d 1170, 1177 n.7 (5th Cir. 1993)\\n(explaining that an equitable defense—even to a legal claim—is tried to the court); Reg’l\\nProps., Inc. v. Fin. & Real Estate Consulting Co., 752 F.2d 178, 182–83 (5th Cir. 1985)\\n(holding under Texas law that waiver is equitable defense).\\n 67 BCBSLA maintains that its October 4, 2010 demand letter placed Encompass on\\n\\nnotice that its claims would be denied. Encompass waited over 15 months from this date to\\nfile suit. So BCBSLA contends that all Encompass claims submitted before October 4, 2010\\nare barred by limitations.\\n 68 Heimeshoff v. Hartford Life & Accident Ins. Co., 571 U.S. 99, 105–06 (2013).\\n 69 See Santana-Diaz v. Metro. Life Ins. Co., 816 F.3d 172, 179–82 (1st Cir. 2016) (citing\\n\\n29 C.F.R. § 2560.503–1(g)(1)(iv) for proposition that administrator must provide notice of\\n 20\\n\\n Case: 17-10736 Document: 00514879053 Page: 21 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\na result, we do not disturb the district court’s conclusion that the contractual\\nlimitations provisions are unenforceable.\\n 3. Abuse of Discretion\\n We now review the merits of Encompass’s ERISA claims. To determine\\nwhether an administrator abused its discretion in construing a plan’s terms,\\nwe analyze its plan interpretation in two steps. 70 First, was BCBSLA’s reading\\n“legally correct”? 71 ERISA plans must be written “to be understood by the\\naverage plan participant,” 72 so plans “are interpreted in their ordinary and\\npopular sense as would a person of average intelligence and experience.” 73 The\\n“most important factor to consider” is whether BCBSLA’s “interpretation is\\nconsistent with a fair reading of the plan[s].” 74 If so, the inquiry ends, and there\\nwas no abuse of discretion. 75 Otherwise, the court “must then determine\\nwhether [BCBSLA’s] decision was an abuse of discretion.” 76 “[T]his court may\\nbypass, without deciding, the issue whether the Plan Administrator’s denial\\nwas legally correct, reviewing only whether the Plan Administrator abused its\\ndiscretion in denying the claim if that can be more readily determined.” 77\\n In the second step—deciding whether BCBSLA abused its discretion—\\nthe court considers “(1) the internal consistency of the plan under the\\nadministrator’s interpretation, (2) any relevant regulations formulated by the\\n\\n\\nlimitations period when denying benefits); Mirza v. Ins. Adm’r of Am., Inc., 800 F.3d 129,\\n137–38 (3d Cir. 2015) (same); Moyer v. Metro. Life Ins. Co., 762 F.3d 503, 507 (6th Cir. 2014)\\n(same).\\n 70 Humble Surgical Hosp., 878 F.3d at 483; NCMC, 781 F.3d at 195 (citing Stone v.\\n\\nUNOCAL Termination Allowance Plan, 570 F.3d 252, 257 (5th Cir. 2009)).\\n 71 Humble Surgical Hosp., 878 F.3d at 483 (quoting NCMC, 781 F.3d at 195).\\n 72 29 U.S.C. § 1022(a).\\n 73 NCMC, 781 F.3d at 195 (quoting Stone, 570 F.3d at 260).\\n 74 Id. at 195 (alteration in original) (quoting Crowell v. Shell Oil Co., 541 F.3d 295,\\n\\n313 (5th Cir. 2008)).\\n 75 Humble Surgical Hosp., 878 F.3d at 483.\\n 76 Id. (quoting Stone, 570 F.3d at 257).\\n 77 McCorkle v. Metro. Life Ins. Co., 757 F.3d 452, 457 n.10 (5th Cir. 2014) (alterations\\n\\nand internal quotation marks omitted).\\n 21\\n\\n Case: 17-10736 Document: 00514879053 Page: 22 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\nappropriate administrative agencies, and (3) the factual background of the\\ndetermination and any inferences of lack of good faith.” 78 “In applying the\\nabuse of discretion standard, we analyze whether the plan administrator acted\\narbitrarily or capriciously.” 79\\n Here, the district court only addressed the second step—whether\\nBCBSLA abused its discretion. We take the same approach. 80 This is\\nappropriate because all agree that Encompass’s services were covered under\\nthe plans, and the only dispute is whether Encompass’s claims are\\n“duplicative” of other providers.\\n BCBSLA paid doctors a Global Fee for all services related to surgeries\\nperformed at their offices. The Global Fee compensated a doctor for both his\\nprofessional services and the use of his facility. But when surgery was done at\\na hospital or ASC, BCBSLA made separate payments to those providers to\\ncompensate for use of their facilities and services. In BCBSLA’s view,\\nEncompass is distinguishable from hospitals and ASCs because it is only a\\nservice provider, not a physical facility. And for surgery at a doctor’s office,\\nBCBSLA’s fee already included compensation for both his professional services\\nand a facility. Thus, according to BCBSLA, any other payment would be\\nduplicative.\\n This approach is not internally consistent. BCBSLA admits that the\\nplans cover services like Encompass’s, but cites no plan language authorizing\\nit to limit payment based on who provided the service. 81 Nor does BCBSLA\\n\\n\\n 78 Wildbur v. ARCO Chem. Co., 974 F.2d 631, 638 (5th Cir. 1992) (citing Batchelor v.\\nInt’l Bhd. of Elec. Workers Local 861 Pension & Ret. Fund, 877 F.2d 441, 445–48 (5th Cir.\\n1989)).\\n 79 Bellaire Gen. Hosp. v. Blue Cross Blue Shield of Mich., 97 F.3d 822, 829 (5th Cir.\\n\\n1996) (citing Sweatman v. Commercial Union Ins. Co., 39 F.3d 594, 601 (5th Cir. 1994)).\\n 80 See, e.g., McCorkle, 757 F.3d at 457 n.10; Bellaire, 97 F.3d at 829 (finding abuse of\\n\\ndiscretion without deciding legal correctness).\\n 81 See Vega, 188 F.3d at 302 (“[W]e will not countenance a denial of a claim solely\\n\\nbecause an administrator suspects something may be awry. Although we owe deference to an\\n 22\\n\\n Case: 17-10736 Document: 00514879053 Page: 23 Date Filed: 03/19/2019\\n\\n\\n No. 17-10736\\n\\nexplain—in terms of the plan—why it may insist on a Global Fee when surgery\\nis done at a doctor’s office, but make separate payments when it is done at a\\nhospital or ASC. 82 And when BCBSLA denied Encompass’s claims, this\\narrangement was not set out in any written internal policy.\\n As for the other two abuse-of-discretion factors, we first note that the\\nfactual background of BCBSLA’s decision shows equivocation over whether to\\ndo business with Encompass, rather than a clear understanding that its claims\\nwere improper. 83 As one BCBSLA executive emailed internally, “Quite\\nhonestly, I’m not one hundred percent sure why we are not contracting with\\nthem, because I don’t believe we have a concrete policy on this provider type or\\nmaybe I missed that somewhere.” Finally, neither party cites regulations that\\nmaterially affect whether Encompass’s claims should have been paid. 84\\n In sum, BCBSLA abused its discretion by arbitrarily denying\\nEncompass’s claims for covered services, as shown by its inconsistent\\ntreatment of similar providers.\\n\\n IV. CONCLUSION\\n We AFFIRM the judgment of the district court.\\n\\n\\n\\n\\nadministrator’s reasoned decision, we owe no deference to the administrator’s unsupported\\nsuspicions.”).\\n 82 See Lain v. UNUM Life Ins. Co. of Am., 279 F.3d 337, 347 (5th Cir. 2002) (“lack of\\n\\nobjectivity” suggests abuse of discretion), overruled on other grounds by Glenn, 554 U.S. at\\n115–19.\\n 83 See Wildbur, 974 F.2d at 638.\\n 84 See id.\\n\\n 23\\n\\n Case: 17-10736 Document: 00514879053 Page: 24 Date Filed: 03/19/2019\\n\\n\\n\\n\\n No. 17-10736\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1092,"cells":{"id":{"kind":"number","value":4601852,"string":"4,601,852"},"name":{"kind":"string","value":"UNITED STATES of America, Plaintiff-Appellee, v. Daniel SALINAS, Defendant-Appellant. United States of America, Plaintiff-Appellee, v. Mark Anthony Salinas, Defendant-Appellant."},"name_abbreviation":{"kind":"string","value":"United States v. Mark Salinas"},"decision_date":{"kind":"string","value":"2019-03-20"},"docket_number":{"kind":"string","value":"18-40361; cons w/ 18-40407"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before HIGGINBOTHAM, ELROD, and HO, Circuit Judges.\", \"parties\": \"\", \"opinions\": [{\"author\": \"PER CURIAM\", \"type\": \"010combined\", \"text\": \"Case: 18-40361 Document: 00514881265 Page: 1 Date Filed: 03/20/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n\\n\\n No. 18-40361 United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n March 20, 2019\\nUNITED STATES OF AMERICA,\\n Lyle W. Cayce\\n Plaintiff – Appellee, Clerk\\n\\n\\nv.\\n\\nDANIEL SALINAS,\\n\\n Defendant – Appellant.\\n---------------------------------------------------------------------\\ncons w/ 18-40407\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff – Appellee,\\n\\nv.\\n\\nMARK ANTHONY SALINAS,\\n\\n Defendant – Appellant.\\n\\n\\n\\n\\n Appeals from the United States District Court\\n for the Southern District of Texas\\n\\f Case: 18-40361 Document: 00514881265 Page: 2 Date Filed: 03/20/2019\\n\\n\\n\\n Nos. 18-40361, 18-40407\\nBefore HIGGINBOTHAM, ELROD, and HO, Circuit Judges.\\nPER CURIAM:\\n Two brothers pleaded guilty to conspiring to transport illegal aliens\\nwithin the United States by means of a motor vehicle, in violation of 8 U.S.C.\\n§ 1324(a)(1). One of the aliens they transported died from a heart attack while\\nfleeing law enforcement. The brothers now contest their sentences, claiming\\nthat the district court improperly applied an enhancement that is imposed\\nwhen a death results from the illegal transportation of aliens. The brothers\\nassert that the death was too tenuously connected to the defendants’ conduct\\nto justify the sentencing enhancement. We reject this argument and affirm the\\nsentence.\\n I.\\n Mark Anthony Salinas entered into an agreement to smuggle illegal\\naliens, which he referred to his brother Daniel Salinas. Under the terms of the\\nagreement, Daniel would be paid $500 for each alien that Daniel smuggled,\\nand Mark would be paid a referral fee of $50 for each alien that Daniel\\ntransported.\\n Consistent with this agreement, Daniel picked the aliens up in his Chevy\\nSilverado. Police Officer Matias Barrera, on routine patrol at the time, spotted\\nthe Silverado and recognized Daniel as a suspected alien smuggler. Barrera\\nstarted to follow the truck in his patrol car. When Barrera saw Daniel run a\\nstop sign, Barrera activated his emergency lights in an attempt to conduct a\\ntraffic stop.\\n Daniel refused to stop, and a high-speed chase ensued. Barrera pursued\\nhim until Daniel drove into an empty lot and crashed into a tree. Daniel exited\\nthe truck and fled on foot. Five aliens also exited the vehicle. Barrera\\nimmediately apprehended two of them. The other three sprinted on foot into\\nnearby brush. Border Patrol agents arrived and located two of the three fleeing\\n 2\\n\\f Case: 18-40361 Document: 00514881265 Page: 3 Date Filed: 03/20/2019\\n\\n\\n\\n Nos. 18-40361, 18-40407\\naliens. The third, Pedro Martinez, became ill in the brush and was eventually\\ntransported to a hospital, where he later died. An autopsy, conducted by Dr.\\nFortansus Salinas, 1 revealed that Martinez died from “acute myocardial\\ninfarction,” the technical term for a heart attack.\\n At sentencing, the district court applied a 10-level enhancement that is\\nimposed “if any person died” in the course of “[s]muggling, [t]ransporting, or\\n[h]arboring an [u]nlawful [a]lien.” U.S.S.G. § 2L1.1. In reaching this\\nconclusion, the district court heard testimony from Dr. Salinas about the\\nautopsy. The doctor related that Martinez “had an occlusion or a clot in the\\ncoronary that led to him not being able to get oxygen to the heart itself. And\\n[the heart] undergoes a process where he starts to die. We call that myocardial\\ninfarction, which is a heart attack. It also throws him into abnormal rhythms.\\nOnce you do that, you stop the heart and it just stops functioning, usually\\ncollapse.” Dr. Salinas further elaborated that, although Martinez was just 28\\nyears old, the blockage in his arteries was something that the doctor would\\nexpect to see more frequently in people in their “30s, 40s, 50s.” Martinez had\\nother health problems, too: he had an extensive pulmonary edema—which is\\nthe collection of excess fluid in air sacs in the lungs, making it hard to\\nbreathe—that Dr. Salinas thinks started prior to the heart attack. Mr.\\nMartinez also had extensive fatty infiltration of his liver, a result of both his\\ngenetics and his diet. Dr. Salinas said he found no evidence that Mr. Martinez\\nsuffered a head injury or any scratches on his body.\\n In his testimony, Dr. Salinas shed important light on the connection\\nbetween the heart attack and Martinez’s running from law enforcement. While\\nDr. Salinas opined that it was possible for the heart attack to have happened\\n\\n\\n\\n 1 The record does not indicate any relationship between the doctor and the defendants,\\ndespite the shared last name.\\n 3\\n\\f Case: 18-40361 Document: 00514881265 Page: 4 Date Filed: 03/20/2019\\n\\n\\n\\n Nos. 18-40361, 18-40407\\nanywhere—even while Martinez was just sitting down—Dr. Salinas believed\\nthat this particular heart attack was precipitated by the intensity of the\\nsituation and the stress that running placed on Martinez’s heart. Dr. Salinas\\ntestified that “when [Martinez] started running [from law enforcement, he]\\ndemanded more work from his heart; and he just couldn’t comply, and the\\nheart couldn’t comply with it; and he collapse[d], and he die[d].” The doctor\\nexplained further, “[a]nything that will excite you or will get your heart going\\ncan give you this type of scenario.” Specifically, in response to questions, Dr.\\nSalinas explained:\\n Q: Okay. But in this particular instance, you believe that [the\\n heart attack] was pursuant to being chased?\\n A: I believe so, yes.\\n Q: That caused [Martinez’s] heart attack?\\n A: That’s correct; that’s what I believe.\\n After applying the enhancement to each defendant’s sentence, the\\ndistrict court sentenced Daniel to 100 months imprisonment, plus three years\\nof supervised release, and Mark to 78 months imprisonment, also followed by\\nthree years of supervised release. The brothers objected to the enhancement,\\nand the district court overruled. The defendants timely appealed.\\n II.\\n This court reviews the district court’s interpretation and application of\\nthe Sentencing Guidelines de novo and the district court’s findings of fact for\\nclear error. United States v. Ramos-Delgado, 763 F.3d 398, 400 (5th Cir. 2014).\\nIn deciding “whether an enhancement applies, a district court is permitted to\\ndraw reasonable inferences from the facts, and these inferences are fact-\\nfindings reviewed for clear error as well.” United States v. Caldwell, 448 F.3d\\n287, 290 (5th Cir. 2006). “Under the clearly erroneous standard, we will uphold\\na finding so long as it is ‘plausible in light of the record as a whole.’” United\\n 4\\n\\f Case: 18-40361 Document: 00514881265 Page: 5 Date Filed: 03/20/2019\\n\\n\\n\\n Nos. 18-40361, 18-40407\\nStates v. Ekanem, 555 F.3d 172, 175 (5th Cir. 2009) (quoting Caldwell, 448\\nF.3d at 290). The government “must prove sentencing enhancements by a\\npreponderance of the evidence.” United States v. Juarez, 626 F.3d 246, 251\\n(5th Cir. 2010). And we may affirm an enhancement on any ground supported\\nby the record. United States v. Jordan, 851 F.3d 393, 399 (5th Cir. 2017).\\n The Sentencing Guidelines apply an enhancement “[i]f any person died\\nor sustained bodily injury” in the course of smuggling, transporting, or\\nharboring an unlawful alien. U.S.S.G. § 2L1.1(b)(7). In the case of “death”—\\nas opposed to mere injury—that enhancement increases the offense level by\\n10. U.S.S.G. § 2L1.1(b)(7)(D). In United States v. Ramos-Delgado, we held\\nthat the defendant’s conduct must simply be the but-for cause of the death, not\\nits proximate cause. 763 F.3d at 401 (citing Burrage v. United States, 134 S.\\nCt. 881, 887–88 (2014)).\\n In interpreting the provision this way, our court observed that the\\nprovision itself “contains no causation requirement” and therefore\\nacknowledged that “we have no license to impose one.” Id. at 401. We\\nexplained that the only applicable causation requirement, therefore, is the\\ngeneral but-for causation requirement of U.S.S.G. § 1B1.3, an overarching\\nprovision that defines the circumstances that a sentencing court may consider\\nin determining whether any provision of the Guidelines applies. Id. Section\\n1B1.3 allows sentencing courts to consider harm only if it “resulted from” or\\n“was the object of” certain acts and omissions of the defendant. U.S.S.G.\\n§ 1B1.3(a)(3). The Ramos-Delgado court read the phrase “resulted from”\\naccording to its ordinary meaning, imposing a but-for causation requirement,\\n\\n\\n\\n\\n 5\\n\\f Case: 18-40361 Document: 00514881265 Page: 6 Date Filed: 03/20/2019\\n\\n\\n\\n Nos. 18-40361, 18-40407\\njust as the Supreme Court had in Burrage v. United States, 571 U.S. 204, 211\\n(2014). 2\\n But-for causation requires the government to show merely “that the\\nharm would not have occurred in the absence of—that is, but for—the\\ndefendant’s conduct.” Id. at 211 (quoting Univ. of Tex. Sw. Med. Ctr. v. Nassar,\\n570 U.S. 338, 346–47 (2013)). This is “not a difficult burden to meet.” Ramos-\\nDelgado, 763 F.3d at 402. An event might have “many but-for causes.” Id. For\\nexample, the Supreme Court has explained that a leadoff batter’s home run is\\njust one among many but-for causes of a team’s 1-to-0 victory, which resulted\\nalso from the winning team’s “skillful pitching, the coach’s decision to put the\\nleadoff batter in the lineup, and the league’s decision to schedule the game,”\\nBurrage, 571 U.S. at 212, and perhaps also from the opposing pitcher leaving\\n“his fastball hanging over the plate,” Ramos-Delgado, 763 F.3d at 402. A\\nproximate-cause inquiry would ask how directly each cause affected the final\\noutcome, but the but-for causation standard asks simply whether the outcome\\nwould have occurred in the absence of the action. Burrage, 571 U.S. at 211.\\nRamos-Delgado explains that even if an immigrant got thrown from a\\ndefendant’s truck, sprained his hand, went to the hospital because of the\\nsprain, and then died from a gas leak at the hospital, the enhancement would\\nstill apply. Ramos-Delgado, 763 F.3d at 402. It does not matter that the gas\\nleak was unforeseeable to the defendant or only tenuously connected to the\\ndefendant’s conduct.\\n\\n\\n\\n 2 At oral argument, counsel for Daniel described Burrage as holding that “when a\\ndefendant’s conduct is not . . . the independently sufficient cause of death, the defendant\\ncannot be held liable.” Counsel then suggested that Ramos-Delgado misreads Burrage.\\nCounsel’s description of Burrage omits the key language of the case’s holding. The Supreme\\nCourt in Burrage held that “at least where use of the drug distributed by the defendant is not\\nan independently sufficient cause of the victim’s death or serious bodily injury, a defendant\\ncannot be liable . . . unless such use is a but-for cause of the death or injury.” Burrage, 571\\nU.S. at 218 (emphasis added). Ramos-Delgado is fully consistent with this holding.\\n 6\\n\\f Case: 18-40361 Document: 00514881265 Page: 7 Date Filed: 03/20/2019\\n\\n\\n\\n Nos. 18-40361, 18-40407\\n Two published Fifth Circuit cases illustrate the application of this rule.\\nFirst, in Ramos-Delgado, the defendant tried to evade Border Patrol while\\ndriving a pickup truck with aliens in the truck’s bed. Id. at 400. One of the\\naliens was thrown from the truck, suffering a massive skull fracture and brain\\ninjuries from which he died. Id. We affirmed the district court’s application of\\nthe enhancement. In light of the victim’s “medical records, it [was] plausible\\nthat he died from the injuries sustained in being thrown from the bed of a\\ntruck.” Id. at 402. And because the victim would not have been thrown from\\nthe truck’s bed but for the defendant’s decision to transport the aliens in the\\nfirst place, the defendant’s conduct was a but-for cause of the death. Id.\\n Similarly, in United States v. Ruiz-Hernandez, the defendant\\ntransported an alien at night in an inner tube across a ship channel. 890 F.3d\\n202, 207–08 (5th Cir. 2018). An unlit Coast Guard vessel sped through the\\nchannel, killing the alien. Id. We held that the defendant’s conduct was a but-\\nfor cause of the death because, even though the vessel’s speed and lack of lights\\ncontributed greatly to the death, the alien would not have been in the ship’s\\npath in the absence of the defendant’s conduct. Id. at 212–13.\\n The instant case falls squarely within the reach of Ramos-Delgado and\\nRuiz-Hernandez. The district court heard extensive testimony from Dr.\\nSalinas, who concluded that this particular heart attack was triggered by\\nMartinez’s running. In light of this testimony, it was certainly “plausible” that\\nMartinez’s fatal heart attack was caused by the running. Ramos-Delgado, 763\\nF.3d at 402. The district court did not clearly err in accepting that testimony\\nand making this finding of fact. Martinez would not have run had the Salinas\\nbrothers not arranged to pick up the aliens, driven the aliens in the Silverado,\\nand crashed the Silverado into a tree with law enforcement closing in. Just as\\nin Ramos-Delgado and Ruiz-Hernandez, the Salinas brothers were fully\\nresponsible for placing the victim in a precarious position where subsequent\\n 7\\n\\f Case: 18-40361 Document: 00514881265 Page: 8 Date Filed: 03/20/2019\\n\\n\\n\\n Nos. 18-40361, 18-40407\\nbut-for causes ultimately took his life. In short: No criminal conduct, no\\nrunning. No running, no death. The defendants’ conduct was the but-for cause\\nof Martinez’s death, which is all that this sentencing enhancement requires.\\n III.\\n We are bound by precedent—both the Supreme Court’s and our own—\\nand by our fidelity to the text of the Guidelines to impose only a but-for\\ncausation requirement. Under that standard, the sentencing enhancement is\\nappropriate. For these reasons, we AFFIRM the district court’s sentence.\\n\\n\\n\\n\\n 8\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4379105/\", \"author_raw\": \"PER CURIAM\"}]}"},"judge1":{"kind":"string","value":"HIGGINBOTHAM"},"judge2":{"kind":"string","value":"ELROD"},"judge3":{"kind":"string","value":"HO"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"HIGGINBOTHAM\": \", Circuit\", \"ELROD\": \", Circuit\", \"HO\": \", Circuit\"}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4601852/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Plaintiff-Appellee, v. Daniel SALINAS, Defendant-Appellant. United States of America, Plaintiff-Appellee, v. Mark Anthony Salinas, Defendant-Appellant.\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-20\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 18-40361 Document: 00514881265 Page: 1 Date Filed: 03/20/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\n\n\n No. 18-40361 United States Court of Appeals\n Fifth Circuit\n\n FILED\n March 20, 2019\nUNITED STATES OF AMERICA,\n Lyle W. Cayce\n Plaintiff – Appellee, Clerk\n\n\nv.\n\nDANIEL SALINAS,\n\n Defendant – Appellant.\n---------------------------------------------------------------------\ncons w/ 18-40407\n\nUNITED STATES OF AMERICA,\n\n Plaintiff – Appellee,\n\nv.\n\nMARK ANTHONY SALINAS,\n\n Defendant – Appellant.\n\n\n\n\n Appeals from the United States District Court\n for the Southern District of Texas\n\f Case: 18-40361 Document: 00514881265 Page: 2 Date Filed: 03/20/2019\n\n\n\n Nos. 18-40361, 18-40407\nBefore HIGGINBOTHAM, ELROD, and HO, Circuit Judges.\nPER CURIAM:\n Two brothers pleaded guilty to conspiring to transport illegal aliens\nwithin the United States by means of a motor vehicle, in violation of 8 U.S.C.\n§ 1324(a)(1). One of the aliens they transported died from a heart attack while\nfleeing law enforcement. The brothers now contest their sentences, claiming\nthat the district court improperly applied an enhancement that is imposed\nwhen a death results from the illegal transportation of aliens. The brothers\nassert that the death was too tenuously connected to the defendants’ conduct\nto justify the sentencing enhancement. We reject this argument and affirm the\nsentence.\n I.\n Mark Anthony Salinas entered into an agreement to smuggle illegal\naliens, which he referred to his brother Daniel Salinas. Under the terms of the\nagreement, Daniel would be paid $500 for each alien that Daniel smuggled,\nand Mark would be paid a referral fee of $50 for each alien that Daniel\ntransported.\n Consistent with this agreement, Daniel picked the aliens up in his Chevy\nSilverado. Police Officer Matias Barrera, on routine patrol at the time, spotted\nthe Silverado and recognized Daniel as a suspected alien smuggler. Barrera\nstarted to follow the truck in his patrol car. When Barrera saw Daniel run a\nstop sign, Barrera activated his emergency lights in an attempt to conduct a\ntraffic stop.\n Daniel refused to stop, and a high-speed chase ensued. Barrera pursued\nhim until Daniel drove into an empty lot and crashed into a tree. Daniel exited\nthe truck and fled on foot. Five aliens also exited the vehicle. Barrera\nimmediately apprehended two of them. The other three sprinted on foot into\nnearby brush. Border Patrol agents arrived and located two of the three fleeing\n 2\n\f Case: 18-40361 Document: 00514881265 Page: 3 Date Filed: 03/20/2019\n\n\n\n Nos. 18-40361, 18-40407\naliens. The third, Pedro Martinez, became ill in the brush and was eventually\ntransported to a hospital, where he later died. An autopsy, conducted by Dr.\nFortansus Salinas, 1 revealed that Martinez died from “acute myocardial\ninfarction,” the technical term for a heart attack.\n At sentencing, the district court applied a 10-level enhancement that is\nimposed “if any person died” in the course of “[s]muggling, [t]ransporting, or\n[h]arboring an [u]nlawful [a]lien.” U.S.S.G. § 2L1.1. In reaching this\nconclusion, the district court heard testimony from Dr. Salinas about the\nautopsy. The doctor related that Martinez “had an occlusion or a clot in the\ncoronary that led to him not being able to get oxygen to the heart itself. And\n[the heart] undergoes a process where he starts to die. We call that myocardial\ninfarction, which is a heart attack. It also throws him into abnormal rhythms.\nOnce you do that, you stop the heart and it just stops functioning, usually\ncollapse.” Dr. Salinas further elaborated that, although Martinez was just 28\nyears old, the blockage in his arteries was something that the doctor would\nexpect to see more frequently in people in their “30s, 40s, 50s.” Martinez had\nother health problems, too: he had an extensive pulmonary edema—which is\nthe collection of excess fluid in air sacs in the lungs, making it hard to\nbreathe—that Dr. Salinas thinks started prior to the heart attack. Mr.\nMartinez also had extensive fatty infiltration of his liver, a result of both his\ngenetics and his diet. Dr. Salinas said he found no evidence that Mr. Martinez\nsuffered a head injury or any scratches on his body.\n In his testimony, Dr. Salinas shed important light on the connection\nbetween the heart attack and Martinez’s running from law enforcement. While\nDr. Salinas opined that it was possible for the heart attack to have happened\n\n\n\n 1 The record does not indicate any relationship between the doctor and the defendants,\ndespite the shared last name.\n 3\n\f Case: 18-40361 Document: 00514881265 Page: 4 Date Filed: 03/20/2019\n\n\n\n Nos. 18-40361, 18-40407\nanywhere—even while Martinez was just sitting down—Dr. Salinas believed\nthat this particular heart attack was precipitated by the intensity of the\nsituation and the stress that running placed on Martinez’s heart. Dr. Salinas\ntestified that “when [Martinez] started running [from law enforcement, he]\ndemanded more work from his heart; and he just couldn’t comply, and the\nheart couldn’t comply with it; and he collapse[d], and he die[d].” The doctor\nexplained further, “[a]nything that will excite you or will get your heart going\ncan give you this type of scenario.” Specifically, in response to questions, Dr.\nSalinas explained:\n Q: Okay. But in this particular instance, you believe that [the\n heart attack] was pursuant to being chased?\n A: I believe so, yes.\n Q: That caused [Martinez’s] heart attack?\n A: That’s correct; that’s what I believe.\n After applying the enhancement to each defendant’s sentence, the\ndistrict court sentenced Daniel to 100 months imprisonment, plus three years\nof supervised release, and Mark to 78 months imprisonment, also followed by\nthree years of supervised release. The brothers objected to the enhancement,\nand the district court overruled. The defendants timely appealed.\n II.\n This court reviews the district court’s interpretation and application of\nthe Sentencing Guidelines de novo and the district court’s findings of fact for\nclear error. United States v. Ramos-Delgado, 763 F.3d 398, 400 (5th Cir. 2014).\nIn deciding “whether an enhancement applies, a district court is permitted to\ndraw reasonable inferences from the facts, and these inferences are fact-\nfindings reviewed for clear error as well.” United States v. Caldwell, 448 F.3d\n287, 290 (5th Cir. 2006). “Under the clearly erroneous standard, we will uphold\na finding so long as it is ‘plausible in light of the record as a whole.’” United\n 4\n\f Case: 18-40361 Document: 00514881265 Page: 5 Date Filed: 03/20/2019\n\n\n\n Nos. 18-40361, 18-40407\nStates v. Ekanem, 555 F.3d 172, 175 (5th Cir. 2009) (quoting Caldwell, 448\nF.3d at 290). The government “must prove sentencing enhancements by a\npreponderance of the evidence.” United States v. Juarez, 626 F.3d 246, 251\n(5th Cir. 2010). And we may affirm an enhancement on any ground supported\nby the record. United States v. Jordan, 851 F.3d 393, 399 (5th Cir. 2017).\n The Sentencing Guidelines apply an enhancement “[i]f any person died\nor sustained bodily injury” in the course of smuggling, transporting, or\nharboring an unlawful alien. U.S.S.G. § 2L1.1(b)(7). In the case of “death”—\nas opposed to mere injury—that enhancement increases the offense level by\n10. U.S.S.G. § 2L1.1(b)(7)(D). In United States v. Ramos-Delgado, we held\nthat the defendant’s conduct must simply be the but-for cause of the death, not\nits proximate cause. 763 F.3d at 401 (citing Burrage v. United States, 134 S.\nCt. 881, 887–88 (2014)).\n In interpreting the provision this way, our court observed that the\nprovision itself “contains no causation requirement” and therefore\nacknowledged that “we have no license to impose one.” Id. at 401. We\nexplained that the only applicable causation requirement, therefore, is the\ngeneral but-for causation requirement of U.S.S.G. § 1B1.3, an overarching\nprovision that defines the circumstances that a sentencing court may consider\nin determining whether any provision of the Guidelines applies. Id. Section\n1B1.3 allows sentencing courts to consider harm only if it “resulted from” or\n“was the object of” certain acts and omissions of the defendant. U.S.S.G.\n§ 1B1.3(a)(3). The Ramos-Delgado court read the phrase “resulted from”\naccording to its ordinary meaning, imposing a but-for causation requirement,\n\n\n\n\n 5\n\f Case: 18-40361 Document: 00514881265 Page: 6 Date Filed: 03/20/2019\n\n\n\n Nos. 18-40361, 18-40407\njust as the Supreme Court had in Burrage v. United States, 571 U.S. 204, 211\n(2014). 2\n But-for causation requires the government to show merely “that the\nharm would not have occurred in the absence of—that is, but for—the\ndefendant’s conduct.” Id. at 211 (quoting Univ. of Tex. Sw. Med. Ctr. v. Nassar,\n570 U.S. 338, 346–47 (2013)). This is “not a difficult burden to meet.” Ramos-\nDelgado, 763 F.3d at 402. An event might have “many but-for causes.” Id. For\nexample, the Supreme Court has explained that a leadoff batter’s home run is\njust one among many but-for causes of a team’s 1-to-0 victory, which resulted\nalso from the winning team’s “skillful pitching, the coach’s decision to put the\nleadoff batter in the lineup, and the league’s decision to schedule the game,”\nBurrage, 571 U.S. at 212, and perhaps also from the opposing pitcher leaving\n“his fastball hanging over the plate,” Ramos-Delgado, 763 F.3d at 402. A\nproximate-cause inquiry would ask how directly each cause affected the final\noutcome, but the but-for causation standard asks simply whether the outcome\nwould have occurred in the absence of the action. Burrage, 571 U.S. at 211.\nRamos-Delgado explains that even if an immigrant got thrown from a\ndefendant’s truck, sprained his hand, went to the hospital because of the\nsprain, and then died from a gas leak at the hospital, the enhancement would\nstill apply. Ramos-Delgado, 763 F.3d at 402. It does not matter that the gas\nleak was unforeseeable to the defendant or only tenuously connected to the\ndefendant’s conduct.\n\n\n\n 2 At oral argument, counsel for Daniel described Burrage as holding that “when a\ndefendant’s conduct is not . . . the independently sufficient cause of death, the defendant\ncannot be held liable.” Counsel then suggested that Ramos-Delgado misreads Burrage.\nCounsel’s description of Burrage omits the key language of the case’s holding. The Supreme\nCourt in Burrage held that “at least where use of the drug distributed by the defendant is not\nan independently sufficient cause of the victim’s death or serious bodily injury, a defendant\ncannot be liable . . . unless such use is a but-for cause of the death or injury.” Burrage, 571\nU.S. at 218 (emphasis added). Ramos-Delgado is fully consistent with this holding.\n 6\n\f Case: 18-40361 Document: 00514881265 Page: 7 Date Filed: 03/20/2019\n\n\n\n Nos. 18-40361, 18-40407\n Two published Fifth Circuit cases illustrate the application of this rule.\nFirst, in Ramos-Delgado, the defendant tried to evade Border Patrol while\ndriving a pickup truck with aliens in the truck’s bed. Id. at 400. One of the\naliens was thrown from the truck, suffering a massive skull fracture and brain\ninjuries from which he died. Id. We affirmed the district court’s application of\nthe enhancement. In light of the victim’s “medical records, it [was] plausible\nthat he died from the injuries sustained in being thrown from the bed of a\ntruck.” Id. at 402. And because the victim would not have been thrown from\nthe truck’s bed but for the defendant’s decision to transport the aliens in the\nfirst place, the defendant’s conduct was a but-for cause of the death. Id.\n Similarly, in United States v. Ruiz-Hernandez, the defendant\ntransported an alien at night in an inner tube across a ship channel. 890 F.3d\n202, 207–08 (5th Cir. 2018). An unlit Coast Guard vessel sped through the\nchannel, killing the alien. Id. We held that the defendant’s conduct was a but-\nfor cause of the death because, even though the vessel’s speed and lack of lights\ncontributed greatly to the death, the alien would not have been in the ship’s\npath in the absence of the defendant’s conduct. Id. at 212–13.\n The instant case falls squarely within the reach of Ramos-Delgado and\nRuiz-Hernandez. The district court heard extensive testimony from Dr.\nSalinas, who concluded that this particular heart attack was triggered by\nMartinez’s running. In light of this testimony, it was certainly “plausible” that\nMartinez’s fatal heart attack was caused by the running. Ramos-Delgado, 763\nF.3d at 402. The district court did not clearly err in accepting that testimony\nand making this finding of fact. Martinez would not have run had the Salinas\nbrothers not arranged to pick up the aliens, driven the aliens in the Silverado,\nand crashed the Silverado into a tree with law enforcement closing in. Just as\nin Ramos-Delgado and Ruiz-Hernandez, the Salinas brothers were fully\nresponsible for placing the victim in a precarious position where subsequent\n 7\n\f Case: 18-40361 Document: 00514881265 Page: 8 Date Filed: 03/20/2019\n\n\n\n Nos. 18-40361, 18-40407\nbut-for causes ultimately took his life. In short: No criminal conduct, no\nrunning. No running, no death. The defendants’ conduct was the but-for cause\nof Martinez’s death, which is all that this sentencing enhancement requires.\n III.\n We are bound by precedent—both the Supreme Court’s and our own—\nand by our fidelity to the text of the Guidelines to impose only a but-for\ncausation requirement. Under that standard, the sentencing enhancement is\nappropriate. For these reasons, we AFFIRM the district court’s sentence.\n\n\n\n\n 8\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Plaintiff-Appellee, v. Daniel SALINAS, Defendant-Appellant. United States of America, Plaintiff-Appellee, v. Mark Anthony Salinas, Defendant-Appellant.\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-20\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 18-40361 Document: 00514881265 Page: 1 Date Filed: 03/20/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n\\n\\n No. 18-40361 United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n March 20, 2019\\nUNITED STATES OF AMERICA,\\n Lyle W. Cayce\\n Plaintiff – Appellee, Clerk\\n\\n\\nv.\\n\\nDANIEL SALINAS,\\n\\n Defendant – Appellant.\\n---------------------------------------------------------------------\\ncons w/ 18-40407\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff – Appellee,\\n\\nv.\\n\\nMARK ANTHONY SALINAS,\\n\\n Defendant – Appellant.\\n\\n\\n\\n\\n Appeals from the United States District Court\\n for the Southern District of Texas\\n\\f Case: 18-40361 Document: 00514881265 Page: 2 Date Filed: 03/20/2019\\n\\n\\n\\n Nos. 18-40361, 18-40407\\nBefore HIGGINBOTHAM, ELROD, and HO, Circuit Judges.\\nPER CURIAM:\\n Two brothers pleaded guilty to conspiring to transport illegal aliens\\nwithin the United States by means of a motor vehicle, in violation of 8 U.S.C.\\n§ 1324(a)(1). One of the aliens they transported died from a heart attack while\\nfleeing law enforcement. The brothers now contest their sentences, claiming\\nthat the district court improperly applied an enhancement that is imposed\\nwhen a death results from the illegal transportation of aliens. The brothers\\nassert that the death was too tenuously connected to the defendants’ conduct\\nto justify the sentencing enhancement. We reject this argument and affirm the\\nsentence.\\n I.\\n Mark Anthony Salinas entered into an agreement to smuggle illegal\\naliens, which he referred to his brother Daniel Salinas. Under the terms of the\\nagreement, Daniel would be paid $500 for each alien that Daniel smuggled,\\nand Mark would be paid a referral fee of $50 for each alien that Daniel\\ntransported.\\n Consistent with this agreement, Daniel picked the aliens up in his Chevy\\nSilverado. Police Officer Matias Barrera, on routine patrol at the time, spotted\\nthe Silverado and recognized Daniel as a suspected alien smuggler. Barrera\\nstarted to follow the truck in his patrol car. When Barrera saw Daniel run a\\nstop sign, Barrera activated his emergency lights in an attempt to conduct a\\ntraffic stop.\\n Daniel refused to stop, and a high-speed chase ensued. Barrera pursued\\nhim until Daniel drove into an empty lot and crashed into a tree. Daniel exited\\nthe truck and fled on foot. Five aliens also exited the vehicle. Barrera\\nimmediately apprehended two of them. The other three sprinted on foot into\\nnearby brush. Border Patrol agents arrived and located two of the three fleeing\\n 2\\n\\f Case: 18-40361 Document: 00514881265 Page: 3 Date Filed: 03/20/2019\\n\\n\\n\\n Nos. 18-40361, 18-40407\\naliens. The third, Pedro Martinez, became ill in the brush and was eventually\\ntransported to a hospital, where he later died. An autopsy, conducted by Dr.\\nFortansus Salinas, 1 revealed that Martinez died from “acute myocardial\\ninfarction,” the technical term for a heart attack.\\n At sentencing, the district court applied a 10-level enhancement that is\\nimposed “if any person died” in the course of “[s]muggling, [t]ransporting, or\\n[h]arboring an [u]nlawful [a]lien.” U.S.S.G. § 2L1.1. In reaching this\\nconclusion, the district court heard testimony from Dr. Salinas about the\\nautopsy. The doctor related that Martinez “had an occlusion or a clot in the\\ncoronary that led to him not being able to get oxygen to the heart itself. And\\n[the heart] undergoes a process where he starts to die. We call that myocardial\\ninfarction, which is a heart attack. It also throws him into abnormal rhythms.\\nOnce you do that, you stop the heart and it just stops functioning, usually\\ncollapse.” Dr. Salinas further elaborated that, although Martinez was just 28\\nyears old, the blockage in his arteries was something that the doctor would\\nexpect to see more frequently in people in their “30s, 40s, 50s.” Martinez had\\nother health problems, too: he had an extensive pulmonary edema—which is\\nthe collection of excess fluid in air sacs in the lungs, making it hard to\\nbreathe—that Dr. Salinas thinks started prior to the heart attack. Mr.\\nMartinez also had extensive fatty infiltration of his liver, a result of both his\\ngenetics and his diet. Dr. Salinas said he found no evidence that Mr. Martinez\\nsuffered a head injury or any scratches on his body.\\n In his testimony, Dr. Salinas shed important light on the connection\\nbetween the heart attack and Martinez’s running from law enforcement. While\\nDr. Salinas opined that it was possible for the heart attack to have happened\\n\\n\\n\\n 1 The record does not indicate any relationship between the doctor and the defendants,\\ndespite the shared last name.\\n 3\\n\\f Case: 18-40361 Document: 00514881265 Page: 4 Date Filed: 03/20/2019\\n\\n\\n\\n Nos. 18-40361, 18-40407\\nanywhere—even while Martinez was just sitting down—Dr. Salinas believed\\nthat this particular heart attack was precipitated by the intensity of the\\nsituation and the stress that running placed on Martinez’s heart. Dr. Salinas\\ntestified that “when [Martinez] started running [from law enforcement, he]\\ndemanded more work from his heart; and he just couldn’t comply, and the\\nheart couldn’t comply with it; and he collapse[d], and he die[d].” The doctor\\nexplained further, “[a]nything that will excite you or will get your heart going\\ncan give you this type of scenario.” Specifically, in response to questions, Dr.\\nSalinas explained:\\n Q: Okay. But in this particular instance, you believe that [the\\n heart attack] was pursuant to being chased?\\n A: I believe so, yes.\\n Q: That caused [Martinez’s] heart attack?\\n A: That’s correct; that’s what I believe.\\n After applying the enhancement to each defendant’s sentence, the\\ndistrict court sentenced Daniel to 100 months imprisonment, plus three years\\nof supervised release, and Mark to 78 months imprisonment, also followed by\\nthree years of supervised release. The brothers objected to the enhancement,\\nand the district court overruled. The defendants timely appealed.\\n II.\\n This court reviews the district court’s interpretation and application of\\nthe Sentencing Guidelines de novo and the district court’s findings of fact for\\nclear error. United States v. Ramos-Delgado, 763 F.3d 398, 400 (5th Cir. 2014).\\nIn deciding “whether an enhancement applies, a district court is permitted to\\ndraw reasonable inferences from the facts, and these inferences are fact-\\nfindings reviewed for clear error as well.” United States v. Caldwell, 448 F.3d\\n287, 290 (5th Cir. 2006). “Under the clearly erroneous standard, we will uphold\\na finding so long as it is ‘plausible in light of the record as a whole.’” United\\n 4\\n\\f Case: 18-40361 Document: 00514881265 Page: 5 Date Filed: 03/20/2019\\n\\n\\n\\n Nos. 18-40361, 18-40407\\nStates v. Ekanem, 555 F.3d 172, 175 (5th Cir. 2009) (quoting Caldwell, 448\\nF.3d at 290). The government “must prove sentencing enhancements by a\\npreponderance of the evidence.” United States v. Juarez, 626 F.3d 246, 251\\n(5th Cir. 2010). And we may affirm an enhancement on any ground supported\\nby the record. United States v. Jordan, 851 F.3d 393, 399 (5th Cir. 2017).\\n The Sentencing Guidelines apply an enhancement “[i]f any person died\\nor sustained bodily injury” in the course of smuggling, transporting, or\\nharboring an unlawful alien. U.S.S.G. § 2L1.1(b)(7). In the case of “death”—\\nas opposed to mere injury—that enhancement increases the offense level by\\n10. U.S.S.G. § 2L1.1(b)(7)(D). In United States v. Ramos-Delgado, we held\\nthat the defendant’s conduct must simply be the but-for cause of the death, not\\nits proximate cause. 763 F.3d at 401 (citing Burrage v. United States, 134 S.\\nCt. 881, 887–88 (2014)).\\n In interpreting the provision this way, our court observed that the\\nprovision itself “contains no causation requirement” and therefore\\nacknowledged that “we have no license to impose one.” Id. at 401. We\\nexplained that the only applicable causation requirement, therefore, is the\\ngeneral but-for causation requirement of U.S.S.G. § 1B1.3, an overarching\\nprovision that defines the circumstances that a sentencing court may consider\\nin determining whether any provision of the Guidelines applies. Id. Section\\n1B1.3 allows sentencing courts to consider harm only if it “resulted from” or\\n“was the object of” certain acts and omissions of the defendant. U.S.S.G.\\n§ 1B1.3(a)(3). The Ramos-Delgado court read the phrase “resulted from”\\naccording to its ordinary meaning, imposing a but-for causation requirement,\\n\\n\\n\\n\\n 5\\n\\f Case: 18-40361 Document: 00514881265 Page: 6 Date Filed: 03/20/2019\\n\\n\\n\\n Nos. 18-40361, 18-40407\\njust as the Supreme Court had in Burrage v. United States, 571 U.S. 204, 211\\n(2014). 2\\n But-for causation requires the government to show merely “that the\\nharm would not have occurred in the absence of—that is, but for—the\\ndefendant’s conduct.” Id. at 211 (quoting Univ. of Tex. Sw. Med. Ctr. v. Nassar,\\n570 U.S. 338, 346–47 (2013)). This is “not a difficult burden to meet.” Ramos-\\nDelgado, 763 F.3d at 402. An event might have “many but-for causes.” Id. For\\nexample, the Supreme Court has explained that a leadoff batter’s home run is\\njust one among many but-for causes of a team’s 1-to-0 victory, which resulted\\nalso from the winning team’s “skillful pitching, the coach’s decision to put the\\nleadoff batter in the lineup, and the league’s decision to schedule the game,”\\nBurrage, 571 U.S. at 212, and perhaps also from the opposing pitcher leaving\\n“his fastball hanging over the plate,” Ramos-Delgado, 763 F.3d at 402. A\\nproximate-cause inquiry would ask how directly each cause affected the final\\noutcome, but the but-for causation standard asks simply whether the outcome\\nwould have occurred in the absence of the action. Burrage, 571 U.S. at 211.\\nRamos-Delgado explains that even if an immigrant got thrown from a\\ndefendant’s truck, sprained his hand, went to the hospital because of the\\nsprain, and then died from a gas leak at the hospital, the enhancement would\\nstill apply. Ramos-Delgado, 763 F.3d at 402. It does not matter that the gas\\nleak was unforeseeable to the defendant or only tenuously connected to the\\ndefendant’s conduct.\\n\\n\\n\\n 2 At oral argument, counsel for Daniel described Burrage as holding that “when a\\ndefendant’s conduct is not . . . the independently sufficient cause of death, the defendant\\ncannot be held liable.” Counsel then suggested that Ramos-Delgado misreads Burrage.\\nCounsel’s description of Burrage omits the key language of the case’s holding. The Supreme\\nCourt in Burrage held that “at least where use of the drug distributed by the defendant is not\\nan independently sufficient cause of the victim’s death or serious bodily injury, a defendant\\ncannot be liable . . . unless such use is a but-for cause of the death or injury.” Burrage, 571\\nU.S. at 218 (emphasis added). Ramos-Delgado is fully consistent with this holding.\\n 6\\n\\f Case: 18-40361 Document: 00514881265 Page: 7 Date Filed: 03/20/2019\\n\\n\\n\\n Nos. 18-40361, 18-40407\\n Two published Fifth Circuit cases illustrate the application of this rule.\\nFirst, in Ramos-Delgado, the defendant tried to evade Border Patrol while\\ndriving a pickup truck with aliens in the truck’s bed. Id. at 400. One of the\\naliens was thrown from the truck, suffering a massive skull fracture and brain\\ninjuries from which he died. Id. We affirmed the district court’s application of\\nthe enhancement. In light of the victim’s “medical records, it [was] plausible\\nthat he died from the injuries sustained in being thrown from the bed of a\\ntruck.” Id. at 402. And because the victim would not have been thrown from\\nthe truck’s bed but for the defendant’s decision to transport the aliens in the\\nfirst place, the defendant’s conduct was a but-for cause of the death. Id.\\n Similarly, in United States v. Ruiz-Hernandez, the defendant\\ntransported an alien at night in an inner tube across a ship channel. 890 F.3d\\n202, 207–08 (5th Cir. 2018). An unlit Coast Guard vessel sped through the\\nchannel, killing the alien. Id. We held that the defendant’s conduct was a but-\\nfor cause of the death because, even though the vessel’s speed and lack of lights\\ncontributed greatly to the death, the alien would not have been in the ship’s\\npath in the absence of the defendant’s conduct. Id. at 212–13.\\n The instant case falls squarely within the reach of Ramos-Delgado and\\nRuiz-Hernandez. The district court heard extensive testimony from Dr.\\nSalinas, who concluded that this particular heart attack was triggered by\\nMartinez’s running. In light of this testimony, it was certainly “plausible” that\\nMartinez’s fatal heart attack was caused by the running. Ramos-Delgado, 763\\nF.3d at 402. The district court did not clearly err in accepting that testimony\\nand making this finding of fact. Martinez would not have run had the Salinas\\nbrothers not arranged to pick up the aliens, driven the aliens in the Silverado,\\nand crashed the Silverado into a tree with law enforcement closing in. Just as\\nin Ramos-Delgado and Ruiz-Hernandez, the Salinas brothers were fully\\nresponsible for placing the victim in a precarious position where subsequent\\n 7\\n\\f Case: 18-40361 Document: 00514881265 Page: 8 Date Filed: 03/20/2019\\n\\n\\n\\n Nos. 18-40361, 18-40407\\nbut-for causes ultimately took his life. In short: No criminal conduct, no\\nrunning. No running, no death. The defendants’ conduct was the but-for cause\\nof Martinez’s death, which is all that this sentencing enhancement requires.\\n III.\\n We are bound by precedent—both the Supreme Court’s and our own—\\nand by our fidelity to the text of the Guidelines to impose only a but-for\\ncausation requirement. Under that standard, the sentencing enhancement is\\nappropriate. For these reasons, we AFFIRM the district court’s sentence.\\n\\n\\n\\n\\n 8\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1093,"cells":{"id":{"kind":"number","value":4601854,"string":"4,601,854"},"name":{"kind":"string","value":"UNITED STATES of America, Plaintiff-Appellee v. Calvin ALLEN, Defendant-Appellant"},"name_abbreviation":{"kind":"string","value":"United States v. Calvin Allen"},"decision_date":{"kind":"string","value":"2019-03-20"},"docket_number":{"kind":"string","value":"17-60440"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"James, Higginbotham, Elrod\", \"parties\": \"\", \"opinions\": [{\"author\": \"JAMES C. HO, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 17-60440 Document: 00514881108 Page: 1 Date Filed: 03/20/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n No. 17-60440 FILED\\n March 20, 2019\\n Lyle W. Cayce\\nUNITED STATES OF AMERICA, Clerk\\n\\n Plaintiff - Appellee\\n\\nv.\\n\\nCALVIN ALLEN,\\n\\n Defendant - Appellant\\n\\n\\n\\n\\n Appeal from the United States District Court\\n for the Southern District of Mississippi\\n\\n\\nBefore HIGGINBOTHAM, ELROD, and HO, Circuit Judges.\\nJAMES C. HO, Circuit Judge:\\n Our court previously granted a certificate of appealability (COA) to\\nCalvin Allen on two claims—first, that the government breached its obligations\\nunder his plea agreement when it failed to credit his cooperation in a murder\\nconviction, and second, that Allen received ineffective assistance of counsel due\\nto his attorney’s failure to object to the government’s breach of his plea\\nagreement. We now conclude that the district court should have held an\\nevidentiary hearing on Allen’s ineffective counsel claim. Accordingly, we\\nvacate the judgment and remand for a limited evidentiary inquiry.\\n\\f Case: 17-60440 Document: 00514881108 Page: 2 Date Filed: 03/20/2019\\n\\n\\n\\n No. 17-60440\\n I.\\n Allen pleaded guilty to one count of conspiracy to possess with intent to\\ndistribute a controlled substance. In exchange for Allen’s plea and waiver of\\nthe right to appeal, the government promised that it would:\\n inform the United States Probation Office and the Court of [1] [the\\n plea agreement], [2] the nature and extent of Defendant’s activities\\n with respect to this case and [3] all other activities of Defendant\\n which the U.S. Attorney deems relevant to sentencing, including\\n the nature and extent of Defendant’s cooperation with the U.S.\\n Attorney and law enforcement.\\n\\n Allen cooperated with prosecutors, providing them with information\\nabout his co-conspirators in his drug case. He also provided information\\nleading to the prosecution of an unrelated murder.\\n The presentence report (PSR) included information about Allen’s\\ncooperation in the drug case, but not the murder. On appeal, Allen claims that\\nthis omission constitutes a breach of the plea agreement by the government.\\nBut Allen failed to identify any such breach to the district court: He did not\\nobject to the PSR. Nor did he object during the sentencing hearing. The court\\nsubsequently sentenced him to 188 months in prison and 5 years of supervised\\nrelease.\\n Allen filed a timely pro se motion to vacate, set aside, or correct his\\nsentence under 28 U.S.C. § 2255, alleging that he received ineffective\\nassistance of counsel. He asserted that the plea agreement obligated the\\ngovernment to inform the sentencing court about his cooperation in the murder\\ninvestigation, as well as the drug prosecution. And when the government\\nfailed to do so, Allen contends that his counsel should have either objected or\\nmoved for a downward departure in his sentence. In Allen’s view, this error\\npotentially deprived him of a lower sentence. He also requested an evidentiary\\nhearing on his claim under 28 U.S.C. § 2255(b).\\n\\n 2\\n\\f Case: 17-60440 Document: 00514881108 Page: 3 Date Filed: 03/20/2019\\n\\n\\n\\n No. 17-60440\\n The district court ordered Allen’s attorney to respond to the allegations\\nof ineffective counsel. Allen’s counsel averred that (1) he believed the\\ngovernment discharged its obligation under the plea because the PSR included\\ninformation about Allen’s cooperation; and (2) he and Allen decided not to move\\nfor a downward departure based on Allen’s cooperation because raising\\nmitigating circumstances would open the door to the court considering\\naggravating circumstances.\\n For its part, the government argued that (1) Allen procedurally defaulted\\non any claim that the government violated its plea; and (2) Allen’s counsel was\\nnot constitutionally ineffective.\\n The district court denied Allen’s motion without an evidentiary hearing,\\nafter concluding that (1) the government did not breach its plea obligations;\\nand (2) Allen’s ineffective assistance claim fails because his counsel’s failure to\\nobject was merely a tactical decision.\\n We subsequently granted a COA on two questions:\\n (1) “[W]hether the district court erred in denying without an\\n evidentiary hearing Allen’s claim that the Government breached\\n the plea agreement by failing to disclose his cooperation regarding\\n other criminal cases.”\\n\\n (2) “[W]hether the district court erred in denying without an\\n evidentiary hearing Allen’s claim that he received ineffective\\n assistance because his counsel failed to inform the sentencing\\n court of the Government’s failure to disclose his cooperation\\n regarding other criminal cases.”\\n\\n After the parties submitted their briefs, we requested additional briefing\\non whether Allen procedurally defaulted on his claim that the government\\nbreached its obligations under the plea agreement.\\n II.\\n Allen moved for § 2255 relief on the ground that the sentence was\\nimposed in violation of the Constitution. 28 U.S.C. § 2255(a). See also\\n 3\\n\\f Case: 17-60440 Document: 00514881108 Page: 4 Date Filed: 03/20/2019\\n\\n\\n\\n No. 17-60440\\nStrickland v. Washington, 466 U.S. 668, 686 (1984) (recognizing that\\nineffective assistance of counsel violates the Sixth Amendment); United States\\nv. McDaniels, 907 F.3d 366, 370 (5th Cir. 2018) (“Where a defendant pleads\\nguilty based on a promise by the prosecutor, ‘breach of that promise taints the\\nvoluntariness of his plea’ and offends the Fifth Amendment.”) (quoting Davis\\nv. Butler, 825 F.2d 892, 894 (5th Cir. 1987)). He also requests, at a minimum,\\nan evidentiary hearing on his claims under 28 U.S.C. § 2255(b).\\n We review the district court’s denial of § 2255 relief de novo, and its\\ndenial of an evidentiary hearing for abuse of discretion. See United States v.\\nReed, 719 F.3d 369, 373 (5th Cir. 2013) (citing United States v. Edwards, 442\\nF.3d 258, 264 (5th Cir. 2006)). “A § 2255 motion requires an evidentiary\\nhearing unless either (1) the movant’s claims are clearly frivolous or based\\nupon unsupported generalizations, or (2) the movant would not be entitled to\\nrelief as a matter of law, even if his factual assertions were true.” United States\\nv. Harrison, 910 F.3d 824, 826–27 (5th Cir. 2018) (citing United States v.\\nGuerra, 588 F.2d 519, 521 (5th Cir. 1979)).\\n We conclude that Allen procedurally defaulted his breach of plea claim.\\nHe is therefore only entitled to relief if he can succeed in his ineffective\\nassistance claim—either as “cause” sufficient to excuse his procedural default\\non his breach of plea claim, or as an independent ineffective counsel infirmity.\\nWe conclude that the district court erred by not holding an evidentiary hearing\\nor otherwise inquiring further into Allen’s ineffective counsel claim, because\\nthe record does not “conclusively show” that that claim fails. 28 U.S.C.\\n§ 2255(b).\\n\\n\\n\\n\\n 4\\n\\f Case: 17-60440 Document: 00514881108 Page: 5 Date Filed: 03/20/2019\\n\\n\\n\\n No. 17-60440\\n A.\\n Allen has procedurally defaulted his claim that the government breached\\nits plea obligations, by failing to present any such claim before the district\\ncourt. 1\\n “A movant is barred from raising . . . constitutional claims for the first\\ntime on collateral review unless he demonstrates [1] cause for failing to raise\\nthe issue on direct appeal and [2] actual prejudice resulting from the error.”\\nUnited States v. Patten, 40 F.3d 774, 776 (5th Cir. 1994) (per curiam) (citing\\nUnited States v. Pierce, 959 F.2d 1297, 1301 (5th Cir. 1992)). We may raise\\nprocedural default sua sponte. See United States v. Willis, 273 F.3d 592, 597\\n(5th Cir. 2001). We “should not do so lightly,” however. Id. (citing Rosario v.\\nUnited States, 164 F.3d 729, 733 (2d Cir. 1998)). But when the petitioner is on\\nnotice of the default bar, has had the opportunity to argue against it, and the\\ngovernment has not waived the defense, it may be “proper to invoke the\\nprocedural bar.” Id.\\n Although Allen’s breach of plea claim is procedurally defaulted, whether\\nthe government breached its plea obligations is something we must decide as\\npart of Allen’s ineffective assistance claim. If the government did not breach\\nthe plea agreement, then Allen’s counsel had nothing to respond to, and\\ntherefore was not ineffective.\\n B.\\n To obtain relief, then, Allen must demonstrate that his counsel was\\nconstitutionally ineffective—either to excuse his procedural default on his\\nbreach of plea claim, or as a stand-alone ineffective counsel claim. See Patten,\\n\\n\\n 1 Allen’s § 2255 motion only raised one ground for relief: ineffective assistance of\\ncounsel. To be sure, Allen’s ineffective assistance claim depends on the government\\nbreaching its plea obligations. But the district court considered Allen’s breach of plea claim\\nas a stand-alone ground for relief. We likewise granted a certificate of appealability on the\\nbreach of plea claim. We accordingly address it here.\\n 5\\n\\f Case: 17-60440 Document: 00514881108 Page: 6 Date Filed: 03/20/2019\\n\\n\\n\\n No. 17-60440\\n40 F.3d at 776 (citing Pierce, 959 F.2d at 1301); see also United States v.\\nWalling, 982 F.2d 447, 449 (10th Cir. 1992) (“The Strickland ineffectiveness\\ntest dovetails naturally with the cause and prejudice standard.”).\\n To succeed on his ineffective assistance claim, Allen “must demonstrate\\nthat (1) counsel’s representation fell below an objective standard of\\nreasonableness and that (2) there is a reasonable probability that prejudice\\nresulted.” Druery v. Thaler, 647 F.3d 535, 538 (5th Cir. 2011) (citing Bower v.\\nQuarterman, 497 F.3d 459, 466 (5th Cir. 2007)). “[A] court must indulge a\\nstrong presumption that counsel’s conduct falls within the wide range of\\nreasonable professional assistance; that is, the defendant must overcome the\\npresumption that, under the circumstances, the challenged action ‘might be\\nconsidered sound trial strategy.’” Strickland, 466 U.S. at 689 (quoting Michel\\nv. Louisiana, 350 U.S. 91, 101 (1955)). So mere disagreement about tactics\\ndoes not amount to a constitutional infirmity. See id. at 690.\\n We conclude that an evidentiary hearing is needed before we can decide\\nwhether Allen’s representation was constitutionally deficient, based on the\\nfailure to inform the court of Allen’s cooperation in the murder investigation.\\n First, we must consider whether there was any error by the government\\nthat could support an ineffective assistance claim.\\n As for Allen’s undisputed cooperation in the related drug case, the\\ndistrict court correctly concluded that the government did not breach the plea\\nagreement. The PSR disclosed Allen’s cooperation in the drug case. And\\nnothing in the plea agreement required the government to additionally raise\\nAllen’s cooperation in the drug case at the sentencing hearing. 2\\n\\n\\n\\n 2 The cases Allen cites are inapposite. For example, in United States v. Hunter, the\\nplea agreement expressly provided: “The United States agrees that it will recommend at\\nsentencing that the Court reduce by two levels the sentencing guideline level applicable to\\nthe defendant’s offense.” 835 F.3d 1320, 1323 (11th Cir. 2016) (emphasis added). And in\\n 6\\n\\f Case: 17-60440 Document: 00514881108 Page: 7 Date Filed: 03/20/2019\\n\\n\\n\\n No. 17-60440\\n As for Allen’s cooperation in the murder investigation, however, the\\ngovernment never informed the court, either in the PSR or during the\\nsentencing hearing. If indeed Allen cooperated with law enforcement in the\\nmurder investigation, and if the government deemed his cooperation relevant\\nto his sentencing, then the government was obligated to inform the sentencing\\ncourt. Because there is some indication that the government did not discharge\\nits burden, the district court should not have denied relief without inquiring\\nfurther or holding an evidentiary hearing.\\n The government argues that it did not “deem relevant” Allen’s\\ncooperation because “it was the opinion of the case agent that his information\\nwas not credible.” 3 In essence, the government contends that any decision not\\nto inform the court about Allen’s cooperation was necessarily an exercise of the\\ndiscretion allowed by the plea agreement. But the government had to actually\\nexercise that discretion and determine that Allen’s cooperation was not\\nrelevant—rather than simply refuse to inform the court about relevant\\ninformation. According to Allen’s sworn statement, he “provided information\\nin the unsolved murder case,” and “approximately two weeks after [his]\\ncooperation, an arrest was made in the case.” Moreover, Allen contends that\\nhis “counsel stated that [his counsel] had spoken with the case agent and\\naffirmed that [Allen’s] information in regard to the murder was good and\\nuseful.” So Allen has provided some evidence that the government considered\\n\\n\\n\\n\\nCorreale v. United States, the court considered the government’s total failure to make the\\nrecommendation it promised to make. See 479 F.2d 944, 946, 949 (1st Cir. 1973).\\n 3 It is unclear whether the government was addressing Allen’s cooperation in the drug\\n\\ncase or the murder case. In its briefs before us, the government emphasizes that Allen has\\nnot been clear about when he offered the information about the murder or whether it was\\nuseful to investigators. True as far as it goes, the government’s response only highlights the\\nquestions the district court should consider on remand. Thus, the government has failed to\\nassert that Allen “would not be entitled to relief as a matter of law, even if his factual\\nassertions were true.” Harrison, 910 F.3d at 826–27 (citing Guerra, 588 F.2d at 521).\\n 7\\n\\f Case: 17-60440 Document: 00514881108 Page: 8 Date Filed: 03/20/2019\\n\\n\\n\\n No. 17-60440\\nhis information credible. And without further explanation from the\\ngovernment why the evidence was somehow not relevant to Allen’s sentence,\\nthe government has not offered anything that “conclusively negate[s] the\\nfactual predicates asserted in support of the motion for post-conviction relief.”\\nFriedman v. United States, 588 F.2d 1010, 1015 (5th Cir. 1979) (explaining the\\nrequirements of 28 U.S.C. § 2255(b)).\\n Second, if there was a breach, Allen’s counsel’s failure to object to the\\nbreach may have fallen “below an objective standard of reasonableness.”\\nDruery, 647 F.3d at 538. In his affidavit, Allen’s counsel said that the PSR\\nreflected Allen’s full cooperation with investigators, and that he did not raise\\nAllen’s cooperation separately in the sentencing hearing because raising any\\nmitigating factors would open a “Pandora’s box” of aggravating factors. But\\nthe affidavit, at least on its face, does not address Allen’s contention about his\\ncooperation in the murder investigation. Accordingly, we lack any “sworn\\nrecord testimony from counsel explaining the strategy behind his decision.”\\nUnited States v. Cavitt, 550 F.3d 430, 441 (5th Cir. 2008). So we cannot tell\\nwhether Allen’s counsel believed the government breached its obligations\\nunder the plea, or whether his failure to raise any purported breach was a\\nstrategic decision. See, e.g., Herring v. Estelle, 491 F.2d 125, 128 (5th Cir. 1974)\\n(“[A] lawyer who is not familiar with the facts and law relevant to his client’s\\ncase cannot meet [the] required minimal level.”).\\n Third, if there was a breach of the plea agreement, then Allen may have\\nbeen prejudiced by his counsel’s failure to object to the breach. Allen contends\\nthat the court might have imposed a lesser sentence had it known about the\\nfull scope of his cooperation. To be sure, the district court concluded that “[i]t\\nis pure conjecture that Allen’s sentence would have been lesser had Allen’s\\ncounsel disclosed any purported additional cooperation not reflected in the\\nPSR.” But the district court did not specifically consider Allen’s apparent\\n 8\\n\\f Case: 17-60440 Document: 00514881108 Page: 9 Date Filed: 03/20/2019\\n\\n\\n\\n No. 17-60440\\ncooperation in the murder investigation. Remand will allow the district court\\nto consider Allen’s contention and determine whether this information would\\nhave made Allen’s sentence “significantly less harsh.” Dale v. Quarterman,\\n553 F.3d 876, 880 (5th Cir. 2008) (per curiam) (quoting Spriggs v. Collins, 993\\nF.2d 85, 88–89 (5th Cir. 1993) (per curiam)).\\n III.\\n Once the district court holds an evidentiary hearing, it may turn out that\\nthere was no violation—either because the government did not breach the plea\\nagreement or because Allen’s counsel was not ineffective in failing to discover\\nthe breach. But a “motion brought under 28 U.S.C. § 2255 can be denied\\nwithout a hearing only if the motion, files, and records of the case conclusively\\nshow that the prisoner is entitled to no relief.” Cavitt, 550 F.3d at 442 (internal\\nquotation marks omitted) (quoting United States v. Bartholomew, 974 F.2d 39,\\n41 (5th Cir. 1992) (per curiam)). Because that standard is not met here, we\\nvacate the judgment and remand for an evidentiary hearing. The district court\\nshould consider whether the government breached its obligation to inform the\\ncourt about Allen’s cooperation in the murder case and, if it did, why Allen’s\\ncounsel failed to raise the issue.\\n\\n\\n\\n\\n 9\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4379107/\", \"author_raw\": \"JAMES C. HO, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"JAMES"},"judge2":{"kind":"string","value":"HIGGINBOTHAM"},"judge3":{"kind":"string","value":"ELROD"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4601854/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Plaintiff-Appellee v. Calvin ALLEN, Defendant-Appellant\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-20\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 17-60440 Document: 00514881108 Page: 1 Date Filed: 03/20/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\n United States Court of Appeals\n Fifth Circuit\n\n No. 17-60440 FILED\n March 20, 2019\n Lyle W. Cayce\nUNITED STATES OF AMERICA, Clerk\n\n Plaintiff - Appellee\n\nv.\n\nCALVIN ALLEN,\n\n Defendant - Appellant\n\n\n\n\n Appeal from the United States District Court\n for the Southern District of Mississippi\n\n\nBefore HIGGINBOTHAM, ELROD, and HO, Circuit Judges.\nJAMES C. HO, Circuit Judge:\n Our court previously granted a certificate of appealability (COA) to\nCalvin Allen on two claims—first, that the government breached its obligations\nunder his plea agreement when it failed to credit his cooperation in a murder\nconviction, and second, that Allen received ineffective assistance of counsel due\nto his attorney’s failure to object to the government’s breach of his plea\nagreement. We now conclude that the district court should have held an\nevidentiary hearing on Allen’s ineffective counsel claim. Accordingly, we\nvacate the judgment and remand for a limited evidentiary inquiry.\n\f Case: 17-60440 Document: 00514881108 Page: 2 Date Filed: 03/20/2019\n\n\n\n No. 17-60440\n I.\n Allen pleaded guilty to one count of conspiracy to possess with intent to\ndistribute a controlled substance. In exchange for Allen’s plea and waiver of\nthe right to appeal, the government promised that it would:\n inform the United States Probation Office and the Court of [1] [the\n plea agreement], [2] the nature and extent of Defendant’s activities\n with respect to this case and [3] all other activities of Defendant\n which the U.S. Attorney deems relevant to sentencing, including\n the nature and extent of Defendant’s cooperation with the U.S.\n Attorney and law enforcement.\n\n Allen cooperated with prosecutors, providing them with information\nabout his co-conspirators in his drug case. He also provided information\nleading to the prosecution of an unrelated murder.\n The presentence report (PSR) included information about Allen’s\ncooperation in the drug case, but not the murder. On appeal, Allen claims that\nthis omission constitutes a breach of the plea agreement by the government.\nBut Allen failed to identify any such breach to the district court: He did not\nobject to the PSR. Nor did he object during the sentencing hearing. The court\nsubsequently sentenced him to 188 months in prison and 5 years of supervised\nrelease.\n Allen filed a timely pro se motion to vacate, set aside, or correct his\nsentence under 28 U.S.C. § 2255, alleging that he received ineffective\nassistance of counsel. He asserted that the plea agreement obligated the\ngovernment to inform the sentencing court about his cooperation in the murder\ninvestigation, as well as the drug prosecution. And when the government\nfailed to do so, Allen contends that his counsel should have either objected or\nmoved for a downward departure in his sentence. In Allen’s view, this error\npotentially deprived him of a lower sentence. He also requested an evidentiary\nhearing on his claim under 28 U.S.C. § 2255(b).\n\n 2\n\f Case: 17-60440 Document: 00514881108 Page: 3 Date Filed: 03/20/2019\n\n\n\n No. 17-60440\n The district court ordered Allen’s attorney to respond to the allegations\nof ineffective counsel. Allen’s counsel averred that (1) he believed the\ngovernment discharged its obligation under the plea because the PSR included\ninformation about Allen’s cooperation; and (2) he and Allen decided not to move\nfor a downward departure based on Allen’s cooperation because raising\nmitigating circumstances would open the door to the court considering\naggravating circumstances.\n For its part, the government argued that (1) Allen procedurally defaulted\non any claim that the government violated its plea; and (2) Allen’s counsel was\nnot constitutionally ineffective.\n The district court denied Allen’s motion without an evidentiary hearing,\nafter concluding that (1) the government did not breach its plea obligations;\nand (2) Allen’s ineffective assistance claim fails because his counsel’s failure to\nobject was merely a tactical decision.\n We subsequently granted a COA on two questions:\n (1) “[W]hether the district court erred in denying without an\n evidentiary hearing Allen’s claim that the Government breached\n the plea agreement by failing to disclose his cooperation regarding\n other criminal cases.”\n\n (2) “[W]hether the district court erred in denying without an\n evidentiary hearing Allen’s claim that he received ineffective\n assistance because his counsel failed to inform the sentencing\n court of the Government’s failure to disclose his cooperation\n regarding other criminal cases.”\n\n After the parties submitted their briefs, we requested additional briefing\non whether Allen procedurally defaulted on his claim that the government\nbreached its obligations under the plea agreement.\n II.\n Allen moved for § 2255 relief on the ground that the sentence was\nimposed in violation of the Constitution. 28 U.S.C. § 2255(a). See also\n 3\n\f Case: 17-60440 Document: 00514881108 Page: 4 Date Filed: 03/20/2019\n\n\n\n No. 17-60440\nStrickland v. Washington, 466 U.S. 668, 686 (1984) (recognizing that\nineffective assistance of counsel violates the Sixth Amendment); United States\nv. McDaniels, 907 F.3d 366, 370 (5th Cir. 2018) (“Where a defendant pleads\nguilty based on a promise by the prosecutor, ‘breach of that promise taints the\nvoluntariness of his plea’ and offends the Fifth Amendment.”) (quoting Davis\nv. Butler, 825 F.2d 892, 894 (5th Cir. 1987)). He also requests, at a minimum,\nan evidentiary hearing on his claims under 28 U.S.C. § 2255(b).\n We review the district court’s denial of § 2255 relief de novo, and its\ndenial of an evidentiary hearing for abuse of discretion. See United States v.\nReed, 719 F.3d 369, 373 (5th Cir. 2013) (citing United States v. Edwards, 442\nF.3d 258, 264 (5th Cir. 2006)). “A § 2255 motion requires an evidentiary\nhearing unless either (1) the movant’s claims are clearly frivolous or based\nupon unsupported generalizations, or (2) the movant would not be entitled to\nrelief as a matter of law, even if his factual assertions were true.” United States\nv. Harrison, 910 F.3d 824, 826–27 (5th Cir. 2018) (citing United States v.\nGuerra, 588 F.2d 519, 521 (5th Cir. 1979)).\n We conclude that Allen procedurally defaulted his breach of plea claim.\nHe is therefore only entitled to relief if he can succeed in his ineffective\nassistance claim—either as “cause” sufficient to excuse his procedural default\non his breach of plea claim, or as an independent ineffective counsel infirmity.\nWe conclude that the district court erred by not holding an evidentiary hearing\nor otherwise inquiring further into Allen’s ineffective counsel claim, because\nthe record does not “conclusively show” that that claim fails. 28 U.S.C.\n§ 2255(b).\n\n\n\n\n 4\n\f Case: 17-60440 Document: 00514881108 Page: 5 Date Filed: 03/20/2019\n\n\n\n No. 17-60440\n A.\n Allen has procedurally defaulted his claim that the government breached\nits plea obligations, by failing to present any such claim before the district\ncourt. 1\n “A movant is barred from raising . . . constitutional claims for the first\ntime on collateral review unless he demonstrates [1] cause for failing to raise\nthe issue on direct appeal and [2] actual prejudice resulting from the error.”\nUnited States v. Patten, 40 F.3d 774, 776 (5th Cir. 1994) (per curiam) (citing\nUnited States v. Pierce, 959 F.2d 1297, 1301 (5th Cir. 1992)). We may raise\nprocedural default sua sponte. See United States v. Willis, 273 F.3d 592, 597\n(5th Cir. 2001). We “should not do so lightly,” however. Id. (citing Rosario v.\nUnited States, 164 F.3d 729, 733 (2d Cir. 1998)). But when the petitioner is on\nnotice of the default bar, has had the opportunity to argue against it, and the\ngovernment has not waived the defense, it may be “proper to invoke the\nprocedural bar.” Id.\n Although Allen’s breach of plea claim is procedurally defaulted, whether\nthe government breached its plea obligations is something we must decide as\npart of Allen’s ineffective assistance claim. If the government did not breach\nthe plea agreement, then Allen’s counsel had nothing to respond to, and\ntherefore was not ineffective.\n B.\n To obtain relief, then, Allen must demonstrate that his counsel was\nconstitutionally ineffective—either to excuse his procedural default on his\nbreach of plea claim, or as a stand-alone ineffective counsel claim. See Patten,\n\n\n 1 Allen’s § 2255 motion only raised one ground for relief: ineffective assistance of\ncounsel. To be sure, Allen’s ineffective assistance claim depends on the government\nbreaching its plea obligations. But the district court considered Allen’s breach of plea claim\nas a stand-alone ground for relief. We likewise granted a certificate of appealability on the\nbreach of plea claim. We accordingly address it here.\n 5\n\f Case: 17-60440 Document: 00514881108 Page: 6 Date Filed: 03/20/2019\n\n\n\n No. 17-60440\n40 F.3d at 776 (citing Pierce, 959 F.2d at 1301); see also United States v.\nWalling, 982 F.2d 447, 449 (10th Cir. 1992) (“The Strickland ineffectiveness\ntest dovetails naturally with the cause and prejudice standard.”).\n To succeed on his ineffective assistance claim, Allen “must demonstrate\nthat (1) counsel’s representation fell below an objective standard of\nreasonableness and that (2) there is a reasonable probability that prejudice\nresulted.” Druery v. Thaler, 647 F.3d 535, 538 (5th Cir. 2011) (citing Bower v.\nQuarterman, 497 F.3d 459, 466 (5th Cir. 2007)). “[A] court must indulge a\nstrong presumption that counsel’s conduct falls within the wide range of\nreasonable professional assistance; that is, the defendant must overcome the\npresumption that, under the circumstances, the challenged action ‘might be\nconsidered sound trial strategy.’” Strickland, 466 U.S. at 689 (quoting Michel\nv. Louisiana, 350 U.S. 91, 101 (1955)). So mere disagreement about tactics\ndoes not amount to a constitutional infirmity. See id. at 690.\n We conclude that an evidentiary hearing is needed before we can decide\nwhether Allen’s representation was constitutionally deficient, based on the\nfailure to inform the court of Allen’s cooperation in the murder investigation.\n First, we must consider whether there was any error by the government\nthat could support an ineffective assistance claim.\n As for Allen’s undisputed cooperation in the related drug case, the\ndistrict court correctly concluded that the government did not breach the plea\nagreement. The PSR disclosed Allen’s cooperation in the drug case. And\nnothing in the plea agreement required the government to additionally raise\nAllen’s cooperation in the drug case at the sentencing hearing. 2\n\n\n\n 2 The cases Allen cites are inapposite. For example, in United States v. Hunter, the\nplea agreement expressly provided: “The United States agrees that it will recommend at\nsentencing that the Court reduce by two levels the sentencing guideline level applicable to\nthe defendant’s offense.” 835 F.3d 1320, 1323 (11th Cir. 2016) (emphasis added). And in\n 6\n\f Case: 17-60440 Document: 00514881108 Page: 7 Date Filed: 03/20/2019\n\n\n\n No. 17-60440\n As for Allen’s cooperation in the murder investigation, however, the\ngovernment never informed the court, either in the PSR or during the\nsentencing hearing. If indeed Allen cooperated with law enforcement in the\nmurder investigation, and if the government deemed his cooperation relevant\nto his sentencing, then the government was obligated to inform the sentencing\ncourt. Because there is some indication that the government did not discharge\nits burden, the district court should not have denied relief without inquiring\nfurther or holding an evidentiary hearing.\n The government argues that it did not “deem relevant” Allen’s\ncooperation because “it was the opinion of the case agent that his information\nwas not credible.” 3 In essence, the government contends that any decision not\nto inform the court about Allen’s cooperation was necessarily an exercise of the\ndiscretion allowed by the plea agreement. But the government had to actually\nexercise that discretion and determine that Allen’s cooperation was not\nrelevant—rather than simply refuse to inform the court about relevant\ninformation. According to Allen’s sworn statement, he “provided information\nin the unsolved murder case,” and “approximately two weeks after [his]\ncooperation, an arrest was made in the case.” Moreover, Allen contends that\nhis “counsel stated that [his counsel] had spoken with the case agent and\naffirmed that [Allen’s] information in regard to the murder was good and\nuseful.” So Allen has provided some evidence that the government considered\n\n\n\n\nCorreale v. United States, the court considered the government’s total failure to make the\nrecommendation it promised to make. See 479 F.2d 944, 946, 949 (1st Cir. 1973).\n 3 It is unclear whether the government was addressing Allen’s cooperation in the drug\n\ncase or the murder case. In its briefs before us, the government emphasizes that Allen has\nnot been clear about when he offered the information about the murder or whether it was\nuseful to investigators. True as far as it goes, the government’s response only highlights the\nquestions the district court should consider on remand. Thus, the government has failed to\nassert that Allen “would not be entitled to relief as a matter of law, even if his factual\nassertions were true.” Harrison, 910 F.3d at 826–27 (citing Guerra, 588 F.2d at 521).\n 7\n\f Case: 17-60440 Document: 00514881108 Page: 8 Date Filed: 03/20/2019\n\n\n\n No. 17-60440\nhis information credible. And without further explanation from the\ngovernment why the evidence was somehow not relevant to Allen’s sentence,\nthe government has not offered anything that “conclusively negate[s] the\nfactual predicates asserted in support of the motion for post-conviction relief.”\nFriedman v. United States, 588 F.2d 1010, 1015 (5th Cir. 1979) (explaining the\nrequirements of 28 U.S.C. § 2255(b)).\n Second, if there was a breach, Allen’s counsel’s failure to object to the\nbreach may have fallen “below an objective standard of reasonableness.”\nDruery, 647 F.3d at 538. In his affidavit, Allen’s counsel said that the PSR\nreflected Allen’s full cooperation with investigators, and that he did not raise\nAllen’s cooperation separately in the sentencing hearing because raising any\nmitigating factors would open a “Pandora’s box” of aggravating factors. But\nthe affidavit, at least on its face, does not address Allen’s contention about his\ncooperation in the murder investigation. Accordingly, we lack any “sworn\nrecord testimony from counsel explaining the strategy behind his decision.”\nUnited States v. Cavitt, 550 F.3d 430, 441 (5th Cir. 2008). So we cannot tell\nwhether Allen’s counsel believed the government breached its obligations\nunder the plea, or whether his failure to raise any purported breach was a\nstrategic decision. See, e.g., Herring v. Estelle, 491 F.2d 125, 128 (5th Cir. 1974)\n(“[A] lawyer who is not familiar with the facts and law relevant to his client’s\ncase cannot meet [the] required minimal level.”).\n Third, if there was a breach of the plea agreement, then Allen may have\nbeen prejudiced by his counsel’s failure to object to the breach. Allen contends\nthat the court might have imposed a lesser sentence had it known about the\nfull scope of his cooperation. To be sure, the district court concluded that “[i]t\nis pure conjecture that Allen’s sentence would have been lesser had Allen’s\ncounsel disclosed any purported additional cooperation not reflected in the\nPSR.” But the district court did not specifically consider Allen’s apparent\n 8\n\f Case: 17-60440 Document: 00514881108 Page: 9 Date Filed: 03/20/2019\n\n\n\n No. 17-60440\ncooperation in the murder investigation. Remand will allow the district court\nto consider Allen’s contention and determine whether this information would\nhave made Allen’s sentence “significantly less harsh.” Dale v. Quarterman,\n553 F.3d 876, 880 (5th Cir. 2008) (per curiam) (quoting Spriggs v. Collins, 993\nF.2d 85, 88–89 (5th Cir. 1993) (per curiam)).\n III.\n Once the district court holds an evidentiary hearing, it may turn out that\nthere was no violation—either because the government did not breach the plea\nagreement or because Allen’s counsel was not ineffective in failing to discover\nthe breach. But a “motion brought under 28 U.S.C. § 2255 can be denied\nwithout a hearing only if the motion, files, and records of the case conclusively\nshow that the prisoner is entitled to no relief.” Cavitt, 550 F.3d at 442 (internal\nquotation marks omitted) (quoting United States v. Bartholomew, 974 F.2d 39,\n41 (5th Cir. 1992) (per curiam)). Because that standard is not met here, we\nvacate the judgment and remand for an evidentiary hearing. The district court\nshould consider whether the government breached its obligation to inform the\ncourt about Allen’s cooperation in the murder case and, if it did, why Allen’s\ncounsel failed to raise the issue.\n\n\n\n\n 9\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Plaintiff-Appellee v. Calvin ALLEN, Defendant-Appellant\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-20\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 17-60440 Document: 00514881108 Page: 1 Date Filed: 03/20/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n No. 17-60440 FILED\\n March 20, 2019\\n Lyle W. Cayce\\nUNITED STATES OF AMERICA, Clerk\\n\\n Plaintiff - Appellee\\n\\nv.\\n\\nCALVIN ALLEN,\\n\\n Defendant - Appellant\\n\\n\\n\\n\\n Appeal from the United States District Court\\n for the Southern District of Mississippi\\n\\n\\nBefore HIGGINBOTHAM, ELROD, and HO, Circuit Judges.\\nJAMES C. HO, Circuit Judge:\\n Our court previously granted a certificate of appealability (COA) to\\nCalvin Allen on two claims—first, that the government breached its obligations\\nunder his plea agreement when it failed to credit his cooperation in a murder\\nconviction, and second, that Allen received ineffective assistance of counsel due\\nto his attorney’s failure to object to the government’s breach of his plea\\nagreement. We now conclude that the district court should have held an\\nevidentiary hearing on Allen’s ineffective counsel claim. Accordingly, we\\nvacate the judgment and remand for a limited evidentiary inquiry.\\n\\f Case: 17-60440 Document: 00514881108 Page: 2 Date Filed: 03/20/2019\\n\\n\\n\\n No. 17-60440\\n I.\\n Allen pleaded guilty to one count of conspiracy to possess with intent to\\ndistribute a controlled substance. In exchange for Allen’s plea and waiver of\\nthe right to appeal, the government promised that it would:\\n inform the United States Probation Office and the Court of [1] [the\\n plea agreement], [2] the nature and extent of Defendant’s activities\\n with respect to this case and [3] all other activities of Defendant\\n which the U.S. Attorney deems relevant to sentencing, including\\n the nature and extent of Defendant’s cooperation with the U.S.\\n Attorney and law enforcement.\\n\\n Allen cooperated with prosecutors, providing them with information\\nabout his co-conspirators in his drug case. He also provided information\\nleading to the prosecution of an unrelated murder.\\n The presentence report (PSR) included information about Allen’s\\ncooperation in the drug case, but not the murder. On appeal, Allen claims that\\nthis omission constitutes a breach of the plea agreement by the government.\\nBut Allen failed to identify any such breach to the district court: He did not\\nobject to the PSR. Nor did he object during the sentencing hearing. The court\\nsubsequently sentenced him to 188 months in prison and 5 years of supervised\\nrelease.\\n Allen filed a timely pro se motion to vacate, set aside, or correct his\\nsentence under 28 U.S.C. § 2255, alleging that he received ineffective\\nassistance of counsel. He asserted that the plea agreement obligated the\\ngovernment to inform the sentencing court about his cooperation in the murder\\ninvestigation, as well as the drug prosecution. And when the government\\nfailed to do so, Allen contends that his counsel should have either objected or\\nmoved for a downward departure in his sentence. In Allen’s view, this error\\npotentially deprived him of a lower sentence. He also requested an evidentiary\\nhearing on his claim under 28 U.S.C. § 2255(b).\\n\\n 2\\n\\f Case: 17-60440 Document: 00514881108 Page: 3 Date Filed: 03/20/2019\\n\\n\\n\\n No. 17-60440\\n The district court ordered Allen’s attorney to respond to the allegations\\nof ineffective counsel. Allen’s counsel averred that (1) he believed the\\ngovernment discharged its obligation under the plea because the PSR included\\ninformation about Allen’s cooperation; and (2) he and Allen decided not to move\\nfor a downward departure based on Allen’s cooperation because raising\\nmitigating circumstances would open the door to the court considering\\naggravating circumstances.\\n For its part, the government argued that (1) Allen procedurally defaulted\\non any claim that the government violated its plea; and (2) Allen’s counsel was\\nnot constitutionally ineffective.\\n The district court denied Allen’s motion without an evidentiary hearing,\\nafter concluding that (1) the government did not breach its plea obligations;\\nand (2) Allen’s ineffective assistance claim fails because his counsel’s failure to\\nobject was merely a tactical decision.\\n We subsequently granted a COA on two questions:\\n (1) “[W]hether the district court erred in denying without an\\n evidentiary hearing Allen’s claim that the Government breached\\n the plea agreement by failing to disclose his cooperation regarding\\n other criminal cases.”\\n\\n (2) “[W]hether the district court erred in denying without an\\n evidentiary hearing Allen’s claim that he received ineffective\\n assistance because his counsel failed to inform the sentencing\\n court of the Government’s failure to disclose his cooperation\\n regarding other criminal cases.”\\n\\n After the parties submitted their briefs, we requested additional briefing\\non whether Allen procedurally defaulted on his claim that the government\\nbreached its obligations under the plea agreement.\\n II.\\n Allen moved for § 2255 relief on the ground that the sentence was\\nimposed in violation of the Constitution. 28 U.S.C. § 2255(a). See also\\n 3\\n\\f Case: 17-60440 Document: 00514881108 Page: 4 Date Filed: 03/20/2019\\n\\n\\n\\n No. 17-60440\\nStrickland v. Washington, 466 U.S. 668, 686 (1984) (recognizing that\\nineffective assistance of counsel violates the Sixth Amendment); United States\\nv. McDaniels, 907 F.3d 366, 370 (5th Cir. 2018) (“Where a defendant pleads\\nguilty based on a promise by the prosecutor, ‘breach of that promise taints the\\nvoluntariness of his plea’ and offends the Fifth Amendment.”) (quoting Davis\\nv. Butler, 825 F.2d 892, 894 (5th Cir. 1987)). He also requests, at a minimum,\\nan evidentiary hearing on his claims under 28 U.S.C. § 2255(b).\\n We review the district court’s denial of § 2255 relief de novo, and its\\ndenial of an evidentiary hearing for abuse of discretion. See United States v.\\nReed, 719 F.3d 369, 373 (5th Cir. 2013) (citing United States v. Edwards, 442\\nF.3d 258, 264 (5th Cir. 2006)). “A § 2255 motion requires an evidentiary\\nhearing unless either (1) the movant’s claims are clearly frivolous or based\\nupon unsupported generalizations, or (2) the movant would not be entitled to\\nrelief as a matter of law, even if his factual assertions were true.” United States\\nv. Harrison, 910 F.3d 824, 826–27 (5th Cir. 2018) (citing United States v.\\nGuerra, 588 F.2d 519, 521 (5th Cir. 1979)).\\n We conclude that Allen procedurally defaulted his breach of plea claim.\\nHe is therefore only entitled to relief if he can succeed in his ineffective\\nassistance claim—either as “cause” sufficient to excuse his procedural default\\non his breach of plea claim, or as an independent ineffective counsel infirmity.\\nWe conclude that the district court erred by not holding an evidentiary hearing\\nor otherwise inquiring further into Allen’s ineffective counsel claim, because\\nthe record does not “conclusively show” that that claim fails. 28 U.S.C.\\n§ 2255(b).\\n\\n\\n\\n\\n 4\\n\\f Case: 17-60440 Document: 00514881108 Page: 5 Date Filed: 03/20/2019\\n\\n\\n\\n No. 17-60440\\n A.\\n Allen has procedurally defaulted his claim that the government breached\\nits plea obligations, by failing to present any such claim before the district\\ncourt. 1\\n “A movant is barred from raising . . . constitutional claims for the first\\ntime on collateral review unless he demonstrates [1] cause for failing to raise\\nthe issue on direct appeal and [2] actual prejudice resulting from the error.”\\nUnited States v. Patten, 40 F.3d 774, 776 (5th Cir. 1994) (per curiam) (citing\\nUnited States v. Pierce, 959 F.2d 1297, 1301 (5th Cir. 1992)). We may raise\\nprocedural default sua sponte. See United States v. Willis, 273 F.3d 592, 597\\n(5th Cir. 2001). We “should not do so lightly,” however. Id. (citing Rosario v.\\nUnited States, 164 F.3d 729, 733 (2d Cir. 1998)). But when the petitioner is on\\nnotice of the default bar, has had the opportunity to argue against it, and the\\ngovernment has not waived the defense, it may be “proper to invoke the\\nprocedural bar.” Id.\\n Although Allen’s breach of plea claim is procedurally defaulted, whether\\nthe government breached its plea obligations is something we must decide as\\npart of Allen’s ineffective assistance claim. If the government did not breach\\nthe plea agreement, then Allen’s counsel had nothing to respond to, and\\ntherefore was not ineffective.\\n B.\\n To obtain relief, then, Allen must demonstrate that his counsel was\\nconstitutionally ineffective—either to excuse his procedural default on his\\nbreach of plea claim, or as a stand-alone ineffective counsel claim. See Patten,\\n\\n\\n 1 Allen’s § 2255 motion only raised one ground for relief: ineffective assistance of\\ncounsel. To be sure, Allen’s ineffective assistance claim depends on the government\\nbreaching its plea obligations. But the district court considered Allen’s breach of plea claim\\nas a stand-alone ground for relief. We likewise granted a certificate of appealability on the\\nbreach of plea claim. We accordingly address it here.\\n 5\\n\\f Case: 17-60440 Document: 00514881108 Page: 6 Date Filed: 03/20/2019\\n\\n\\n\\n No. 17-60440\\n40 F.3d at 776 (citing Pierce, 959 F.2d at 1301); see also United States v.\\nWalling, 982 F.2d 447, 449 (10th Cir. 1992) (“The Strickland ineffectiveness\\ntest dovetails naturally with the cause and prejudice standard.”).\\n To succeed on his ineffective assistance claim, Allen “must demonstrate\\nthat (1) counsel’s representation fell below an objective standard of\\nreasonableness and that (2) there is a reasonable probability that prejudice\\nresulted.” Druery v. Thaler, 647 F.3d 535, 538 (5th Cir. 2011) (citing Bower v.\\nQuarterman, 497 F.3d 459, 466 (5th Cir. 2007)). “[A] court must indulge a\\nstrong presumption that counsel’s conduct falls within the wide range of\\nreasonable professional assistance; that is, the defendant must overcome the\\npresumption that, under the circumstances, the challenged action ‘might be\\nconsidered sound trial strategy.’” Strickland, 466 U.S. at 689 (quoting Michel\\nv. Louisiana, 350 U.S. 91, 101 (1955)). So mere disagreement about tactics\\ndoes not amount to a constitutional infirmity. See id. at 690.\\n We conclude that an evidentiary hearing is needed before we can decide\\nwhether Allen’s representation was constitutionally deficient, based on the\\nfailure to inform the court of Allen’s cooperation in the murder investigation.\\n First, we must consider whether there was any error by the government\\nthat could support an ineffective assistance claim.\\n As for Allen’s undisputed cooperation in the related drug case, the\\ndistrict court correctly concluded that the government did not breach the plea\\nagreement. The PSR disclosed Allen’s cooperation in the drug case. And\\nnothing in the plea agreement required the government to additionally raise\\nAllen’s cooperation in the drug case at the sentencing hearing. 2\\n\\n\\n\\n 2 The cases Allen cites are inapposite. For example, in United States v. Hunter, the\\nplea agreement expressly provided: “The United States agrees that it will recommend at\\nsentencing that the Court reduce by two levels the sentencing guideline level applicable to\\nthe defendant’s offense.” 835 F.3d 1320, 1323 (11th Cir. 2016) (emphasis added). And in\\n 6\\n\\f Case: 17-60440 Document: 00514881108 Page: 7 Date Filed: 03/20/2019\\n\\n\\n\\n No. 17-60440\\n As for Allen’s cooperation in the murder investigation, however, the\\ngovernment never informed the court, either in the PSR or during the\\nsentencing hearing. If indeed Allen cooperated with law enforcement in the\\nmurder investigation, and if the government deemed his cooperation relevant\\nto his sentencing, then the government was obligated to inform the sentencing\\ncourt. Because there is some indication that the government did not discharge\\nits burden, the district court should not have denied relief without inquiring\\nfurther or holding an evidentiary hearing.\\n The government argues that it did not “deem relevant” Allen’s\\ncooperation because “it was the opinion of the case agent that his information\\nwas not credible.” 3 In essence, the government contends that any decision not\\nto inform the court about Allen’s cooperation was necessarily an exercise of the\\ndiscretion allowed by the plea agreement. But the government had to actually\\nexercise that discretion and determine that Allen’s cooperation was not\\nrelevant—rather than simply refuse to inform the court about relevant\\ninformation. According to Allen’s sworn statement, he “provided information\\nin the unsolved murder case,” and “approximately two weeks after [his]\\ncooperation, an arrest was made in the case.” Moreover, Allen contends that\\nhis “counsel stated that [his counsel] had spoken with the case agent and\\naffirmed that [Allen’s] information in regard to the murder was good and\\nuseful.” So Allen has provided some evidence that the government considered\\n\\n\\n\\n\\nCorreale v. United States, the court considered the government’s total failure to make the\\nrecommendation it promised to make. See 479 F.2d 944, 946, 949 (1st Cir. 1973).\\n 3 It is unclear whether the government was addressing Allen’s cooperation in the drug\\n\\ncase or the murder case. In its briefs before us, the government emphasizes that Allen has\\nnot been clear about when he offered the information about the murder or whether it was\\nuseful to investigators. True as far as it goes, the government’s response only highlights the\\nquestions the district court should consider on remand. Thus, the government has failed to\\nassert that Allen “would not be entitled to relief as a matter of law, even if his factual\\nassertions were true.” Harrison, 910 F.3d at 826–27 (citing Guerra, 588 F.2d at 521).\\n 7\\n\\f Case: 17-60440 Document: 00514881108 Page: 8 Date Filed: 03/20/2019\\n\\n\\n\\n No. 17-60440\\nhis information credible. And without further explanation from the\\ngovernment why the evidence was somehow not relevant to Allen’s sentence,\\nthe government has not offered anything that “conclusively negate[s] the\\nfactual predicates asserted in support of the motion for post-conviction relief.”\\nFriedman v. United States, 588 F.2d 1010, 1015 (5th Cir. 1979) (explaining the\\nrequirements of 28 U.S.C. § 2255(b)).\\n Second, if there was a breach, Allen’s counsel’s failure to object to the\\nbreach may have fallen “below an objective standard of reasonableness.”\\nDruery, 647 F.3d at 538. In his affidavit, Allen’s counsel said that the PSR\\nreflected Allen’s full cooperation with investigators, and that he did not raise\\nAllen’s cooperation separately in the sentencing hearing because raising any\\nmitigating factors would open a “Pandora’s box” of aggravating factors. But\\nthe affidavit, at least on its face, does not address Allen’s contention about his\\ncooperation in the murder investigation. Accordingly, we lack any “sworn\\nrecord testimony from counsel explaining the strategy behind his decision.”\\nUnited States v. Cavitt, 550 F.3d 430, 441 (5th Cir. 2008). So we cannot tell\\nwhether Allen’s counsel believed the government breached its obligations\\nunder the plea, or whether his failure to raise any purported breach was a\\nstrategic decision. See, e.g., Herring v. Estelle, 491 F.2d 125, 128 (5th Cir. 1974)\\n(“[A] lawyer who is not familiar with the facts and law relevant to his client’s\\ncase cannot meet [the] required minimal level.”).\\n Third, if there was a breach of the plea agreement, then Allen may have\\nbeen prejudiced by his counsel’s failure to object to the breach. Allen contends\\nthat the court might have imposed a lesser sentence had it known about the\\nfull scope of his cooperation. To be sure, the district court concluded that “[i]t\\nis pure conjecture that Allen’s sentence would have been lesser had Allen’s\\ncounsel disclosed any purported additional cooperation not reflected in the\\nPSR.” But the district court did not specifically consider Allen’s apparent\\n 8\\n\\f Case: 17-60440 Document: 00514881108 Page: 9 Date Filed: 03/20/2019\\n\\n\\n\\n No. 17-60440\\ncooperation in the murder investigation. Remand will allow the district court\\nto consider Allen’s contention and determine whether this information would\\nhave made Allen’s sentence “significantly less harsh.” Dale v. Quarterman,\\n553 F.3d 876, 880 (5th Cir. 2008) (per curiam) (quoting Spriggs v. Collins, 993\\nF.2d 85, 88–89 (5th Cir. 1993) (per curiam)).\\n III.\\n Once the district court holds an evidentiary hearing, it may turn out that\\nthere was no violation—either because the government did not breach the plea\\nagreement or because Allen’s counsel was not ineffective in failing to discover\\nthe breach. But a “motion brought under 28 U.S.C. § 2255 can be denied\\nwithout a hearing only if the motion, files, and records of the case conclusively\\nshow that the prisoner is entitled to no relief.” Cavitt, 550 F.3d at 442 (internal\\nquotation marks omitted) (quoting United States v. Bartholomew, 974 F.2d 39,\\n41 (5th Cir. 1992) (per curiam)). Because that standard is not met here, we\\nvacate the judgment and remand for an evidentiary hearing. The district court\\nshould consider whether the government breached its obligation to inform the\\ncourt about Allen’s cooperation in the murder case and, if it did, why Allen’s\\ncounsel failed to raise the issue.\\n\\n\\n\\n\\n 9\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1094,"cells":{"id":{"kind":"number","value":4601859,"string":"4,601,859"},"name":{"kind":"string","value":"BP EXPLORATION & PRODUCTION, INCORPORATED; BP America Production Company; BP, P.L.C., Requesting Parties-Appellants, v. CLAIMANT ID 100281817, Objecting Party-Appellee."},"name_abbreviation":{"kind":"string","value":"BP Exploration & Prodn, Inc. v. ID"},"decision_date":{"kind":"string","value":"2019-03-20"},"docket_number":{"kind":"string","value":"18-30394"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Jones, Haynes, Oldham\", \"parties\": \"\", \"opinions\": [{\"author\": \"ANDREW S. OLDHAM, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 18-30394 Document: 00514881236 Page: 1 Date Filed: 03/20/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n March 20, 2019\\n No. 18-30394\\n Lyle W. Cayce\\n Clerk\\n\\nBP EXPLORATION & PRODUCTION, INCORPORATED; BP AMERICA\\nPRODUCTION COMPANY; BP, P.L.C.,\\n\\n Requesting Parties-Appellants,\\n\\nv.\\n\\nCLAIMANT ID 100281817,\\n\\n Objecting Party-Appellee.\\n\\n\\n\\n Appeal from the United States District Court\\n for the Eastern District of Louisiana\\n\\n\\nBefore JONES, HAYNES, and OLDHAM, Circuit Judges.\\nANDREW S. OLDHAM, Circuit Judge:\\n An NBA player named David West negotiated a contract with the New\\nOrleans Hornets before the Deepwater Horizon oil spill. He received every\\npenny specified in that contract both before and after the spill. Still, the\\nClaims Administrator for the Deepwater Horizon Economic and Property\\nDamages Settlement Agreement awarded West almost $1.5 million in “lost”\\nearnings. The Settlement Appeal Panel affirmed, and the district court denied\\ndiscretionary review. We reverse.\\n I.\\n The Deepwater Horizon oil rig exploded on April 20, 2010. At that time,\\nDavid West played professional basketball for the New Orleans Hornets (now\\n\\n Case: 18-30394 Document: 00514881236 Page: 2 Date Filed: 03/20/2019\\n\\n\\n\\n No. 18-30394\\nknown as the New Orleans Pelicans). He was four years into a five-year\\ncontract. That contract paid West a total of $45 million. But it was “front-\\nloaded,” meaning West’s annual salary decreased every year of the contract—\\nincluding from 2009 to 2010. West received all $45 million owed to him under\\nthe contract.\\n Still, he submitted an “Individual Economic Loss Claim” under the\\nDeepwater Horizon Economic and Property Damages Settlement Agreement\\n(“Settlement”). 1 These claims can be submitted only by individuals “who seek\\ncompensation for lost earnings from employment due to or resulting from the\\n[Deepwater Horizon] Spill.” Settlement Agreement Ex. 8A at 1 (emphasis\\nadded). And the Individual Economic Loss Claim form states, on its very first\\npage, that it covers only “individuals who have experienced income losses\\ncaused by the Spill.” Individual Economic Loss Claim Form 1 (emphasis\\nadded). It also required West to certify “that the information provided in [his]\\nClaim Form [was] true and accurate to the best of [his] knowledge.” Id. at 15.\\nBased on that attestation, the Claims Administrator used West’s tax forms to\\ncalculate his “lost earnings.” The Claims Administrator determined West was\\nentitled to $1,412,673.06. BP contested that determination because West “lost”\\nnothing—he received all the money promised by the front-loaded terms of his\\npre-spill contract.\\n BP first sought reversal before the Appeal Panel. It argued West was\\nnot entitled to any award under the Agreement because (1) Individual\\nEconomic Loss Claimants can recover only if they experienced a loss caused by\\nthe spill, and (2) West cannot satisfy the Settlement’s attestation\\n\\n\\n 1In previous cases, we have discussed the Deepwater Horizon oil spill and resulting\\nsettlement at great length. See, e.g., In re Deepwater Horizon (Deepwater Horizon III ), 744\\nF.3d 370 (5th Cir. 2014); In re Deepwater Horizon (Deepwater Horizon II ), 739 F.3d 790 (5th\\nCir. 2014); In re Deepwater Horizon (Deepwater Horizon I ), 732 F.3d 326 (5th Cir. 2013). We\\ntherefore need not recount that history here.\\n 2\\n\\n Case: 18-30394 Document: 00514881236 Page: 3 Date Filed: 03/20/2019\\n\\n\\n\\n No. 18-30394\\nrequirements. The Appeal Panel affirmed West’s award. It concluded West\\nestablished causation because his employer—the Hornets—benefited from\\npresumed causation under the Settlement. It therefore held West needed\\nnothing more to claim “lost” earnings.\\n BP asked the district court to review the award decision. But the court\\ndenied discretionary review without explanation. BP timely appealed.\\n II.\\n Our review is for abuse of discretion. Holmes Motors, Inc. v. BP Expl. &\\nProd., Inc., 829 F.3d 313, 315 (5th Cir. 2016). The district court abuses its\\ndiscretion when “the decision not reviewed by the district court actually\\ncontradicted or misapplied the Settlement Agreement, or had the clear\\npotential to contradict or misapply the Settlement Agreement.” Ibid.\\n(quotation omitted). It’s likewise “an abuse of discretion to deny a request for\\nreview that raises a recurring issue on which the Appeal Panels are split if the\\nresolution of the question will substantially impact the administration of the\\nAgreement.” Claimant ID 100212278 v. BP Expl. & Prod., Inc., 848 F.3d 407,\\n410 (5th Cir. 2017) (per curiam) (quotation omitted). In contrast, denying “a\\nrequest for review that involve[s] no pressing question of how the Settlement\\nAgreement should be interpreted or implemented, but simply raise[s] the\\ncorrectness of a discretionary administrative decision in the facts of a single\\nclaimant’s case,” does not amount to an abuse of discretion. Ibid. (quotation\\nomitted) (alterations in original).\\n That said, the Settlement Agreement is a contract. The proper\\ninterpretation of it “is a question of law.” In re Deepwater Horizon (Deepwater\\nHorizon I ), 732 F.3d 326, 345 (5th Cir. 2013). And making “an error of law\\nconstitutes an abuse of discretion.” In re Deepwater Horizon, 785 F.3d 986, 999\\n(5th Cir. 2015). Accordingly, when the district court is “presented with purely\\n\\n\\n 3\\n\\n Case: 18-30394 Document: 00514881236 Page: 4 Date Filed: 03/20/2019\\n\\n\\n\\n No. 18-30394\\nlegal questions of contract interpretation,” our review is de novo. In re\\nDeepwater Horizon, 785 F.3d 1003, 1011 (5th Cir. 2015).\\n A.\\n We start with the contractual provisions governing West’s claim. West\\nsubmitted a specific type of claim—an “Individual Economic Loss Claim.” It is\\ndefined to include a claim brought by an individual described in Exhibit 8A.\\nExhibit 8A, in turn, provides the following description for Individual Economic\\nLoss Claims:\\n Individual economic loss claims are claims by Individuals, who\\n shall be defined as (i) Natural Persons who (a) satisfy (or whose\\n employers satisfy) the Class Definition and (b) whose losses are not\\n excluded from the Class and (ii) who seek compensation for lost\\n earnings from employment due to or resulting from the [Deepwater\\n Horizon oil spill] . . . .\\nSettlement Agreement Ex. 8A at 1 (emphases added). The claim form that\\nWest submitted similarly stated: “The Individual Economic Loss Claim is for\\nindividuals who have experienced income losses caused by the Spill.”\\nIndividual Economic Loss Claim Form 1 (emphasis added). Thus, these types\\nof claims may be brought only by individuals who experienced losses and seek\\ncompensation for lost earnings caused by the oil spill. We’ve previously\\ninterpreted the Agreement as allowing “proof of loss as a substitute for proof\\nof causation.” In re Deepwater (Deepwater Horizon III ), 744 F.3d 370, 375 (5th\\nCir. 2014). But what do “loss” and “lost earnings” mean?\\n They are undefined in the Settlement, so we look to their plain meaning.\\nSee BP Expl. & Prod., Inc. v. Claimant ID 100094497, 910 F.3d 797, 801 (5th\\nCir. 2018). “Loss” typically means “the disappearance or diminution of\\nvalue . . . in an unexpected or relatively unpredictable way.” Loss, BLACK’S\\nLAW DICTIONARY (10th ed. 2014); see also Economic Loss, BLACK’S LAW\\nDICTIONARY (10th ed. 2014) (explaining “economic loss” means “monetary loss\\nsuch as lost wages or lost profits” and usually “refers to a type of damages\\n 4\\n\\n Case: 18-30394 Document: 00514881236 Page: 5 Date Filed: 03/20/2019\\n\\n\\n\\n No. 18-30394\\nrecoverable in a lawsuit”). And “lost earnings” refers to “[w]ages, salary, or\\nother income that a person could have earned if he or she had not lost a job,\\nsuffered a disabling injury, or died.” Earnings, BLACK’S LAW DICTIONARY (10th\\ned. 2014). These definitions suggest “loss” or “lost earnings” are unexpected\\ndiminutions in wages or other income that could otherwise support a claim for\\ncivil damages.\\n West argues these plain meanings of “loss” and “lost earnings” do not\\napply. Instead, he says, his “loss” is proved by the seven-step mathematical\\nequation that appears in Exhibit 8A. But that puts the cart before the horse.\\nOnly claimants who suffer unexpected damages can submit an Individual\\nEconomic Loss Claim; then they use Exhibit 8A’s equation to determine the\\nvalue of that claim. The defined terms in the seven-step equation make that\\nclear. “Claimant Lost Earnings” is defined as “[t]he claimant’s Expected\\nEarnings from all Claiming Jobs minus the claimant’s Actual Earnings\\nfrom all Claiming Jobs during the Compensation Period, minus any\\nOffsetting Earnings.” Settlement Agreement Ex. 8A at 4. “Expected\\nEarnings” refers to the “[c]laimant’s earnings in the Compensation Period\\nin the Claiming Job that would have been expected in the absence of the\\n[Deepwater Horizon] Spill.” Id. at 5 (emphasis added). West expected to earn\\nin the absence of the spill precisely what he did earn after it. He therefore did\\nnot suffer unexpected damages, and Exhibit 8A does not apply to him. 2\\n\\n\\n 2 Because West’s expected earnings equal his actual earnings based on Exhibit 8A’s\\ndefinitions, West ignores them. (Indeed, he does not even include the Agreement’s definition\\nof “Expected Earnings” in his brief.) He instead implies “Expected Earnings” is defined in\\nExhibit 8A as a calculation based on what he earned in previous time periods, not what his\\nfive-year contract provided. And applying that “definition,” West’s expected earnings would\\nbe higher than his actual earnings. But we cannot focus exclusively on Exhibit 8A’s\\ncalculations and ignore its list of defined terms and accompanying definitions. Instead, we\\nmust read the Agreement’s provisions “as a whole,” Claimant ID 100094497, 910 F.3d at 801,\\nand harmonize the Agreement—giving effect to all its terms “without rendering any of them\\n\\n 5\\n\\n Case: 18-30394 Document: 00514881236 Page: 6 Date Filed: 03/20/2019\\n\\n\\n\\n No. 18-30394\\n This interpretation comports not only with the Agreement’s text, but also\\nwith our precedent. As we explained in Deepwater Horizon I, when\\ninterpreting the Agreement, we must give “some weight” to “what damages\\nrecoverable in civil litigation actually are.” 732 F.3d at 339. And in civil\\nlitigation, the plaintiff can recover damages only after suffering actual losses.\\nSee Lewis v. Casey, 518 U.S. 343, 349 (1996) (explaining the court’s role is\\nlimited to “provid[ing] relief to claimants, in individual or class actions, who\\nhave suffered, or will imminently suffer, actual harm”).\\n B.\\n West did not suffer actual and unexpected “losses” or damages. In 2010,\\nhe earned exactly what he was entitled to receive under his contract. The fact\\nthat West received less money in 2010 than in 2009 does not mean he “lost”\\nanything or was “damaged” in any way. It means only he agreed to a front-\\nloaded contract. And he did so many years before the Deepwater Horizon\\ncatastrophe.\\n The decision to give money to West “actually contradicted or misapplied\\nthe Settlement Agreement.” Holmes Motors, 829 F.3d at 315 (quotation\\nomitted). Our holding to that effect answers a “purely legal question[ ] of\\ncontract interpretation.” In re Deepwater Horizon, 785 F.3d at 1011.\\nAccordingly, “remand is unnecessary.” Aransas Project v. Shaw, 775 F.3d 641,\\n658 (5th Cir. 2014) (per curiam); cf. United States v. Douglas, 696 F. App’x 666,\\n669 (5th Cir. 2017) (per curiam) (“In certain circumstances, however, the\\nappellate court may determine that remand of a particular case is unnecessary\\nand instead, simply reverse and render.”); United States v. Hernandez-\\n\\n\\n\\nmeaningless or superfluous,” Chembulk Trading LLC v. Chemex Ltd., 393 F.3d 550, 555 (5th\\nCir. 2004). The fact that the definition of “Expected Earnings” cannot be squared with the\\ncalculation as applied to West’s claim further illustrates the compensation formula does not\\napply to him. It applies only to eligible individuals—those who suffered unexpected damages.\\n 6\\n\\n Case: 18-30394 Document: 00514881236 Page: 7 Date Filed: 03/20/2019\\n\\n\\n\\n No. 18-30394\\nGuevara, 162 F.3d 863, 878 (5th Cir. 1998) (“[W]e need not waste judicial\\nresources by remanding for what undoubtedly would be a rote resentencing.”).\\n The judgment of the district court is REVERSED.\\n\\n\\n\\n\\n 7\\n\\n Case: 18-30394 Document: 00514881236 Page: 8 Date Filed: 03/20/2019\\n\\n\\n\\n No. 18-30394\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4379112/\", \"author_raw\": \"ANDREW S. OLDHAM, Circuit Judge:\"}, {\"author\": \"HAYNES, Circuit Judge, concurring\", \"type\": \"concurrence\", \"text\": \"HAYNES, Circuit Judge, concurring and dissenting:\\n\\n I concur in the portion of the judgment reversing the district\\ncourt’s denial of review and the determination by the majority opinion that the\\nparticular sums awarded, which rely upon the contractual losses, reflect a\\n“loss” that was not caused by the oil spill. However, I would stop there and\\nremand the case to the district court.\\n As the majority opinion explains, the question before us is whether the\\ndistrict court abused its discretion in not reviewing the Appeal Panel’s decision\\nbecause there was an erroneous interpretation of the Settlement Agreement\\nimpacting the settlement as a whole. Holmes Motors, Inc. v. BP Expl. & Prod.,\\n829 F.3d 313, 315 (5th Cir. 2016). We answer that “yes.” The remedy, then, is\\nto send it back to the district court to review the case consistent with our\\nanalysis. BP Expl. & Prod. Inc. v. Claimant ID 100094497, 910 F.3d 797, 803\\n(5th Cir. 2018) (remanding to the district court even though the majority\\nopinion (in the face of a dissenting opinion) decided a legal question); see also\\nIn re Deepwater Horizon, 632 F. App’x 199, 204 (5th Cir. 2015) (per curiam)\\n(remanding where district court refused to review issues that would arise\\nrepeatedly); cf. Claimant ID 100227611 v. BP Expl. & Prod., No. 18-30396,\\n2018 U.S. App. LEXIS 33357, at *6 (5th Cir. Nov. 28, 2018) (per curiam)\\n(declining to overturn the refusal of discretionary review 1 when the case\\ninvolved a decision on “the facts of a single claimant’s case”); see generally\\n\\n\\n\\n 1 While the legal question may be reviewed “de novo,” even a “legal error” should not\\ncause us to reverse a denial of discretionary review that involves just a single claim or does\\nnot negate relevant portions of the Settlement Agreement. In other words, whether a legal\\nerror is made is not discretionary but whether to grant discretionary review of a legal error\\nis discretionary. Here, however, the district court’s failure to address this glaring legal error\\ninvolves the very heart of the Settlement Agreement, so denial of review was an abuse of\\ndiscretion.\\n 8\\n\\n Case: 18-30394 Document: 00514881236 Page: 9 Date Filed: 03/20/2019\\n\\n\\n\\n No. 18-30394\\nSanchez v. Young Cty., 866 F.3d 274, 279 (5th Cir. 2017) (per curiam) (“In\\ndeference to the trial court’s responsibility to review the record in the first\\ninstance, we vacate and remand . . . .”). Yet the majority opinion does not.\\n Would a remand be based upon a mere technicality and, in turn, be a\\nwaste of time here because it is a purely legal question? No.\\n There are additional factual questions here. The question of whether the\\nparticular contractual “loss” approved by the Claims Administrator is fundable\\nunder the Settlement Agreement is, perhaps, a pure legal question. But West\\nraises arguments concerning losses beyond the “do the math” arguments we\\nrejected. If I were a factfinder, I would be unpersuaded by his arguments. But,\\nas appellate judges, we are not factfinders in this case. Accordingly, we should\\nremand to the district court to review and make any necessary determinations\\nin the first instance (or, in turn, remand for factual investigation by the Claims\\nAdministrator), including determination of whether arguments were properly\\nraised or forfeited.\\n The decision not to remand ignores the reality of how these Settlement\\nAgreement cases proceed and the history of this specific case. Throughout the\\nproceedings below, the question was whether the Claims Administrator,\\nAppeals Panel, and District Court can or should “pierce the veil” of the\\nclaimant’s application which, on its face, undeniably demonstrated a loss. At\\neach stage, West successfully argued, “No, there should be no piercing,”\\nmeaning he had no reason to provide evidence of any other theory of recovery;\\nthe whole point was that the document to which he attested stands as is. He\\nprevailed repeatedly on that theory as numerous others had and still do. We\\nhave now, for the first time, found a case that we only theorized about in earlier\\ndecisions, the “implausible” causation case (“implausible” being a nice way of\\nputting it here). See In re Deepwater Horizon, 744 F.3d 370, 377–78 (5th Cir.\\n 9\\n\\n Case: 18-30394 Document: 00514881236 Page: 10 Date Filed: 03/20/2019\\n\\n\\n\\n No. 18-30394\\n2014). But that case specifically stated: “The claims administrator, parties,\\nand district court can resolve real examples of implausible claims as they\\nresolve other questions that arise in the handling of specific claims.” Id.\\n(emphasis added). Nothing in that opinion suggested making the Fifth Circuit\\nthe factfinder.\\n Indeed, BP has stipulated that causation arguments are preserved in\\nthis context. The stipulation states: “BP and Class counsel further agree that,\\nfor any Deepwater Horizon Court-Supervised Settlement Program appeal,\\nrequest for discretionary review, or appeal to the Fifth Circuit Court in which\\nthe attestation issue is raised, the Claimant will be deemed to have preserved,\\nand not waived, any argument that BP is estopped from challenging the\\nattestation . . . , as well as any other appropriate argument and/or objection\\nrelevant to the question of causation.” (emphasis added). BP acknowledged that\\nstipulation in its briefing to the Appeals Panel in this very case: “Pursuant to\\nthe stipulation entered into between BP and the Class . . . , BP is preserving\\n[the attestation requirement] issue for further review but does not brief it\\nfurther herein.” BP’s footnote to that statement suggests that it did not expect\\nWest to address this argument. This case is thus not one of the “mine-run” of\\nforfeiture or waiver cases where a litigant should have raised an issue sooner\\nbut failed to do so. 2\\n Finally, perhaps for the above reasons, BP did not request that we\\n“reverse and render.” It only asked for a remand: “For the foregoing reasons,\\nthe district court’s denial of discretionary review should be reversed and\\n\\n\\n 2 Indeed, the entire record on appeal is very thinly developed beyond BP citing to\\narticles about the contract in question, and West not denying the fact of the contract but\\narguing its irrelevance. BP itself put into evidence the article West relies upon to show that\\nhe had a potential for a future lucrative contract. Thus, the thin record provides some\\nsupport for West’s argument.\\n 10\\n\\n Case: 18-30394 Document: 00514881236 Page: 11 Date Filed: 03/20/2019\\n\\n\\n\\n No. 18-30394\\nremanded.” “[A] party is bound by, or limited to, the relief it seeks on appeal.”\\nWhitehead v. Food Max, Inc., 163 F.3d 265, 270 (5th Cir. 1998); see also\\nHolloway v. Purvis, 680 F. App’x 282, 286 (5th Cir. 2017) (“[O]ur precedent\\nstates that parties are limited to the relief requested in their briefs.”) Thus,\\nwe must remand, not render.\\n In sum, our usual course is to remand to the district court to resolve\\noutstanding factual issues and failing to do so on this procedural history is\\nparticularly inappropriate. Our precedent also requires that we not grant\\nmore relief than requested by rendering when only remand was sought. I\\nwould reverse and remand to the district court. Because the majority opinion\\nleaves out this important step, I respectfully dissent from that portion of the\\nopinion and resulting judgment.\\n\\n\\n\\n\\n 11\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4379112/\", \"author_raw\": \"HAYNES, Circuit Judge, concurring\"}]}"},"judge1":{"kind":"string","value":"JONES"},"judge2":{"kind":"string","value":"HAYNES"},"judge3":{"kind":"string","value":"OLDHAM"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":2,"string":"2"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":1,"string":"1"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4601859/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: BP EXPLORATION & PRODUCTION, INCORPORATED; BP America Production Company; BP, P.L.C., Requesting Parties-Appellants, v. CLAIMANT ID 100281817, Objecting Party-Appellee.\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-20\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: Yes\nAdditional notes: \n\n[CASE_TEXT]\nCase: 18-30394 Document: 00514881236 Page: 1 Date Filed: 03/20/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT United States Court of Appeals\n Fifth Circuit\n\n FILED\n March 20, 2019\n No. 18-30394\n Lyle W. Cayce\n Clerk\n\nBP EXPLORATION & PRODUCTION, INCORPORATED; BP AMERICA\nPRODUCTION COMPANY; BP, P.L.C.,\n\n Requesting Parties-Appellants,\n\nv.\n\nCLAIMANT ID 100281817,\n\n Objecting Party-Appellee.\n\n\n\n Appeal from the United States District Court\n for the Eastern District of Louisiana\n\n\nBefore JONES, HAYNES, and OLDHAM, Circuit Judges.\nANDREW S. OLDHAM, Circuit Judge:\n An NBA player named David West negotiated a contract with the New\nOrleans Hornets before the Deepwater Horizon oil spill. He received every\npenny specified in that contract both before and after the spill. Still, the\nClaims Administrator for the Deepwater Horizon Economic and Property\nDamages Settlement Agreement awarded West almost $1.5 million in “lost”\nearnings. The Settlement Appeal Panel affirmed, and the district court denied\ndiscretionary review. We reverse.\n I.\n The Deepwater Horizon oil rig exploded on April 20, 2010. At that time,\nDavid West played professional basketball for the New Orleans Hornets (now\n\n Case: 18-30394 Document: 00514881236 Page: 2 Date Filed: 03/20/2019\n\n\n\n No. 18-30394\nknown as the New Orleans Pelicans). He was four years into a five-year\ncontract. That contract paid West a total of $45 million. But it was “front-\nloaded,” meaning West’s annual salary decreased every year of the contract—\nincluding from 2009 to 2010. West received all $45 million owed to him under\nthe contract.\n Still, he submitted an “Individual Economic Loss Claim” under the\nDeepwater Horizon Economic and Property Damages Settlement Agreement\n(“Settlement”). 1 These claims can be submitted only by individuals “who seek\ncompensation for lost earnings from employment due to or resulting from the\n[Deepwater Horizon] Spill.” Settlement Agreement Ex. 8A at 1 (emphasis\nadded). And the Individual Economic Loss Claim form states, on its very first\npage, that it covers only “individuals who have experienced income losses\ncaused by the Spill.” Individual Economic Loss Claim Form 1 (emphasis\nadded). It also required West to certify “that the information provided in [his]\nClaim Form [was] true and accurate to the best of [his] knowledge.” Id. at 15.\nBased on that attestation, the Claims Administrator used West’s tax forms to\ncalculate his “lost earnings.” The Claims Administrator determined West was\nentitled to $1,412,673.06. BP contested that determination because West “lost”\nnothing—he received all the money promised by the front-loaded terms of his\npre-spill contract.\n BP first sought reversal before the Appeal Panel. It argued West was\nnot entitled to any award under the Agreement because (1) Individual\nEconomic Loss Claimants can recover only if they experienced a loss caused by\nthe spill, and (2) West cannot satisfy the Settlement’s attestation\n\n\n 1In previous cases, we have discussed the Deepwater Horizon oil spill and resulting\nsettlement at great length. See, e.g., In re Deepwater Horizon (Deepwater Horizon III ), 744\nF.3d 370 (5th Cir. 2014); In re Deepwater Horizon (Deepwater Horizon II ), 739 F.3d 790 (5th\nCir. 2014); In re Deepwater Horizon (Deepwater Horizon I ), 732 F.3d 326 (5th Cir. 2013). We\ntherefore need not recount that history here.\n 2\n\n Case: 18-30394 Document: 00514881236 Page: 3 Date Filed: 03/20/2019\n\n\n\n No. 18-30394\nrequirements. The Appeal Panel affirmed West’s award. It concluded West\nestablished causation because his employer—the Hornets—benefited from\npresumed causation under the Settlement. It therefore held West needed\nnothing more to claim “lost” earnings.\n BP asked the district court to review the award decision. But the court\ndenied discretionary review without explanation. BP timely appealed.\n II.\n Our review is for abuse of discretion. Holmes Motors, Inc. v. BP Expl. &\nProd., Inc., 829 F.3d 313, 315 (5th Cir. 2016). The district court abuses its\ndiscretion when “the decision not reviewed by the district court actually\ncontradicted or misapplied the Settlement Agreement, or had the clear\npotential to contradict or misapply the Settlement Agreement.” Ibid.\n(quotation omitted). It’s likewise “an abuse of discretion to deny a request for\nreview that raises a recurring issue on which the Appeal Panels are split if the\nresolution of the question will substantially impact the administration of the\nAgreement.” Claimant ID 100212278 v. BP Expl. & Prod., Inc., 848 F.3d 407,\n410 (5th Cir. 2017) (per curiam) (quotation omitted). In contrast, denying “a\nrequest for review that involve[s] no pressing question of how the Settlement\nAgreement should be interpreted or implemented, but simply raise[s] the\ncorrectness of a discretionary administrative decision in the facts of a single\nclaimant’s case,” does not amount to an abuse of discretion. Ibid. (quotation\nomitted) (alterations in original).\n That said, the Settlement Agreement is a contract. The proper\ninterpretation of it “is a question of law.” In re Deepwater Horizon (Deepwater\nHorizon I ), 732 F.3d 326, 345 (5th Cir. 2013). And making “an error of law\nconstitutes an abuse of discretion.” In re Deepwater Horizon, 785 F.3d 986, 999\n(5th Cir. 2015). Accordingly, when the district court is “presented with purely\n\n\n 3\n\n Case: 18-30394 Document: 00514881236 Page: 4 Date Filed: 03/20/2019\n\n\n\n No. 18-30394\nlegal questions of contract interpretation,” our review is de novo. In re\nDeepwater Horizon, 785 F.3d 1003, 1011 (5th Cir. 2015).\n A.\n We start with the contractual provisions governing West’s claim. West\nsubmitted a specific type of claim—an “Individual Economic Loss Claim.” It is\ndefined to include a claim brought by an individual described in Exhibit 8A.\nExhibit 8A, in turn, provides the following description for Individual Economic\nLoss Claims:\n Individual economic loss claims are claims by Individuals, who\n shall be defined as (i) Natural Persons who (a) satisfy (or whose\n employers satisfy) the Class Definition and (b) whose losses are not\n excluded from the Class and (ii) who seek compensation for lost\n earnings from employment due to or resulting from the [Deepwater\n Horizon oil spill] . . . .\nSettlement Agreement Ex. 8A at 1 (emphases added). The claim form that\nWest submitted similarly stated: “The Individual Economic Loss Claim is for\nindividuals who have experienced income losses caused by the Spill.”\nIndividual Economic Loss Claim Form 1 (emphasis added). Thus, these types\nof claims may be brought only by individuals who experienced losses and seek\ncompensation for lost earnings caused by the oil spill. We’ve previously\ninterpreted the Agreement as allowing “proof of loss as a substitute for proof\nof causation.” In re Deepwater (Deepwater Horizon III ), 744 F.3d 370, 375 (5th\nCir. 2014). But what do “loss” and “lost earnings” mean?\n They are undefined in the Settlement, so we look to their plain meaning.\nSee BP Expl. & Prod., Inc. v. Claimant ID 100094497, 910 F.3d 797, 801 (5th\nCir. 2018). “Loss” typically means “the disappearance or diminution of\nvalue . . . in an unexpected or relatively unpredictable way.” Loss, BLACK’S\nLAW DICTIONARY (10th ed. 2014); see also Economic Loss, BLACK’S LAW\nDICTIONARY (10th ed. 2014) (explaining “economic loss” means “monetary loss\nsuch as lost wages or lost profits” and usually “refers to a type of damages\n 4\n\n Case: 18-30394 Document: 00514881236 Page: 5 Date Filed: 03/20/2019\n\n\n\n No. 18-30394\nrecoverable in a lawsuit”). And “lost earnings” refers to “[w]ages, salary, or\nother income that a person could have earned if he or she had not lost a job,\nsuffered a disabling injury, or died.” Earnings, BLACK’S LAW DICTIONARY (10th\ned. 2014). These definitions suggest “loss” or “lost earnings” are unexpected\ndiminutions in wages or other income that could otherwise support a claim for\ncivil damages.\n West argues these plain meanings of “loss” and “lost earnings” do not\napply. Instead, he says, his “loss” is proved by the seven-step mathematical\nequation that appears in Exhibit 8A. But that puts the cart before the horse.\nOnly claimants who suffer unexpected damages can submit an Individual\nEconomic Loss Claim; then they use Exhibit 8A’s equation to determine the\nvalue of that claim. The defined terms in the seven-step equation make that\nclear. “Claimant Lost Earnings” is defined as “[t]he claimant’s Expected\nEarnings from all Claiming Jobs minus the claimant’s Actual Earnings\nfrom all Claiming Jobs during the Compensation Period, minus any\nOffsetting Earnings.” Settlement Agreement Ex. 8A at 4. “Expected\nEarnings” refers to the “[c]laimant’s earnings in the Compensation Period\nin the Claiming Job that would have been expected in the absence of the\n[Deepwater Horizon] Spill.” Id. at 5 (emphasis added). West expected to earn\nin the absence of the spill precisely what he did earn after it. He therefore did\nnot suffer unexpected damages, and Exhibit 8A does not apply to him. 2\n\n\n 2 Because West’s expected earnings equal his actual earnings based on Exhibit 8A’s\ndefinitions, West ignores them. (Indeed, he does not even include the Agreement’s definition\nof “Expected Earnings” in his brief.) He instead implies “Expected Earnings” is defined in\nExhibit 8A as a calculation based on what he earned in previous time periods, not what his\nfive-year contract provided. And applying that “definition,” West’s expected earnings would\nbe higher than his actual earnings. But we cannot focus exclusively on Exhibit 8A’s\ncalculations and ignore its list of defined terms and accompanying definitions. Instead, we\nmust read the Agreement’s provisions “as a whole,” Claimant ID 100094497, 910 F.3d at 801,\nand harmonize the Agreement—giving effect to all its terms “without rendering any of them\n\n 5\n\n Case: 18-30394 Document: 00514881236 Page: 6 Date Filed: 03/20/2019\n\n\n\n No. 18-30394\n This interpretation comports not only with the Agreement’s text, but also\nwith our precedent. As we explained in Deepwater Horizon I, when\ninterpreting the Agreement, we must give “some weight” to “what damages\nrecoverable in civil litigation actually are.” 732 F.3d at 339. And in civil\nlitigation, the plaintiff can recover damages only after suffering actual losses.\nSee Lewis v. Casey, 518 U.S. 343, 349 (1996) (explaining the court’s role is\nlimited to “provid[ing] relief to claimants, in individual or class actions, who\nhave suffered, or will imminently suffer, actual harm”).\n B.\n West did not suffer actual and unexpected “losses” or damages. In 2010,\nhe earned exactly what he was entitled to receive under his contract. The fact\nthat West received less money in 2010 than in 2009 does not mean he “lost”\nanything or was “damaged” in any way. It means only he agreed to a front-\nloaded contract. And he did so many years before the Deepwater Horizon\ncatastrophe.\n The decision to give money to West “actually contradicted or misapplied\nthe Settlement Agreement.” Holmes Motors, 829 F.3d at 315 (quotation\nomitted). Our holding to that effect answers a “purely legal question[ ] of\ncontract interpretation.” In re Deepwater Horizon, 785 F.3d at 1011.\nAccordingly, “remand is unnecessary.” Aransas Project v. Shaw, 775 F.3d 641,\n658 (5th Cir. 2014) (per curiam); cf. United States v. Douglas, 696 F. App’x 666,\n669 (5th Cir. 2017) (per curiam) (“In certain circumstances, however, the\nappellate court may determine that remand of a particular case is unnecessary\nand instead, simply reverse and render.”); United States v. Hernandez-\n\n\n\nmeaningless or superfluous,” Chembulk Trading LLC v. Chemex Ltd., 393 F.3d 550, 555 (5th\nCir. 2004). The fact that the definition of “Expected Earnings” cannot be squared with the\ncalculation as applied to West’s claim further illustrates the compensation formula does not\napply to him. It applies only to eligible individuals—those who suffered unexpected damages.\n 6\n\n Case: 18-30394 Document: 00514881236 Page: 7 Date Filed: 03/20/2019\n\n\n\n No. 18-30394\nGuevara, 162 F.3d 863, 878 (5th Cir. 1998) (“[W]e need not waste judicial\nresources by remanding for what undoubtedly would be a rote resentencing.”).\n The judgment of the district court is REVERSED.\n\n\n\n\n 7\n\n Case: 18-30394 Document: 00514881236 Page: 8 Date Filed: 03/20/2019\n\n\n\n No. 18-30394\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: BP EXPLORATION & PRODUCTION, INCORPORATED; BP America Production Company; BP, P.L.C., Requesting Parties-Appellants, v. CLAIMANT ID 100281817, Objecting Party-Appellee.\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-20\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: Yes\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 18-30394 Document: 00514881236 Page: 1 Date Filed: 03/20/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n March 20, 2019\\n No. 18-30394\\n Lyle W. Cayce\\n Clerk\\n\\nBP EXPLORATION & PRODUCTION, INCORPORATED; BP AMERICA\\nPRODUCTION COMPANY; BP, P.L.C.,\\n\\n Requesting Parties-Appellants,\\n\\nv.\\n\\nCLAIMANT ID 100281817,\\n\\n Objecting Party-Appellee.\\n\\n\\n\\n Appeal from the United States District Court\\n for the Eastern District of Louisiana\\n\\n\\nBefore JONES, HAYNES, and OLDHAM, Circuit Judges.\\nANDREW S. OLDHAM, Circuit Judge:\\n An NBA player named David West negotiated a contract with the New\\nOrleans Hornets before the Deepwater Horizon oil spill. He received every\\npenny specified in that contract both before and after the spill. Still, the\\nClaims Administrator for the Deepwater Horizon Economic and Property\\nDamages Settlement Agreement awarded West almost $1.5 million in “lost”\\nearnings. The Settlement Appeal Panel affirmed, and the district court denied\\ndiscretionary review. We reverse.\\n I.\\n The Deepwater Horizon oil rig exploded on April 20, 2010. At that time,\\nDavid West played professional basketball for the New Orleans Hornets (now\\n\\n Case: 18-30394 Document: 00514881236 Page: 2 Date Filed: 03/20/2019\\n\\n\\n\\n No. 18-30394\\nknown as the New Orleans Pelicans). He was four years into a five-year\\ncontract. That contract paid West a total of $45 million. But it was “front-\\nloaded,” meaning West’s annual salary decreased every year of the contract—\\nincluding from 2009 to 2010. West received all $45 million owed to him under\\nthe contract.\\n Still, he submitted an “Individual Economic Loss Claim” under the\\nDeepwater Horizon Economic and Property Damages Settlement Agreement\\n(“Settlement”). 1 These claims can be submitted only by individuals “who seek\\ncompensation for lost earnings from employment due to or resulting from the\\n[Deepwater Horizon] Spill.” Settlement Agreement Ex. 8A at 1 (emphasis\\nadded). And the Individual Economic Loss Claim form states, on its very first\\npage, that it covers only “individuals who have experienced income losses\\ncaused by the Spill.” Individual Economic Loss Claim Form 1 (emphasis\\nadded). It also required West to certify “that the information provided in [his]\\nClaim Form [was] true and accurate to the best of [his] knowledge.” Id. at 15.\\nBased on that attestation, the Claims Administrator used West’s tax forms to\\ncalculate his “lost earnings.” The Claims Administrator determined West was\\nentitled to $1,412,673.06. BP contested that determination because West “lost”\\nnothing—he received all the money promised by the front-loaded terms of his\\npre-spill contract.\\n BP first sought reversal before the Appeal Panel. It argued West was\\nnot entitled to any award under the Agreement because (1) Individual\\nEconomic Loss Claimants can recover only if they experienced a loss caused by\\nthe spill, and (2) West cannot satisfy the Settlement’s attestation\\n\\n\\n 1In previous cases, we have discussed the Deepwater Horizon oil spill and resulting\\nsettlement at great length. See, e.g., In re Deepwater Horizon (Deepwater Horizon III ), 744\\nF.3d 370 (5th Cir. 2014); In re Deepwater Horizon (Deepwater Horizon II ), 739 F.3d 790 (5th\\nCir. 2014); In re Deepwater Horizon (Deepwater Horizon I ), 732 F.3d 326 (5th Cir. 2013). We\\ntherefore need not recount that history here.\\n 2\\n\\n Case: 18-30394 Document: 00514881236 Page: 3 Date Filed: 03/20/2019\\n\\n\\n\\n No. 18-30394\\nrequirements. The Appeal Panel affirmed West’s award. It concluded West\\nestablished causation because his employer—the Hornets—benefited from\\npresumed causation under the Settlement. It therefore held West needed\\nnothing more to claim “lost” earnings.\\n BP asked the district court to review the award decision. But the court\\ndenied discretionary review without explanation. BP timely appealed.\\n II.\\n Our review is for abuse of discretion. Holmes Motors, Inc. v. BP Expl. &\\nProd., Inc., 829 F.3d 313, 315 (5th Cir. 2016). The district court abuses its\\ndiscretion when “the decision not reviewed by the district court actually\\ncontradicted or misapplied the Settlement Agreement, or had the clear\\npotential to contradict or misapply the Settlement Agreement.” Ibid.\\n(quotation omitted). It’s likewise “an abuse of discretion to deny a request for\\nreview that raises a recurring issue on which the Appeal Panels are split if the\\nresolution of the question will substantially impact the administration of the\\nAgreement.” Claimant ID 100212278 v. BP Expl. & Prod., Inc., 848 F.3d 407,\\n410 (5th Cir. 2017) (per curiam) (quotation omitted). In contrast, denying “a\\nrequest for review that involve[s] no pressing question of how the Settlement\\nAgreement should be interpreted or implemented, but simply raise[s] the\\ncorrectness of a discretionary administrative decision in the facts of a single\\nclaimant’s case,” does not amount to an abuse of discretion. Ibid. (quotation\\nomitted) (alterations in original).\\n That said, the Settlement Agreement is a contract. The proper\\ninterpretation of it “is a question of law.” In re Deepwater Horizon (Deepwater\\nHorizon I ), 732 F.3d 326, 345 (5th Cir. 2013). And making “an error of law\\nconstitutes an abuse of discretion.” In re Deepwater Horizon, 785 F.3d 986, 999\\n(5th Cir. 2015). Accordingly, when the district court is “presented with purely\\n\\n\\n 3\\n\\n Case: 18-30394 Document: 00514881236 Page: 4 Date Filed: 03/20/2019\\n\\n\\n\\n No. 18-30394\\nlegal questions of contract interpretation,” our review is de novo. In re\\nDeepwater Horizon, 785 F.3d 1003, 1011 (5th Cir. 2015).\\n A.\\n We start with the contractual provisions governing West’s claim. West\\nsubmitted a specific type of claim—an “Individual Economic Loss Claim.” It is\\ndefined to include a claim brought by an individual described in Exhibit 8A.\\nExhibit 8A, in turn, provides the following description for Individual Economic\\nLoss Claims:\\n Individual economic loss claims are claims by Individuals, who\\n shall be defined as (i) Natural Persons who (a) satisfy (or whose\\n employers satisfy) the Class Definition and (b) whose losses are not\\n excluded from the Class and (ii) who seek compensation for lost\\n earnings from employment due to or resulting from the [Deepwater\\n Horizon oil spill] . . . .\\nSettlement Agreement Ex. 8A at 1 (emphases added). The claim form that\\nWest submitted similarly stated: “The Individual Economic Loss Claim is for\\nindividuals who have experienced income losses caused by the Spill.”\\nIndividual Economic Loss Claim Form 1 (emphasis added). Thus, these types\\nof claims may be brought only by individuals who experienced losses and seek\\ncompensation for lost earnings caused by the oil spill. We’ve previously\\ninterpreted the Agreement as allowing “proof of loss as a substitute for proof\\nof causation.” In re Deepwater (Deepwater Horizon III ), 744 F.3d 370, 375 (5th\\nCir. 2014). But what do “loss” and “lost earnings” mean?\\n They are undefined in the Settlement, so we look to their plain meaning.\\nSee BP Expl. & Prod., Inc. v. Claimant ID 100094497, 910 F.3d 797, 801 (5th\\nCir. 2018). “Loss” typically means “the disappearance or diminution of\\nvalue . . . in an unexpected or relatively unpredictable way.” Loss, BLACK’S\\nLAW DICTIONARY (10th ed. 2014); see also Economic Loss, BLACK’S LAW\\nDICTIONARY (10th ed. 2014) (explaining “economic loss” means “monetary loss\\nsuch as lost wages or lost profits” and usually “refers to a type of damages\\n 4\\n\\n Case: 18-30394 Document: 00514881236 Page: 5 Date Filed: 03/20/2019\\n\\n\\n\\n No. 18-30394\\nrecoverable in a lawsuit”). And “lost earnings” refers to “[w]ages, salary, or\\nother income that a person could have earned if he or she had not lost a job,\\nsuffered a disabling injury, or died.” Earnings, BLACK’S LAW DICTIONARY (10th\\ned. 2014). These definitions suggest “loss” or “lost earnings” are unexpected\\ndiminutions in wages or other income that could otherwise support a claim for\\ncivil damages.\\n West argues these plain meanings of “loss” and “lost earnings” do not\\napply. Instead, he says, his “loss” is proved by the seven-step mathematical\\nequation that appears in Exhibit 8A. But that puts the cart before the horse.\\nOnly claimants who suffer unexpected damages can submit an Individual\\nEconomic Loss Claim; then they use Exhibit 8A’s equation to determine the\\nvalue of that claim. The defined terms in the seven-step equation make that\\nclear. “Claimant Lost Earnings” is defined as “[t]he claimant’s Expected\\nEarnings from all Claiming Jobs minus the claimant’s Actual Earnings\\nfrom all Claiming Jobs during the Compensation Period, minus any\\nOffsetting Earnings.” Settlement Agreement Ex. 8A at 4. “Expected\\nEarnings” refers to the “[c]laimant’s earnings in the Compensation Period\\nin the Claiming Job that would have been expected in the absence of the\\n[Deepwater Horizon] Spill.” Id. at 5 (emphasis added). West expected to earn\\nin the absence of the spill precisely what he did earn after it. He therefore did\\nnot suffer unexpected damages, and Exhibit 8A does not apply to him. 2\\n\\n\\n 2 Because West’s expected earnings equal his actual earnings based on Exhibit 8A’s\\ndefinitions, West ignores them. (Indeed, he does not even include the Agreement’s definition\\nof “Expected Earnings” in his brief.) He instead implies “Expected Earnings” is defined in\\nExhibit 8A as a calculation based on what he earned in previous time periods, not what his\\nfive-year contract provided. And applying that “definition,” West’s expected earnings would\\nbe higher than his actual earnings. But we cannot focus exclusively on Exhibit 8A’s\\ncalculations and ignore its list of defined terms and accompanying definitions. Instead, we\\nmust read the Agreement’s provisions “as a whole,” Claimant ID 100094497, 910 F.3d at 801,\\nand harmonize the Agreement—giving effect to all its terms “without rendering any of them\\n\\n 5\\n\\n Case: 18-30394 Document: 00514881236 Page: 6 Date Filed: 03/20/2019\\n\\n\\n\\n No. 18-30394\\n This interpretation comports not only with the Agreement’s text, but also\\nwith our precedent. As we explained in Deepwater Horizon I, when\\ninterpreting the Agreement, we must give “some weight” to “what damages\\nrecoverable in civil litigation actually are.” 732 F.3d at 339. And in civil\\nlitigation, the plaintiff can recover damages only after suffering actual losses.\\nSee Lewis v. Casey, 518 U.S. 343, 349 (1996) (explaining the court’s role is\\nlimited to “provid[ing] relief to claimants, in individual or class actions, who\\nhave suffered, or will imminently suffer, actual harm”).\\n B.\\n West did not suffer actual and unexpected “losses” or damages. In 2010,\\nhe earned exactly what he was entitled to receive under his contract. The fact\\nthat West received less money in 2010 than in 2009 does not mean he “lost”\\nanything or was “damaged” in any way. It means only he agreed to a front-\\nloaded contract. And he did so many years before the Deepwater Horizon\\ncatastrophe.\\n The decision to give money to West “actually contradicted or misapplied\\nthe Settlement Agreement.” Holmes Motors, 829 F.3d at 315 (quotation\\nomitted). Our holding to that effect answers a “purely legal question[ ] of\\ncontract interpretation.” In re Deepwater Horizon, 785 F.3d at 1011.\\nAccordingly, “remand is unnecessary.” Aransas Project v. Shaw, 775 F.3d 641,\\n658 (5th Cir. 2014) (per curiam); cf. United States v. Douglas, 696 F. App’x 666,\\n669 (5th Cir. 2017) (per curiam) (“In certain circumstances, however, the\\nappellate court may determine that remand of a particular case is unnecessary\\nand instead, simply reverse and render.”); United States v. Hernandez-\\n\\n\\n\\nmeaningless or superfluous,” Chembulk Trading LLC v. Chemex Ltd., 393 F.3d 550, 555 (5th\\nCir. 2004). The fact that the definition of “Expected Earnings” cannot be squared with the\\ncalculation as applied to West’s claim further illustrates the compensation formula does not\\napply to him. It applies only to eligible individuals—those who suffered unexpected damages.\\n 6\\n\\n Case: 18-30394 Document: 00514881236 Page: 7 Date Filed: 03/20/2019\\n\\n\\n\\n No. 18-30394\\nGuevara, 162 F.3d 863, 878 (5th Cir. 1998) (“[W]e need not waste judicial\\nresources by remanding for what undoubtedly would be a rote resentencing.”).\\n The judgment of the district court is REVERSED.\\n\\n\\n\\n\\n 7\\n\\n Case: 18-30394 Document: 00514881236 Page: 8 Date Filed: 03/20/2019\\n\\n\\n\\n No. 18-30394\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1095,"cells":{"id":{"kind":"number","value":4602317,"string":"4,602,317"},"name":{"kind":"string","value":"ALLIANCE FOR GOOD GOVERNMENT, Plaintiff - Appellee v. COALITION FOR BETTER GOVERNMENT, Defendant - Appellant"},"name_abbreviation":{"kind":"string","value":"Alliance for Good Government v. Coalition for Bett"},"decision_date":{"kind":"string","value":"2019-03-21"},"docket_number":{"kind":"string","value":"18-30759"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Higginbotham, Smith, Higginson\", \"parties\": \"\", \"opinions\": [{\"author\": \"PATRICK E. HIGGINBOTHAM, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 18-30759 Document: 00514882154 Page: 1 Date Filed: 03/21/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n No. 18-30759 FILED\\n March 21, 2019\\n Lyle W. Cayce\\nALLIANCE FOR GOOD GOVERNMENT, Clerk\\n\\n Plaintiff - Appellee\\n\\nv.\\n\\nCOALITION FOR BETTER GOVERNMENT,\\n\\n Defendant - Appellant\\n\\n\\n\\n\\n Appeals from the United States District Court\\n for the Eastern District of Louisiana\\n\\n\\nBefore HIGGINBOTHAM, SMITH, and HIGGINSON, Circuit Judges.\\nPATRICK E. HIGGINBOTHAM, Circuit Judge:\\n The district court granted Alliance for Good Government summary\\njudgment on its trademark infringement claim against Coalition for Better\\nGovernment, enjoined Coalition from the use of both its logo and its trade\\nname, and then awarded Alliance attorney’s fees incurred in bringing the\\nlawsuit. It did not abuse its discretion in finding that Alliance is entitled to\\nfees, and so we affirm that portion of its order. Because we have since modified\\nthe district court’s injunction to permit Coalition to use its trade name,\\nhowever, we remand for the district court to reassess the amount of fees.\\n\\f Case: 18-30759 Document: 00514882154 Page: 2 Date Filed: 03/21/2019\\n\\n\\n\\n No. 18-30759\\n I\\n Our earlier opinion describes this case’s background. 1 In short, Alliance\\nand Coalition are both nonprofit organizations that endorse political\\ncandidates in New Orleans. Alliance began using a logo featuring a bird with\\nwings outstretched in the late 1960s; Coalition began using a similar logo in\\nthe 1980s or 1990s, then changed its logo in 2008 to be virtually identical to\\nAlliance’s. 2 Below are the Alliance and post-2008 Coalition logos:\\n\\n\\n\\n\\n Alliance sued Coalition for trademark infringement in Louisiana court\\nin 2008, then voluntarily dismissed its suit, believing Coalition had ceased\\nusing the logo to endorse candidates. 3 When Coalition resumed the use of its\\nlogo in 2016, Alliance sued Coalition in the Eastern District of Louisiana,\\nclaiming federal and state trademark infringement and unfair trade\\npractices. 4 It argued that both Coalition’s “word mark”—its trade name,\\n“Coalition for Better Government”—and its “composite mark”—its logo—\\ninfringed Alliance’s marks. The district court granted Alliance’s motion for\\n\\n\\n\\n\\n 1 See All. for Good Gov’t v. Coal. for Better Gov’t (Alliance I), 901 F.3d 498 (5th Cir.\\n2018).\\n Id. at 503. In 2013, Alliance registered both the trade name “Alliance for Good\\n 2\\n\\nGovernment” and its logo with the U.S. Patent and Trademark Office. Id.\\n 3 See id. at 504.\\n 4 See id.\\n\\n 2\\n\\f Case: 18-30759 Document: 00514882154 Page: 3 Date Filed: 03/21/2019\\n\\n\\n\\n No. 18-30759\\npartial summary judgment, enjoining Coalition from using both its name and\\nlogo. 5 Alliance voluntarily dismissed its other claims.\\n Coalition appealed the summary judgment. While the appeal was\\npending, Alliance moved for attorney’s fees under the Lanham Act. The district\\ncourt awarded Alliance everything it requested—$68,237.25 in fees,\\nencompassing fees already incurred and projected fees from replying to\\nCoalition’s opposition to the fees motion. Coalition separately appealed the fee\\naward. 6\\n During briefing in this fees appeal, we affirmed Alliance’s entitlement to\\nsummary judgment on its claim that Coalition’s logo infringed its composite\\nmark. 7 We concluded that based on the summary judgment record, however,\\nCoalition’s trade name did not by itself generate a likelihood of confusion with\\nAlliance’s “differently-worded” trade name. 8 We therefore modified the district\\ncourt’s injunction to permit Coalition to continue using its name.\\n\\n\\n\\n\\n 5 The parties had cross-moved for summary judgment: Coalition argued that Alliance’s\\nsuit was barred by laches, while Alliance argued that it was entitled to partial summary\\njudgment on its federal trademark infringement claim. While Coalition had initially asserted\\ntwelve affirmative defenses in its Answer, its motion for summary judgment and opposition\\nto Alliance’s motion focused on laches. Coalition also averred that there was no likelihood of\\nconfusion between the marks as a matter of law and that Alliance had fraudulently obtained\\nits federal trademark registration. Along with granting Alliance’s motion for partial\\nsummary judgment, the district court granted Alliance’s separate motion to dismiss\\nCoalition’s counterclaims, including the fraudulent-registration claim.\\n 6 The notice of appeal of the fee order was filed approximately two weeks before oral\\n\\nargument in the summary judgment appeal, and we denied Alliance’s emergency motion to\\nconsolidate the appeals, explaining that either party could seek a stay of the fees appeal if it\\nbelieved that unnecessary resources would be expended in the fees appeal during the\\npendency of the summary judgment appeal.\\n 7 Alliance I, 901 F.3d at 513.\\n 8 Id. at 513–14. We observed that our decision was based purely on the summary\\n\\njudgment record and was without prejudice to Alliance’s opposition to Coalition’s pending\\napplication to register its name with the USPTO. Id. at 513 n.15.\\n 3\\n\\f Case: 18-30759 Document: 00514882154 Page: 4 Date Filed: 03/21/2019\\n\\n\\n\\n No. 18-30759\\n II\\n The Lanham Act authorizes the award of “reasonable attorney fees to\\nthe prevailing party” in “exceptional cases.” 9 In Octane Fitness, LLC v. ICON\\nHealth & Fitness, Inc., the Supreme Court established that an “exceptional”\\ncase meriting fees under the Patent Act does not require a prevailing party to\\ndemonstrate bad faith. 10 Rather, a party seeking fees under the Patent Act\\nmust demonstrate that the case “stands out from others with respect to the\\nsubstantive strength of a party’s litigating position (considering both the\\ngoverning law and the facts of the case) or the unreasonable manner in which\\nthe case was litigated.” 11 Recognizing that the Lanham Act’s fee-shifting\\nprovision is identical to the Patent Act’s, we have extended Octane Fitness’s\\ndisjunctive standard for “exceptional” cases to claims for fees brought under\\nthe Lanham Act. 12\\n Before Octane Fitness, we “review[ed] the district court’s determination\\nas to whether a case is ‘exceptional’ under § 1117(a) for clear error, but . . .\\nreview[ed] the . . . ultimate decision [on] attorney’s fees for an abuse of\\ndiscretion.” 13 The same day Octane Fitness was decided, the Supreme Court\\nrecognized that because Octane Fitness commits the determination about\\nwhether a case is “exceptional” to the district court’s discretion, “an appellate\\ncourt should review all aspects of a district court’s [fees determination under\\nthe Patent Act] for abuse of discretion.” 14 Since the Lanham Act’s fee-shifting\\n\\n\\n\\n 9 15 U.S.C. § 1117(a).\\n 10 572 U.S. 545, 555 (2014).\\n 11 Id. at 554.\\n 12 Baker v. DeShong, 821 F.3d 620, 622–25 (5th Cir. 2016); see also Octane Fitness,\\n\\n572 U.S. at 554 (observing that the two provisions are identical).\\n 13 E.g., Nat’l Bus. Forms & Printing, Inc. v. Ford Motor Co., 671 F.3d 526, 537 (5th\\n\\nCir. 2012).\\n 14 Highmark, Inc. v. Allcare Health Mgmt. Sys., Inc., 572 U.S. 559, 561 (2014)\\n\\n(emphasis added).\\n 4\\n\\f Case: 18-30759 Document: 00514882154 Page: 5 Date Filed: 03/21/2019\\n\\n\\n\\n No. 18-30759\\nprovision is identical to the Patent Act’s—as we recognized in Baker—we\\nconclude that this same standard of review applies to district court fee\\ndeterminations under the Lanham Act. We will therefore review all aspects of\\nthe district court’s fee determination, including its conclusion that this was an\\n“exceptional” case, for abuse of discretion. 15\\n III\\n As we have explained, a fee award may be warranted either where the\\nprevailing party stood out in terms of the strength of its litigating position or\\nwhere the non-prevailing party litigated the case in an “unreasonable\\nmanner.” The district court found that both grounds justified an award of fees\\nto Alliance. We conclude that with respect to Alliance’s claim that Coalition’s\\nlogo infringed Alliance’s composite mark, the district court did not abuse its\\ndiscretion in concluding that this was an “exceptional” case warranting fees. 16\\n A\\n The district court first found that the case stood out due to the strength\\nof Alliance’s litigating position: Alliance adopted its logo at least 15 years\\nbefore Coalition began using its similar logo; Alliance’s composite mark was\\nstrong; the marks were very similar; and both parties provided the same\\n“product,” used the same advertising channels, and targeted the same\\n“customers.” In sum, “[t]he likelihood of confusion [was] so great that it would\\n\\n\\n 15 Two circuits have already extended Highmark’s articulation of the proper standard\\nof review to the review of fee awards under the Lanham Act. See Romag Fasteners, Inc. v.\\nFossil, Inc., 866 F.3d 1330, 1334 (Fed. Cir. 2017); SunEarth, Inc. v. Sun Earth Solar Power\\nCo., Ltd., 839 F.3d 1179, 1181 (9th Cir. 2016) (en banc).\\n 16 Coalition does not directly contest that Alliance is a prevailing party, nor can it. We\\n\\nhave recognized that in the Lanham Act context, a prevailing party is “a party in whose favor\\njudgment is rendered” or “one who has been awarded some relief by the court.” Kiva Kitchen\\n& Bath Inc. v. Capital Distrib., Inc., 319 F. App’x 316, 322 (5th Cir. 2009). Alliance has\\nreceived a judgment in its favor and relief in the form of an injunction prohibiting Coalition\\nfrom using its logo, and therefore is a prevailing party potentially entitled to fees. We will\\nlater address the relevance of the fact that Alliance did not prevail on all aspects of the relief\\nit sought.\\n 5\\n\\f Case: 18-30759 Document: 00514882154 Page: 6 Date Filed: 03/21/2019\\n\\n\\n\\n No. 18-30759\\nappear that customer confusion was Coalition’s motivation for adopting the\\nCoalition Mark.” Further, Coalition presented meritless defenses at the\\nsummary judgment stage: a laches argument that was not supported by “any\\ncredible evidence,” as well as the bare assertion that the composite marks were\\ndifferent because one depicted an eagle while the other depicted a hawk.\\n We find no abuse of discretion in the district court’s conclusion that\\nAlliance had an exceptionally strong infringement claim. Indeed, many of the\\ndistrict court’s observations also underpinned our decision to affirm the grant\\nof summary judgment to Alliance. 17 While Coalition attempts to repackage\\nseveral of the defenses it raised to summary judgment as reasons why this case\\nis not “exceptional” under the Lanham Act, we have already concluded that\\nthose arguments were either waived in the district court or plainly meritless—\\nor both. 18\\n B\\n The district court also determined that this case was exceptional because\\nCoalition litigated it in an unreasonable manner. Coalition behaved\\nunreasonably at several points during the litigation, filing an unsupported\\n\\n\\n\\n\\n 17 For example, we were not just struck by the fact that Alliance and Coalition “have\\nthe same logo”—we also flatly rejected Coalition’s attempt to “distinguish the two logos[ ] not\\nby appearance, design, color, or font[,] but by the birds’ species.” See Alliance I, 901 F.3d at\\n511. Ultimately, we “agree[d] with the district court: the birds are identical. Whether that\\nbird is a haliaeetus leucocephalus (bald eagle), a buteo jamaicensis (red-tailed hawk), or some\\nother bird, we need not determine.” Id. at 512.\\n 18 See id. at 505–06 (finding that Coalition waived its arguments about political speech\\n\\nand non-engagement in commerce by failing to press them before the district court); id. at\\n507 n.9 (finding that Coalition’s counterclaim that Alliance fraudulently obtained its\\ntrademark registration was both waived and “easily resolved”); id. at 512–13 (agreeing with\\nthe district court that “while there was no evidence of ‘actual intent to infringe’ . . . . [the only\\nplausible explanation for the marks’ similarity was] Coalition’s intent to benefit from\\nAlliance’s pre-existing reputation”).\\n 6\\n\\f Case: 18-30759 Document: 00514882154 Page: 7 Date Filed: 03/21/2019\\n\\n\\n\\n No. 18-30759\\nlaches defense; 19 a “counterclaim without any actionable conduct”; and a\\nmeritless motion to dismiss that was rendered moot by a summary judgment\\nmotion filed two weeks later. 20 The district court also found that Coalition’s\\nbehavior during discovery was unreasonable, especially its refusal to postpone\\ndepositions after the district court ruled on the parties’ cross-motions for\\nsummary judgment.\\n Coalition urges that it was the unwilling defendant in a lawsuit initiated\\nby Alliance. To the extent that Coalition argues that only prevailing defendants\\nshould be awarded fees under the Lanham Act, we cannot agree. 21 The district\\ncourt did not abuse its discretion in concluding that taken as a whole,\\nCoalition’s litigation conduct rendered this case exceptional.\\n C\\n We pause to address Coalition’s argument that as a nonprofit entity\\nengaged in political speech, its First Amendment rights are threatened by the\\nimposition of attorney’s fees. This is a variant of Coalition’s earlier argument,\\nmade during the summary judgment appeal, that the First Amendment\\nprotected it from liability for trademark infringement. We declined to address\\nthis argument on the summary judgment appeal because “Coalition never\\ndeveloped the argument beyond [a cursory statement] and, by the time of the\\n\\n\\n\\n 19 Specifically, Coalition was unable to point to any evidence beyond a bare-bones\\naffidavit to show that Coalition used its logo to endorse candidates between 2010 and 2016—\\na critical aspect of its laches defense.\\n 20 While Coalition points out that Alliance also filed a motion to dismiss alongside its\\n\\nmotion for summary judgment, it fails to acknowledge the difference in context. Alliance filed\\na motion to dismiss Coalition’s counterclaims for failure to state a claim after moving for\\npartial summary judgment on its own federal trademark infringement claim.\\n 21 This suggestion is both waived by Coalition’s failure to argue it in its opening brief\\n\\nand contradicted by a wealth of cases granting fees to prevailing Lanham Act cases. See\\n“Recovery of Attorney’s Fees—Award to a Prevailing Plaintiff,” 5 McCarthy on Trademarks\\n& Unfair Competition § 30:100 (5th ed.) (collecting cases awarding fees to prevailing\\nplaintiffs, including many decided even before Octane Fitness clarified that a prevailing\\nplaintiff did not need to show willful infringement to recover fees under the Patent Act).\\n 7\\n\\f Case: 18-30759 Document: 00514882154 Page: 8 Date Filed: 03/21/2019\\n\\n\\n\\n No. 18-30759\\nsummary judgment proceedings, the issue had vanished.” 22 Ultimately, we\\nobserved, “[t]he interplay between the Lanham Act and the First Amendment’s\\npolitical and commercial speech doctrines raises a thicket of issues we decline\\nto enter when the issues were not preserved or ruled on below.” 23 Here too,\\nCoalition fleetingly raises the slightly different argument that a fees award\\nmight interfere with its First Amendment rights, but it did not so contend\\nbefore the district court in its opposition to attorney’s fees, nor did it present a\\nfully developed argument in its briefing on this appeal. We will not reach the\\nissue.\\n IV\\n We have concluded that the district court did not abuse its discretion in\\nfinding Alliance to be entitled to attorney’s fees. We agree with Coalition,\\nhowever, that the district court must reassess their amount given our decision\\nto modify the district court’s injunction to allow Coalition to continue the use\\nof its trade name.\\n When a party advances both Lanham Act and non-Lanham Act claims,\\na district court should make efforts to award fees only for successful Lanham\\nAct claims. 24 This reflects “the background rule in America . . . [that] the\\nprevailing party usually cannot recover fees absent statutory authority.” 25 The\\nsame apportionment principle should apply “when in one lawsuit some\\nLanham Act claims qualify for an attorney’s fee award and other Lanham Act\\nclaims do not.” 26\\n\\n\\n\\n\\n Alliance I, 901 F.3d at 506.\\n 22\\n\\n Id. at 506 n.8.\\n 23\\n 24 Procter & Gamble Co. v. Amway Corp., 280 F.3d 519, 527 (5th Cir. 2002).\\n 25 Id.\\n 26 See “Recovery of Attorney’s Fees—Apportionment Among Claims,” 5 McCarthy on\\n\\nTrademarks & Unfair Competition § 30:103; see also Cairns v. Franklin Mint Co., 292 F.3d\\n1139, 1157–58 (9th Cir. 2002) (affirming a twenty-six-percent reduction in fees where the\\n 8\\n\\f Case: 18-30759 Document: 00514882154 Page: 9 Date Filed: 03/21/2019\\n\\n\\n\\n No. 18-30759\\n Here, Alliance prevailed on its claim that Coalition’s logo infringed\\nAlliance’s composite mark—and, as we have explained, the district court did\\nnot abuse its discretion in holding that Alliance was entitled to fees on this\\nclaim. Alliance did not prevail, however, in its effort to enjoin Coalition from\\nusing the “Coalition for Better Government” designation. 27 Further, Alliance\\nvoluntarily dismissed its other counts after prevailing on the main trademark\\ninfringement claim; the district court’s fee award did not distinguish between\\ntime spent on the infringement claim and time Alliance’s attorneys spent—\\nhowever limited—on these other counts. Alliance is only entitled to fees for\\nwork its attorneys performed on its claim that Coalition’s logo infringed its\\ncomposite mark.\\n While Alliance’s composite-mark claim may be intertwined with its other\\nclaims to some extent, 28 “the impossibility of making an exact apportionment\\ndoes not relieve the district court of its duty to make some attempt to adjust\\nthe fee award in an effort to reflect an apportionment.” 29 We remand to the\\nable district court to account for billed time for claims on which Alliance did\\nnot prevail, and to adjust the fee award accordingly.\\n\\n\\n\\n\\nlosing party brought some Lanham Act claims that merited fees alongside other claims that,\\nalthough unsuccessful, were not groundless).\\n 27 While Alliance frequently referred to the marks collectively and addressed federal\\n\\ntrademark infringement of both marks in a single count of its complaint, we analyzed the\\ncomposite and word marks separately for the purposes of summary judgment.\\n 28 Cf. Procter & Gamble, 280 F.3d at 527 (explaining that where a party has brought\\n\\nboth Lanham Act and non-Lanham Act claims, “[a] court should permit recovery for work on\\nnon-Lanham Act claims only if ‘the Lanham Act and non-Lanham Act claims are so\\nintertwined that it is impossible to differentiate between work done on claims’” (quoting\\nGracie v. Gracie, 217 F.3d 1060, 1069 (9th Cir. 2000)).\\n 29 Gracie, 217 F.3d at 1070.\\n\\n 9\\n\\f Case: 18-30759 Document: 00514882154 Page: 10 Date Filed: 03/21/2019\\n\\n\\n\\n No. 18-30759\\n V\\n We affirm the district court’s determination that Alliance is entitled to\\nattorney’s fees, vacate the amount of fees awarded, and remand for the district\\ncourt to assess the amount of the award of fees in light of this opinion. 30\\n Affirmed in part and remanded in part.\\n\\n\\n\\n\\n 30We do not address Coalition’s argument that the district court erred in denying its\\nmotion to strike, as Coalition failed to identify this as one of the issues presented for review\\nand did not present legal authority to support its contention. See, e.g., Procter & Gamble Co.\\nv. Amway Corp. 376 F.3d 496, 499 n.1 (5th Cir. 2004) (“Failure adequately to brief an issue\\non appeal constitutes waiver of that argument.”).\\n 10\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4379570/\", \"author_raw\": \"PATRICK E. HIGGINBOTHAM, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"HIGGINBOTHAM"},"judge2":{"kind":"string","value":"SMITH"},"judge3":{"kind":"string","value":"HIGGINSON"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4602317/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: ALLIANCE FOR GOOD GOVERNMENT, Plaintiff - Appellee v. COALITION FOR BETTER GOVERNMENT, Defendant - Appellant\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-21\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 18-30759 Document: 00514882154 Page: 1 Date Filed: 03/21/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\n United States Court of Appeals\n Fifth Circuit\n\n No. 18-30759 FILED\n March 21, 2019\n Lyle W. Cayce\nALLIANCE FOR GOOD GOVERNMENT, Clerk\n\n Plaintiff - Appellee\n\nv.\n\nCOALITION FOR BETTER GOVERNMENT,\n\n Defendant - Appellant\n\n\n\n\n Appeals from the United States District Court\n for the Eastern District of Louisiana\n\n\nBefore HIGGINBOTHAM, SMITH, and HIGGINSON, Circuit Judges.\nPATRICK E. HIGGINBOTHAM, Circuit Judge:\n The district court granted Alliance for Good Government summary\njudgment on its trademark infringement claim against Coalition for Better\nGovernment, enjoined Coalition from the use of both its logo and its trade\nname, and then awarded Alliance attorney’s fees incurred in bringing the\nlawsuit. It did not abuse its discretion in finding that Alliance is entitled to\nfees, and so we affirm that portion of its order. Because we have since modified\nthe district court’s injunction to permit Coalition to use its trade name,\nhowever, we remand for the district court to reassess the amount of fees.\n\f Case: 18-30759 Document: 00514882154 Page: 2 Date Filed: 03/21/2019\n\n\n\n No. 18-30759\n I\n Our earlier opinion describes this case’s background. 1 In short, Alliance\nand Coalition are both nonprofit organizations that endorse political\ncandidates in New Orleans. Alliance began using a logo featuring a bird with\nwings outstretched in the late 1960s; Coalition began using a similar logo in\nthe 1980s or 1990s, then changed its logo in 2008 to be virtually identical to\nAlliance’s. 2 Below are the Alliance and post-2008 Coalition logos:\n\n\n\n\n Alliance sued Coalition for trademark infringement in Louisiana court\nin 2008, then voluntarily dismissed its suit, believing Coalition had ceased\nusing the logo to endorse candidates. 3 When Coalition resumed the use of its\nlogo in 2016, Alliance sued Coalition in the Eastern District of Louisiana,\nclaiming federal and state trademark infringement and unfair trade\npractices. 4 It argued that both Coalition’s “word mark”—its trade name,\n“Coalition for Better Government”—and its “composite mark”—its logo—\ninfringed Alliance’s marks. The district court granted Alliance’s motion for\n\n\n\n\n 1 See All. for Good Gov’t v. Coal. for Better Gov’t (Alliance I), 901 F.3d 498 (5th Cir.\n2018).\n Id. at 503. In 2013, Alliance registered both the trade name “Alliance for Good\n 2\n\nGovernment” and its logo with the U.S. Patent and Trademark Office. Id.\n 3 See id. at 504.\n 4 See id.\n\n 2\n\f Case: 18-30759 Document: 00514882154 Page: 3 Date Filed: 03/21/2019\n\n\n\n No. 18-30759\npartial summary judgment, enjoining Coalition from using both its name and\nlogo. 5 Alliance voluntarily dismissed its other claims.\n Coalition appealed the summary judgment. While the appeal was\npending, Alliance moved for attorney’s fees under the Lanham Act. The district\ncourt awarded Alliance everything it requested—$68,237.25 in fees,\nencompassing fees already incurred and projected fees from replying to\nCoalition’s opposition to the fees motion. Coalition separately appealed the fee\naward. 6\n During briefing in this fees appeal, we affirmed Alliance’s entitlement to\nsummary judgment on its claim that Coalition’s logo infringed its composite\nmark. 7 We concluded that based on the summary judgment record, however,\nCoalition’s trade name did not by itself generate a likelihood of confusion with\nAlliance’s “differently-worded” trade name. 8 We therefore modified the district\ncourt’s injunction to permit Coalition to continue using its name.\n\n\n\n\n 5 The parties had cross-moved for summary judgment: Coalition argued that Alliance’s\nsuit was barred by laches, while Alliance argued that it was entitled to partial summary\njudgment on its federal trademark infringement claim. While Coalition had initially asserted\ntwelve affirmative defenses in its Answer, its motion for summary judgment and opposition\nto Alliance’s motion focused on laches. Coalition also averred that there was no likelihood of\nconfusion between the marks as a matter of law and that Alliance had fraudulently obtained\nits federal trademark registration. Along with granting Alliance’s motion for partial\nsummary judgment, the district court granted Alliance’s separate motion to dismiss\nCoalition’s counterclaims, including the fraudulent-registration claim.\n 6 The notice of appeal of the fee order was filed approximately two weeks before oral\n\nargument in the summary judgment appeal, and we denied Alliance’s emergency motion to\nconsolidate the appeals, explaining that either party could seek a stay of the fees appeal if it\nbelieved that unnecessary resources would be expended in the fees appeal during the\npendency of the summary judgment appeal.\n 7 Alliance I, 901 F.3d at 513.\n 8 Id. at 513–14. We observed that our decision was based purely on the summary\n\njudgment record and was without prejudice to Alliance’s opposition to Coalition’s pending\napplication to register its name with the USPTO. Id. at 513 n.15.\n 3\n\f Case: 18-30759 Document: 00514882154 Page: 4 Date Filed: 03/21/2019\n\n\n\n No. 18-30759\n II\n The Lanham Act authorizes the award of “reasonable attorney fees to\nthe prevailing party” in “exceptional cases.” 9 In Octane Fitness, LLC v. ICON\nHealth & Fitness, Inc., the Supreme Court established that an “exceptional”\ncase meriting fees under the Patent Act does not require a prevailing party to\ndemonstrate bad faith. 10 Rather, a party seeking fees under the Patent Act\nmust demonstrate that the case “stands out from others with respect to the\nsubstantive strength of a party’s litigating position (considering both the\ngoverning law and the facts of the case) or the unreasonable manner in which\nthe case was litigated.” 11 Recognizing that the Lanham Act’s fee-shifting\nprovision is identical to the Patent Act’s, we have extended Octane Fitness’s\ndisjunctive standard for “exceptional” cases to claims for fees brought under\nthe Lanham Act. 12\n Before Octane Fitness, we “review[ed] the district court’s determination\nas to whether a case is ‘exceptional’ under § 1117(a) for clear error, but . . .\nreview[ed] the . . . ultimate decision [on] attorney’s fees for an abuse of\ndiscretion.” 13 The same day Octane Fitness was decided, the Supreme Court\nrecognized that because Octane Fitness commits the determination about\nwhether a case is “exceptional” to the district court’s discretion, “an appellate\ncourt should review all aspects of a district court’s [fees determination under\nthe Patent Act] for abuse of discretion.” 14 Since the Lanham Act’s fee-shifting\n\n\n\n 9 15 U.S.C. § 1117(a).\n 10 572 U.S. 545, 555 (2014).\n 11 Id. at 554.\n 12 Baker v. DeShong, 821 F.3d 620, 622–25 (5th Cir. 2016); see also Octane Fitness,\n\n572 U.S. at 554 (observing that the two provisions are identical).\n 13 E.g., Nat’l Bus. Forms & Printing, Inc. v. Ford Motor Co., 671 F.3d 526, 537 (5th\n\nCir. 2012).\n 14 Highmark, Inc. v. Allcare Health Mgmt. Sys., Inc., 572 U.S. 559, 561 (2014)\n\n(emphasis added).\n 4\n\f Case: 18-30759 Document: 00514882154 Page: 5 Date Filed: 03/21/2019\n\n\n\n No. 18-30759\nprovision is identical to the Patent Act’s—as we recognized in Baker—we\nconclude that this same standard of review applies to district court fee\ndeterminations under the Lanham Act. We will therefore review all aspects of\nthe district court’s fee determination, including its conclusion that this was an\n“exceptional” case, for abuse of discretion. 15\n III\n As we have explained, a fee award may be warranted either where the\nprevailing party stood out in terms of the strength of its litigating position or\nwhere the non-prevailing party litigated the case in an “unreasonable\nmanner.” The district court found that both grounds justified an award of fees\nto Alliance. We conclude that with respect to Alliance’s claim that Coalition’s\nlogo infringed Alliance’s composite mark, the district court did not abuse its\ndiscretion in concluding that this was an “exceptional” case warranting fees. 16\n A\n The district court first found that the case stood out due to the strength\nof Alliance’s litigating position: Alliance adopted its logo at least 15 years\nbefore Coalition began using its similar logo; Alliance’s composite mark was\nstrong; the marks were very similar; and both parties provided the same\n“product,” used the same advertising channels, and targeted the same\n“customers.” In sum, “[t]he likelihood of confusion [was] so great that it would\n\n\n 15 Two circuits have already extended Highmark’s articulation of the proper standard\nof review to the review of fee awards under the Lanham Act. See Romag Fasteners, Inc. v.\nFossil, Inc., 866 F.3d 1330, 1334 (Fed. Cir. 2017); SunEarth, Inc. v. Sun Earth Solar Power\nCo., Ltd., 839 F.3d 1179, 1181 (9th Cir. 2016) (en banc).\n 16 Coalition does not directly contest that Alliance is a prevailing party, nor can it. We\n\nhave recognized that in the Lanham Act context, a prevailing party is “a party in whose favor\njudgment is rendered” or “one who has been awarded some relief by the court.” Kiva Kitchen\n& Bath Inc. v. Capital Distrib., Inc., 319 F. App’x 316, 322 (5th Cir. 2009). Alliance has\nreceived a judgment in its favor and relief in the form of an injunction prohibiting Coalition\nfrom using its logo, and therefore is a prevailing party potentially entitled to fees. We will\nlater address the relevance of the fact that Alliance did not prevail on all aspects of the relief\nit sought.\n 5\n\f Case: 18-30759 Document: 00514882154 Page: 6 Date Filed: 03/21/2019\n\n\n\n No. 18-30759\nappear that customer confusion was Coalition’s motivation for adopting the\nCoalition Mark.” Further, Coalition presented meritless defenses at the\nsummary judgment stage: a laches argument that was not supported by “any\ncredible evidence,” as well as the bare assertion that the composite marks were\ndifferent because one depicted an eagle while the other depicted a hawk.\n We find no abuse of discretion in the district court’s conclusion that\nAlliance had an exceptionally strong infringement claim. Indeed, many of the\ndistrict court’s observations also underpinned our decision to affirm the grant\nof summary judgment to Alliance. 17 While Coalition attempts to repackage\nseveral of the defenses it raised to summary judgment as reasons why this case\nis not “exceptional” under the Lanham Act, we have already concluded that\nthose arguments were either waived in the district court or plainly meritless—\nor both. 18\n B\n The district court also determined that this case was exceptional because\nCoalition litigated it in an unreasonable manner. Coalition behaved\nunreasonably at several points during the litigation, filing an unsupported\n\n\n\n\n 17 For example, we were not just struck by the fact that Alliance and Coalition “have\nthe same logo”—we also flatly rejected Coalition’s attempt to “distinguish the two logos[ ] not\nby appearance, design, color, or font[,] but by the birds’ species.” See Alliance I, 901 F.3d at\n511. Ultimately, we “agree[d] with the district court: the birds are identical. Whether that\nbird is a haliaeetus leucocephalus (bald eagle), a buteo jamaicensis (red-tailed hawk), or some\nother bird, we need not determine.” Id. at 512.\n 18 See id. at 505–06 (finding that Coalition waived its arguments about political speech\n\nand non-engagement in commerce by failing to press them before the district court); id. at\n507 n.9 (finding that Coalition’s counterclaim that Alliance fraudulently obtained its\ntrademark registration was both waived and “easily resolved”); id. at 512–13 (agreeing with\nthe district court that “while there was no evidence of ‘actual intent to infringe’ . . . . [the only\nplausible explanation for the marks’ similarity was] Coalition’s intent to benefit from\nAlliance’s pre-existing reputation”).\n 6\n\f Case: 18-30759 Document: 00514882154 Page: 7 Date Filed: 03/21/2019\n\n\n\n No. 18-30759\nlaches defense; 19 a “counterclaim without any actionable conduct”; and a\nmeritless motion to dismiss that was rendered moot by a summary judgment\nmotion filed two weeks later. 20 The district court also found that Coalition’s\nbehavior during discovery was unreasonable, especially its refusal to postpone\ndepositions after the district court ruled on the parties’ cross-motions for\nsummary judgment.\n Coalition urges that it was the unwilling defendant in a lawsuit initiated\nby Alliance. To the extent that Coalition argues that only prevailing defendants\nshould be awarded fees under the Lanham Act, we cannot agree. 21 The district\ncourt did not abuse its discretion in concluding that taken as a whole,\nCoalition’s litigation conduct rendered this case exceptional.\n C\n We pause to address Coalition’s argument that as a nonprofit entity\nengaged in political speech, its First Amendment rights are threatened by the\nimposition of attorney’s fees. This is a variant of Coalition’s earlier argument,\nmade during the summary judgment appeal, that the First Amendment\nprotected it from liability for trademark infringement. We declined to address\nthis argument on the summary judgment appeal because “Coalition never\ndeveloped the argument beyond [a cursory statement] and, by the time of the\n\n\n\n 19 Specifically, Coalition was unable to point to any evidence beyond a bare-bones\naffidavit to show that Coalition used its logo to endorse candidates between 2010 and 2016—\na critical aspect of its laches defense.\n 20 While Coalition points out that Alliance also filed a motion to dismiss alongside its\n\nmotion for summary judgment, it fails to acknowledge the difference in context. Alliance filed\na motion to dismiss Coalition’s counterclaims for failure to state a claim after moving for\npartial summary judgment on its own federal trademark infringement claim.\n 21 This suggestion is both waived by Coalition’s failure to argue it in its opening brief\n\nand contradicted by a wealth of cases granting fees to prevailing Lanham Act cases. See\n“Recovery of Attorney’s Fees—Award to a Prevailing Plaintiff,” 5 McCarthy on Trademarks\n& Unfair Competition § 30:100 (5th ed.) (collecting cases awarding fees to prevailing\nplaintiffs, including many decided even before Octane Fitness clarified that a prevailing\nplaintiff did not need to show willful infringement to recover fees under the Patent Act).\n 7\n\f Case: 18-30759 Document: 00514882154 Page: 8 Date Filed: 03/21/2019\n\n\n\n No. 18-30759\nsummary judgment proceedings, the issue had vanished.” 22 Ultimately, we\nobserved, “[t]he interplay between the Lanham Act and the First Amendment’s\npolitical and commercial speech doctrines raises a thicket of issues we decline\nto enter when the issues were not preserved or ruled on below.” 23 Here too,\nCoalition fleetingly raises the slightly different argument that a fees award\nmight interfere with its First Amendment rights, but it did not so contend\nbefore the district court in its opposition to attorney’s fees, nor did it present a\nfully developed argument in its briefing on this appeal. We will not reach the\nissue.\n IV\n We have concluded that the district court did not abuse its discretion in\nfinding Alliance to be entitled to attorney’s fees. We agree with Coalition,\nhowever, that the district court must reassess their amount given our decision\nto modify the district court’s injunction to allow Coalition to continue the use\nof its trade name.\n When a party advances both Lanham Act and non-Lanham Act claims,\na district court should make efforts to award fees only for successful Lanham\nAct claims. 24 This reflects “the background rule in America . . . [that] the\nprevailing party usually cannot recover fees absent statutory authority.” 25 The\nsame apportionment principle should apply “when in one lawsuit some\nLanham Act claims qualify for an attorney’s fee award and other Lanham Act\nclaims do not.” 26\n\n\n\n\n Alliance I, 901 F.3d at 506.\n 22\n\n Id. at 506 n.8.\n 23\n 24 Procter & Gamble Co. v. Amway Corp., 280 F.3d 519, 527 (5th Cir. 2002).\n 25 Id.\n 26 See “Recovery of Attorney’s Fees—Apportionment Among Claims,” 5 McCarthy on\n\nTrademarks & Unfair Competition § 30:103; see also Cairns v. Franklin Mint Co., 292 F.3d\n1139, 1157–58 (9th Cir. 2002) (affirming a twenty-six-percent reduction in fees where the\n 8\n\f Case: 18-30759 Document: 00514882154 Page: 9 Date Filed: 03/21/2019\n\n\n\n No. 18-30759\n Here, Alliance prevailed on its claim that Coalition’s logo infringed\nAlliance’s composite mark—and, as we have explained, the district court did\nnot abuse its discretion in holding that Alliance was entitled to fees on this\nclaim. Alliance did not prevail, however, in its effort to enjoin Coalition from\nusing the “Coalition for Better Government” designation. 27 Further, Alliance\nvoluntarily dismissed its other counts after prevailing on the main trademark\ninfringement claim; the district court’s fee award did not distinguish between\ntime spent on the infringement claim and time Alliance’s attorneys spent—\nhowever limited—on these other counts. Alliance is only entitled to fees for\nwork its attorneys performed on its claim that Coalition’s logo infringed its\ncomposite mark.\n While Alliance’s composite-mark claim may be intertwined with its other\nclaims to some extent, 28 “the impossibility of making an exact apportionment\ndoes not relieve the district court of its duty to make some attempt to adjust\nthe fee award in an effort to reflect an apportionment.” 29 We remand to the\nable district court to account for billed time for claims on which Alliance did\nnot prevail, and to adjust the fee award accordingly.\n\n\n\n\nlosing party brought some Lanham Act claims that merited fees alongside other claims that,\nalthough unsuccessful, were not groundless).\n 27 While Alliance frequently referred to the marks collectively and addressed federal\n\ntrademark infringement of both marks in a single count of its complaint, we analyzed the\ncomposite and word marks separately for the purposes of summary judgment.\n 28 Cf. Procter & Gamble, 280 F.3d at 527 (explaining that where a party has brought\n\nboth Lanham Act and non-Lanham Act claims, “[a] court should permit recovery for work on\nnon-Lanham Act claims only if ‘the Lanham Act and non-Lanham Act claims are so\nintertwined that it is impossible to differentiate between work done on claims’” (quoting\nGracie v. Gracie, 217 F.3d 1060, 1069 (9th Cir. 2000)).\n 29 Gracie, 217 F.3d at 1070.\n\n 9\n\f Case: 18-30759 Document: 00514882154 Page: 10 Date Filed: 03/21/2019\n\n\n\n No. 18-30759\n V\n We affirm the district court’s determination that Alliance is entitled to\nattorney’s fees, vacate the amount of fees awarded, and remand for the district\ncourt to assess the amount of the award of fees in light of this opinion. 30\n Affirmed in part and remanded in part.\n\n\n\n\n 30We do not address Coalition’s argument that the district court erred in denying its\nmotion to strike, as Coalition failed to identify this as one of the issues presented for review\nand did not present legal authority to support its contention. See, e.g., Procter & Gamble Co.\nv. Amway Corp. 376 F.3d 496, 499 n.1 (5th Cir. 2004) (“Failure adequately to brief an issue\non appeal constitutes waiver of that argument.”).\n 10\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: ALLIANCE FOR GOOD GOVERNMENT, Plaintiff - Appellee v. COALITION FOR BETTER GOVERNMENT, Defendant - Appellant\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-21\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 18-30759 Document: 00514882154 Page: 1 Date Filed: 03/21/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n No. 18-30759 FILED\\n March 21, 2019\\n Lyle W. Cayce\\nALLIANCE FOR GOOD GOVERNMENT, Clerk\\n\\n Plaintiff - Appellee\\n\\nv.\\n\\nCOALITION FOR BETTER GOVERNMENT,\\n\\n Defendant - Appellant\\n\\n\\n\\n\\n Appeals from the United States District Court\\n for the Eastern District of Louisiana\\n\\n\\nBefore HIGGINBOTHAM, SMITH, and HIGGINSON, Circuit Judges.\\nPATRICK E. HIGGINBOTHAM, Circuit Judge:\\n The district court granted Alliance for Good Government summary\\njudgment on its trademark infringement claim against Coalition for Better\\nGovernment, enjoined Coalition from the use of both its logo and its trade\\nname, and then awarded Alliance attorney’s fees incurred in bringing the\\nlawsuit. It did not abuse its discretion in finding that Alliance is entitled to\\nfees, and so we affirm that portion of its order. Because we have since modified\\nthe district court’s injunction to permit Coalition to use its trade name,\\nhowever, we remand for the district court to reassess the amount of fees.\\n\\f Case: 18-30759 Document: 00514882154 Page: 2 Date Filed: 03/21/2019\\n\\n\\n\\n No. 18-30759\\n I\\n Our earlier opinion describes this case’s background. 1 In short, Alliance\\nand Coalition are both nonprofit organizations that endorse political\\ncandidates in New Orleans. Alliance began using a logo featuring a bird with\\nwings outstretched in the late 1960s; Coalition began using a similar logo in\\nthe 1980s or 1990s, then changed its logo in 2008 to be virtually identical to\\nAlliance’s. 2 Below are the Alliance and post-2008 Coalition logos:\\n\\n\\n\\n\\n Alliance sued Coalition for trademark infringement in Louisiana court\\nin 2008, then voluntarily dismissed its suit, believing Coalition had ceased\\nusing the logo to endorse candidates. 3 When Coalition resumed the use of its\\nlogo in 2016, Alliance sued Coalition in the Eastern District of Louisiana,\\nclaiming federal and state trademark infringement and unfair trade\\npractices. 4 It argued that both Coalition’s “word mark”—its trade name,\\n“Coalition for Better Government”—and its “composite mark”—its logo—\\ninfringed Alliance’s marks. The district court granted Alliance’s motion for\\n\\n\\n\\n\\n 1 See All. for Good Gov’t v. Coal. for Better Gov’t (Alliance I), 901 F.3d 498 (5th Cir.\\n2018).\\n Id. at 503. In 2013, Alliance registered both the trade name “Alliance for Good\\n 2\\n\\nGovernment” and its logo with the U.S. Patent and Trademark Office. Id.\\n 3 See id. at 504.\\n 4 See id.\\n\\n 2\\n\\f Case: 18-30759 Document: 00514882154 Page: 3 Date Filed: 03/21/2019\\n\\n\\n\\n No. 18-30759\\npartial summary judgment, enjoining Coalition from using both its name and\\nlogo. 5 Alliance voluntarily dismissed its other claims.\\n Coalition appealed the summary judgment. While the appeal was\\npending, Alliance moved for attorney’s fees under the Lanham Act. The district\\ncourt awarded Alliance everything it requested—$68,237.25 in fees,\\nencompassing fees already incurred and projected fees from replying to\\nCoalition’s opposition to the fees motion. Coalition separately appealed the fee\\naward. 6\\n During briefing in this fees appeal, we affirmed Alliance’s entitlement to\\nsummary judgment on its claim that Coalition’s logo infringed its composite\\nmark. 7 We concluded that based on the summary judgment record, however,\\nCoalition’s trade name did not by itself generate a likelihood of confusion with\\nAlliance’s “differently-worded” trade name. 8 We therefore modified the district\\ncourt’s injunction to permit Coalition to continue using its name.\\n\\n\\n\\n\\n 5 The parties had cross-moved for summary judgment: Coalition argued that Alliance’s\\nsuit was barred by laches, while Alliance argued that it was entitled to partial summary\\njudgment on its federal trademark infringement claim. While Coalition had initially asserted\\ntwelve affirmative defenses in its Answer, its motion for summary judgment and opposition\\nto Alliance’s motion focused on laches. Coalition also averred that there was no likelihood of\\nconfusion between the marks as a matter of law and that Alliance had fraudulently obtained\\nits federal trademark registration. Along with granting Alliance’s motion for partial\\nsummary judgment, the district court granted Alliance’s separate motion to dismiss\\nCoalition’s counterclaims, including the fraudulent-registration claim.\\n 6 The notice of appeal of the fee order was filed approximately two weeks before oral\\n\\nargument in the summary judgment appeal, and we denied Alliance’s emergency motion to\\nconsolidate the appeals, explaining that either party could seek a stay of the fees appeal if it\\nbelieved that unnecessary resources would be expended in the fees appeal during the\\npendency of the summary judgment appeal.\\n 7 Alliance I, 901 F.3d at 513.\\n 8 Id. at 513–14. We observed that our decision was based purely on the summary\\n\\njudgment record and was without prejudice to Alliance’s opposition to Coalition’s pending\\napplication to register its name with the USPTO. Id. at 513 n.15.\\n 3\\n\\f Case: 18-30759 Document: 00514882154 Page: 4 Date Filed: 03/21/2019\\n\\n\\n\\n No. 18-30759\\n II\\n The Lanham Act authorizes the award of “reasonable attorney fees to\\nthe prevailing party” in “exceptional cases.” 9 In Octane Fitness, LLC v. ICON\\nHealth & Fitness, Inc., the Supreme Court established that an “exceptional”\\ncase meriting fees under the Patent Act does not require a prevailing party to\\ndemonstrate bad faith. 10 Rather, a party seeking fees under the Patent Act\\nmust demonstrate that the case “stands out from others with respect to the\\nsubstantive strength of a party’s litigating position (considering both the\\ngoverning law and the facts of the case) or the unreasonable manner in which\\nthe case was litigated.” 11 Recognizing that the Lanham Act’s fee-shifting\\nprovision is identical to the Patent Act’s, we have extended Octane Fitness’s\\ndisjunctive standard for “exceptional” cases to claims for fees brought under\\nthe Lanham Act. 12\\n Before Octane Fitness, we “review[ed] the district court’s determination\\nas to whether a case is ‘exceptional’ under § 1117(a) for clear error, but . . .\\nreview[ed] the . . . ultimate decision [on] attorney’s fees for an abuse of\\ndiscretion.” 13 The same day Octane Fitness was decided, the Supreme Court\\nrecognized that because Octane Fitness commits the determination about\\nwhether a case is “exceptional” to the district court’s discretion, “an appellate\\ncourt should review all aspects of a district court’s [fees determination under\\nthe Patent Act] for abuse of discretion.” 14 Since the Lanham Act’s fee-shifting\\n\\n\\n\\n 9 15 U.S.C. § 1117(a).\\n 10 572 U.S. 545, 555 (2014).\\n 11 Id. at 554.\\n 12 Baker v. DeShong, 821 F.3d 620, 622–25 (5th Cir. 2016); see also Octane Fitness,\\n\\n572 U.S. at 554 (observing that the two provisions are identical).\\n 13 E.g., Nat’l Bus. Forms & Printing, Inc. v. Ford Motor Co., 671 F.3d 526, 537 (5th\\n\\nCir. 2012).\\n 14 Highmark, Inc. v. Allcare Health Mgmt. Sys., Inc., 572 U.S. 559, 561 (2014)\\n\\n(emphasis added).\\n 4\\n\\f Case: 18-30759 Document: 00514882154 Page: 5 Date Filed: 03/21/2019\\n\\n\\n\\n No. 18-30759\\nprovision is identical to the Patent Act’s—as we recognized in Baker—we\\nconclude that this same standard of review applies to district court fee\\ndeterminations under the Lanham Act. We will therefore review all aspects of\\nthe district court’s fee determination, including its conclusion that this was an\\n“exceptional” case, for abuse of discretion. 15\\n III\\n As we have explained, a fee award may be warranted either where the\\nprevailing party stood out in terms of the strength of its litigating position or\\nwhere the non-prevailing party litigated the case in an “unreasonable\\nmanner.” The district court found that both grounds justified an award of fees\\nto Alliance. We conclude that with respect to Alliance’s claim that Coalition’s\\nlogo infringed Alliance’s composite mark, the district court did not abuse its\\ndiscretion in concluding that this was an “exceptional” case warranting fees. 16\\n A\\n The district court first found that the case stood out due to the strength\\nof Alliance’s litigating position: Alliance adopted its logo at least 15 years\\nbefore Coalition began using its similar logo; Alliance’s composite mark was\\nstrong; the marks were very similar; and both parties provided the same\\n“product,” used the same advertising channels, and targeted the same\\n“customers.” In sum, “[t]he likelihood of confusion [was] so great that it would\\n\\n\\n 15 Two circuits have already extended Highmark’s articulation of the proper standard\\nof review to the review of fee awards under the Lanham Act. See Romag Fasteners, Inc. v.\\nFossil, Inc., 866 F.3d 1330, 1334 (Fed. Cir. 2017); SunEarth, Inc. v. Sun Earth Solar Power\\nCo., Ltd., 839 F.3d 1179, 1181 (9th Cir. 2016) (en banc).\\n 16 Coalition does not directly contest that Alliance is a prevailing party, nor can it. We\\n\\nhave recognized that in the Lanham Act context, a prevailing party is “a party in whose favor\\njudgment is rendered” or “one who has been awarded some relief by the court.” Kiva Kitchen\\n& Bath Inc. v. Capital Distrib., Inc., 319 F. App’x 316, 322 (5th Cir. 2009). Alliance has\\nreceived a judgment in its favor and relief in the form of an injunction prohibiting Coalition\\nfrom using its logo, and therefore is a prevailing party potentially entitled to fees. We will\\nlater address the relevance of the fact that Alliance did not prevail on all aspects of the relief\\nit sought.\\n 5\\n\\f Case: 18-30759 Document: 00514882154 Page: 6 Date Filed: 03/21/2019\\n\\n\\n\\n No. 18-30759\\nappear that customer confusion was Coalition’s motivation for adopting the\\nCoalition Mark.” Further, Coalition presented meritless defenses at the\\nsummary judgment stage: a laches argument that was not supported by “any\\ncredible evidence,” as well as the bare assertion that the composite marks were\\ndifferent because one depicted an eagle while the other depicted a hawk.\\n We find no abuse of discretion in the district court’s conclusion that\\nAlliance had an exceptionally strong infringement claim. Indeed, many of the\\ndistrict court’s observations also underpinned our decision to affirm the grant\\nof summary judgment to Alliance. 17 While Coalition attempts to repackage\\nseveral of the defenses it raised to summary judgment as reasons why this case\\nis not “exceptional” under the Lanham Act, we have already concluded that\\nthose arguments were either waived in the district court or plainly meritless—\\nor both. 18\\n B\\n The district court also determined that this case was exceptional because\\nCoalition litigated it in an unreasonable manner. Coalition behaved\\nunreasonably at several points during the litigation, filing an unsupported\\n\\n\\n\\n\\n 17 For example, we were not just struck by the fact that Alliance and Coalition “have\\nthe same logo”—we also flatly rejected Coalition’s attempt to “distinguish the two logos[ ] not\\nby appearance, design, color, or font[,] but by the birds’ species.” See Alliance I, 901 F.3d at\\n511. Ultimately, we “agree[d] with the district court: the birds are identical. Whether that\\nbird is a haliaeetus leucocephalus (bald eagle), a buteo jamaicensis (red-tailed hawk), or some\\nother bird, we need not determine.” Id. at 512.\\n 18 See id. at 505–06 (finding that Coalition waived its arguments about political speech\\n\\nand non-engagement in commerce by failing to press them before the district court); id. at\\n507 n.9 (finding that Coalition’s counterclaim that Alliance fraudulently obtained its\\ntrademark registration was both waived and “easily resolved”); id. at 512–13 (agreeing with\\nthe district court that “while there was no evidence of ‘actual intent to infringe’ . . . . [the only\\nplausible explanation for the marks’ similarity was] Coalition’s intent to benefit from\\nAlliance’s pre-existing reputation”).\\n 6\\n\\f Case: 18-30759 Document: 00514882154 Page: 7 Date Filed: 03/21/2019\\n\\n\\n\\n No. 18-30759\\nlaches defense; 19 a “counterclaim without any actionable conduct”; and a\\nmeritless motion to dismiss that was rendered moot by a summary judgment\\nmotion filed two weeks later. 20 The district court also found that Coalition’s\\nbehavior during discovery was unreasonable, especially its refusal to postpone\\ndepositions after the district court ruled on the parties’ cross-motions for\\nsummary judgment.\\n Coalition urges that it was the unwilling defendant in a lawsuit initiated\\nby Alliance. To the extent that Coalition argues that only prevailing defendants\\nshould be awarded fees under the Lanham Act, we cannot agree. 21 The district\\ncourt did not abuse its discretion in concluding that taken as a whole,\\nCoalition’s litigation conduct rendered this case exceptional.\\n C\\n We pause to address Coalition’s argument that as a nonprofit entity\\nengaged in political speech, its First Amendment rights are threatened by the\\nimposition of attorney’s fees. This is a variant of Coalition’s earlier argument,\\nmade during the summary judgment appeal, that the First Amendment\\nprotected it from liability for trademark infringement. We declined to address\\nthis argument on the summary judgment appeal because “Coalition never\\ndeveloped the argument beyond [a cursory statement] and, by the time of the\\n\\n\\n\\n 19 Specifically, Coalition was unable to point to any evidence beyond a bare-bones\\naffidavit to show that Coalition used its logo to endorse candidates between 2010 and 2016—\\na critical aspect of its laches defense.\\n 20 While Coalition points out that Alliance also filed a motion to dismiss alongside its\\n\\nmotion for summary judgment, it fails to acknowledge the difference in context. Alliance filed\\na motion to dismiss Coalition’s counterclaims for failure to state a claim after moving for\\npartial summary judgment on its own federal trademark infringement claim.\\n 21 This suggestion is both waived by Coalition’s failure to argue it in its opening brief\\n\\nand contradicted by a wealth of cases granting fees to prevailing Lanham Act cases. See\\n“Recovery of Attorney’s Fees—Award to a Prevailing Plaintiff,” 5 McCarthy on Trademarks\\n& Unfair Competition § 30:100 (5th ed.) (collecting cases awarding fees to prevailing\\nplaintiffs, including many decided even before Octane Fitness clarified that a prevailing\\nplaintiff did not need to show willful infringement to recover fees under the Patent Act).\\n 7\\n\\f Case: 18-30759 Document: 00514882154 Page: 8 Date Filed: 03/21/2019\\n\\n\\n\\n No. 18-30759\\nsummary judgment proceedings, the issue had vanished.” 22 Ultimately, we\\nobserved, “[t]he interplay between the Lanham Act and the First Amendment’s\\npolitical and commercial speech doctrines raises a thicket of issues we decline\\nto enter when the issues were not preserved or ruled on below.” 23 Here too,\\nCoalition fleetingly raises the slightly different argument that a fees award\\nmight interfere with its First Amendment rights, but it did not so contend\\nbefore the district court in its opposition to attorney’s fees, nor did it present a\\nfully developed argument in its briefing on this appeal. We will not reach the\\nissue.\\n IV\\n We have concluded that the district court did not abuse its discretion in\\nfinding Alliance to be entitled to attorney’s fees. We agree with Coalition,\\nhowever, that the district court must reassess their amount given our decision\\nto modify the district court’s injunction to allow Coalition to continue the use\\nof its trade name.\\n When a party advances both Lanham Act and non-Lanham Act claims,\\na district court should make efforts to award fees only for successful Lanham\\nAct claims. 24 This reflects “the background rule in America . . . [that] the\\nprevailing party usually cannot recover fees absent statutory authority.” 25 The\\nsame apportionment principle should apply “when in one lawsuit some\\nLanham Act claims qualify for an attorney’s fee award and other Lanham Act\\nclaims do not.” 26\\n\\n\\n\\n\\n Alliance I, 901 F.3d at 506.\\n 22\\n\\n Id. at 506 n.8.\\n 23\\n 24 Procter & Gamble Co. v. Amway Corp., 280 F.3d 519, 527 (5th Cir. 2002).\\n 25 Id.\\n 26 See “Recovery of Attorney’s Fees—Apportionment Among Claims,” 5 McCarthy on\\n\\nTrademarks & Unfair Competition § 30:103; see also Cairns v. Franklin Mint Co., 292 F.3d\\n1139, 1157–58 (9th Cir. 2002) (affirming a twenty-six-percent reduction in fees where the\\n 8\\n\\f Case: 18-30759 Document: 00514882154 Page: 9 Date Filed: 03/21/2019\\n\\n\\n\\n No. 18-30759\\n Here, Alliance prevailed on its claim that Coalition’s logo infringed\\nAlliance’s composite mark—and, as we have explained, the district court did\\nnot abuse its discretion in holding that Alliance was entitled to fees on this\\nclaim. Alliance did not prevail, however, in its effort to enjoin Coalition from\\nusing the “Coalition for Better Government” designation. 27 Further, Alliance\\nvoluntarily dismissed its other counts after prevailing on the main trademark\\ninfringement claim; the district court’s fee award did not distinguish between\\ntime spent on the infringement claim and time Alliance’s attorneys spent—\\nhowever limited—on these other counts. Alliance is only entitled to fees for\\nwork its attorneys performed on its claim that Coalition’s logo infringed its\\ncomposite mark.\\n While Alliance’s composite-mark claim may be intertwined with its other\\nclaims to some extent, 28 “the impossibility of making an exact apportionment\\ndoes not relieve the district court of its duty to make some attempt to adjust\\nthe fee award in an effort to reflect an apportionment.” 29 We remand to the\\nable district court to account for billed time for claims on which Alliance did\\nnot prevail, and to adjust the fee award accordingly.\\n\\n\\n\\n\\nlosing party brought some Lanham Act claims that merited fees alongside other claims that,\\nalthough unsuccessful, were not groundless).\\n 27 While Alliance frequently referred to the marks collectively and addressed federal\\n\\ntrademark infringement of both marks in a single count of its complaint, we analyzed the\\ncomposite and word marks separately for the purposes of summary judgment.\\n 28 Cf. Procter & Gamble, 280 F.3d at 527 (explaining that where a party has brought\\n\\nboth Lanham Act and non-Lanham Act claims, “[a] court should permit recovery for work on\\nnon-Lanham Act claims only if ‘the Lanham Act and non-Lanham Act claims are so\\nintertwined that it is impossible to differentiate between work done on claims’” (quoting\\nGracie v. Gracie, 217 F.3d 1060, 1069 (9th Cir. 2000)).\\n 29 Gracie, 217 F.3d at 1070.\\n\\n 9\\n\\f Case: 18-30759 Document: 00514882154 Page: 10 Date Filed: 03/21/2019\\n\\n\\n\\n No. 18-30759\\n V\\n We affirm the district court’s determination that Alliance is entitled to\\nattorney’s fees, vacate the amount of fees awarded, and remand for the district\\ncourt to assess the amount of the award of fees in light of this opinion. 30\\n Affirmed in part and remanded in part.\\n\\n\\n\\n\\n 30We do not address Coalition’s argument that the district court erred in denying its\\nmotion to strike, as Coalition failed to identify this as one of the issues presented for review\\nand did not present legal authority to support its contention. See, e.g., Procter & Gamble Co.\\nv. Amway Corp. 376 F.3d 496, 499 n.1 (5th Cir. 2004) (“Failure adequately to brief an issue\\non appeal constitutes waiver of that argument.”).\\n 10\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1096,"cells":{"id":{"kind":"number","value":4603084,"string":"4,603,084"},"name":{"kind":"string","value":"Teresa BUCHANAN, Plaintiff - Appellant v. F. King ALEXANDER; Damon Andrew; A. G. Monaco; Gaston Reinoso, Defendants - Appellees"},"name_abbreviation":{"kind":"string","value":"Teresa Buchanan v. F. Alexander"},"decision_date":{"kind":"string","value":"2019-03-22"},"docket_number":{"kind":"string","value":"18-30148"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Wiener, Southwick, Costa\", \"parties\": \"\", \"opinions\": [{\"author\": \"WIENER, Circuit Judge\", \"type\": \"010combined\", \"text\": \"Case: 18-30148 Document: 00514885022 Page: 1 Date Filed: 03/22/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n No. 18-30148 March 22, 2019\\n Lyle W. Cayce\\n Clerk\\nTERESA BUCHANAN,\\n\\n Plaintiff - Appellant\\n\\nv.\\n\\nF. KING ALEXANDER; DAMON ANDREW; A. G. MONACO; GASTON\\nREINOSO,\\n\\n Defendants - Appellees\\n\\n\\n\\n\\n Appeal from the United States District Court\\n for the Middle District of Louisiana\\n\\n\\nBefore WIENER, SOUTHWICK, and COSTA, Circuit Judges.\\nWIENER, Circuit Judge\\n Plaintiff-Appellant Dr. Teresa Buchanan (“Dr. Buchanan”) was fired\\nfrom her tenured professorship by the Board of Supervisors (“the Board”) of\\nLouisiana State University and Agricultural and Mechanical College (“LSU”)\\nin June 2015. In January 2016, Dr. Buchanan filed the instant lawsuit against\\n(1) F. King Alexander (“President Alexander”), President and Chancellor of\\nLSU; (2) Damon Andrew (“Dean Andrew”), Dean of the College of Human\\nSciences and Education at LSU; (3) A.G. Monaco (“Vice Chancellor Monaco”),\\nVice Chancellor of the Office Human Resource Management at LSU; and (4)\\nGaston Reinoso (“Director Reinoso”), Director of the Office of Human Resource\\n\\f Case: 18-30148 Document: 00514885022 Page: 2 Date Filed: 03/22/2019\\n\\n\\n\\n No. 18-30148\\nManagement and Executive Director of Equal Employment Opportunities at\\nLSU (collectively “Defendants”). Dr. Buchanan alleged (a) that Defendants\\nviolated her First and Fourteenth Amendment right to free speech and\\nacademic freedom (the “as-applied challenge”), (b) that Defendants violated her\\nFourteenth Amendment procedural and substantive due process rights, and (c)\\na facial challenge to LSU’s sexual harassment policies (the “facial challenge”).\\nDr. Buchanan sought reinstatement and declaratory and injunctive relief. On\\ncross-motions for summary judgment, the district court granted Defendants’\\nmotion and dismissed Dr. Buchanan’s claims. Dr. Buchanan now appeals that\\ndecision.\\n I. FACTS AND PROCEEDINGS\\n A. Factual Background\\n Before she was fired, Dr. Buchanan was an associate professor at LSU\\nwith tenure. She taught in the Early Childhood Program for teacher education.\\nIn November 2013, LSU received a complaint from the superintendent of a\\nlocal public school district regarding Dr. Buchanan’s “professionalism and her\\nbehavior” when she visited schools in his district. LSU also received complaints\\nfrom some of Dr. Buchanan’s students regarding her classroom behavior. One\\nstudent complained about Dr. Buchanan’s comments regarding the student’s\\nsexual relationship with her fiancé. 1 Another student complained that Dr.\\nBuchanan recorded her crying during an assessment team meeting. 2 LSU had\\nreceived a letter in 2012 from a group of students complaining that Dr.\\n\\n\\n\\n 1 “According to Student 1: ‘Dr. Buchanan had offered them condoms, had told them it\\nwas unacceptable to become pregnant. And that if you chose to become a mother, that your\\ngrades would suffer for that. She told them . . . enjoy the sex while the sex is – good. If you’re\\ndating – if you’re dating, make sure the sex is good, something along those lines.’” Dr.\\nBuchanan further told the student that her fiancé was “supportive now while the sex is good,\\nbut just wait until you’re married five years.”\\n 2 This student claimed that Dr. Buchanan was aggressive during the meeting and\\n\\nyelled at her. The student stated that she felt attacked.\\n 2\\n\\f Case: 18-30148 Document: 00514885022 Page: 3 Date Filed: 03/22/2019\\n\\n\\n\\n No. 18-30148\\nBuchanan made offensive classroom comments, such as (1) “a woman is\\nthought to be a dike if she wears brown pants”; (2) “it was a choice to be in the\\nprogram and it was not the fault or problem of the professors if any of us chose\\nto be mommies or wives and not to expect to get an A in the class”; and (3) use\\nof “extreme profanity on a regular basis.”\\n These complaints were reported to Associate Dean Jennifer Curry\\n(“Dean Curry”) who discussed them with Dr. Earl Cheek (“Dr. Cheek”),\\nDirector of the College of Education. After learning of these incidents, Dean\\nAndrew directed Dean Curry to gather the complaints; he then consulted with\\nHuman Resources. 3 In December 2013, Dean Andrew told Dr. Buchanan that\\nshe would be removed from the classroom during a human resources\\ninvestigation. Director Reinoso investigated to determine whether Dr.\\nBuchanan had violated LSU policies, interviewed witnesses, and wrote a\\nreport. Dean Andrew reviewed Director Reinoso’s report and recommended\\nappointment of a Faculty Senate Grievance Committee (“Faculty Committee”)\\nunder LSU’s Policy Statement-104 for Dismissal for Cause of Faculty. In\\nJanuary 2014, Dr. Buchanan met with Director Reinoso and other human\\nresources managers to discuss the complaints.\\n In May 2014, Director Reinoso sent a memorandum to Dr. Buchanan\\nwhich stated that he found her “actions and behavior . . . inappropriate,\\nunwelcome, and a direct violation of the University’s Policy Statements on\\nSexual Harassment, PS-73 and PS-95” and her “reported communication style\\nwith students, faculty, and outside administrators . . . to be inappropriate.” In\\nJune 2014, Dean Andrew met with Dr. Buchanan to discuss Director Reinoso’s\\nreport, and they subsequently communicated about the report in writing. In\\n\\n\\n\\n 3 While gathering the complaints, Dean Curry was informed that Dr. Buchanan “was\\nno longer authorized to be on any Iberville Parish school campus.”\\n 3\\n\\f Case: 18-30148 Document: 00514885022 Page: 4 Date Filed: 03/22/2019\\n\\n\\n\\n No. 18-30148\\nJuly 2014, Dean Andrew recommended to Provost Stuart Bell that Dr.\\nBuchanan be dismissed for cause. Provost Bell then requested and impaneled\\na Faculty Committee.\\n In March 2015, the Faculty Committee held a lengthy hearing regarding\\nDr. Buchanan’s classroom behavior. The Faculty Committee concluded that\\nDr. Buchanan had violated LSU’s sexual harassment policies, PS-73 and PS-\\n95, “through her use of profanity, poorly worded jokes, and sometimes sexually\\nexplicit ‘jokes.’” The Committee also found that Dr. Buchanan had created a\\n“hostile learning environment.” The Committee recommended censure.\\n In April 2015, despite the Faculty Committee’s censure recommendation,\\nPresident Alexander informed Dr. Buchanan that he was going to recommend\\nto the Board that she be dismissed for cause and violations of LSU’s policies\\nand the Americans with Disabilities Act (“ADA”). 4 Dr. Buchanan appealed this\\nrecommendation and addressed the Board. The Board fired Dr. Buchanan in\\nJune 2015.\\n B. Procedural Background\\n Dr. Buchanan filed this lawsuit after she was fired. The parties filed\\ncross-motions for summary judgment. The district court denied Dr.\\nBuchanan’s motion and granted Defendants’ motion, holding that: (1) for\\npurposes of these Defendants’ qualified immunity, liability for retaliation in\\nviolation of the First Amendment based on a defendant’s merely causing an\\nadverse employment action was not clearly established, (2) there was no\\nevidence of a violation of Dr. Buchanan’s First Amendment right to academic\\nfreedom, (3) LSU’s sexual harassment policies were not facially overbroad, (4)\\nLSU’s sexual harassment policies as applied to Dr. Buchanan did not violate\\n\\n\\n 4 The Faculty Committee also investigated whether Dr. Buchanan violated the ADA\\nby revealing a student’s medical information to other students. The Committee found\\ninsufficient evidence to establish an ADA violation.\\n 4\\n\\f Case: 18-30148 Document: 00514885022 Page: 5 Date Filed: 03/22/2019\\n\\n\\n\\n No. 18-30148\\nher First Amendment rights, and (5) Defendants did not violate Dr.\\nBuchanan’s right to procedural due process. 5 Dr. Buchanan now appeals the\\ndistrict court’s denial of her facial and as-applied challenges to LSU’s sexual\\nharassment policies and the district court’s holdings that Defendants are not\\npersonally liable.\\n II. LAW AND ANALYSIS\\n A. As-Applied Challenge\\n When a litigant brings both as-applied and facial challenges, we\\ngenerally decide the as-applied challenge first because it is the narrower\\nconsideration. 6 The Fifth Circuit reviews summary judgments de novo 7 and\\ncases raising First Amendment issues by examining the whole record. 8\\n The Supreme Court has established that academic freedom is “a special\\nconcern of the First Amendment, which does not tolerate laws that cast a pall\\nof orthodoxy over the classroom.” 9 Accordingly, “classroom discussion is\\nprotected activity.” 10 However, even this protection has limits: Students,\\nteachers, and professors are not permitted to say anything and everything\\nsimply because the words are uttered in the classroom context. 11\\n\\n\\n 5 Buchanan v. Alexander, 284 F. Supp. 3d 792 (M.D. La. 2018).\\n 6 Serafine v. Branaman, 810 F.3d 354, 362 (5th Cir. 2016).\\n 7 MacLachlan v. ExxonMobil Corp., 350 F.3d 472, 478 (5th Cir. 2003), abrogated on\\n\\nother grounds by Crowell v. Shell Oil Co., 541 F.3d 295 (5th Cir. 2008).\\n 8 Denton v. Morgan, 136 F.3d 1038, 1042–43 (5th Cir. 1998).\\n 9 Keyishian v. Bd. of Regents, 385 U.S. 589, 603 (1967).\\n 10 Kingsville Indep. Sch. Dist. v. Cooper, 611 F.2d 1109, 1113 (5th Cir. 1980).\\n 11 See, e.g., Bethel Sch. Dist. No. 403 v. Fraser, 478 U.S. 675 (1986) (holding that\\n\\nstudent could not claim First Amendment protection for offensively lewd and indecent\\nspeech); Martin v. Parrish, 805 F.2d 583 (5th Cir. 1986) (holding that professor had no First\\nAmendment right to use profane language in the classroom). In his book, Democracy,\\nExpertise, and Academic Freedom, Robert C. Post, Yale Law Professor and former Dean of\\nYale Law School and general counsel for the AAUP, discusses the limits of First Amendment\\nacademic freedom. He notes that the value of academic freedom depends on universities\\nholding professors to professional standards in contrast with the traditional First\\nAmendment value of the free marketplace of ideas. Therefore, “[t]he right question for courts\\nto ask about academic freedom is how to fashion doctrine that best protects the ‘freedom of\\n 5\\n\\f Case: 18-30148 Document: 00514885022 Page: 6 Date Filed: 03/22/2019\\n\\n\\n\\n No. 18-30148\\n Public university professors are public employees. To establish a § 1983\\nclaim for violation of the First Amendment right to free speech, they must show\\nthat (1) they were disciplined or fired for speech that is a matter of public\\nconcern, and (2) their interest in the speech outweighed the university’s\\ninterest in regulating the speech. 12 The first question, asking whether the\\nprofessor’s speech is protected as a matter of public concern, is a question of\\nlaw. 13\\n The inquiry into whether Plaintiff’s interests in speaking\\n outweigh the College’s interests in regulating Plaintiff’s speech is\\n a factual determination conducted under the well known\\n Pickering[-Connick] balancing test. . . . If Plaintiff’s interests in the\\n prohibited speech outweigh the College’s interests, then Plaintiff’s\\n First Amendment rights have been violated. . . . If the First\\n Amendment violation was a substantial or motivating factor in\\n Defendants’ disciplinary action against Plaintiff, Defendants may\\n present evidence that they would have disciplined Plaintiff in the\\n absence of his protected conduct. . . . However, if Plaintiff’s speech\\n does not involve a matter of public concern, it is unnecessary for\\n the court to scrutinize the reason for the discipline. 14\\n\\n If Dr. Buchanan did not speak as a citizen on a matter of public concern,\\nthen she has no First Amendment claim for LSU’s response to her speech. 15\\n“[W]hether an employee’s speech addresses a matter of public concern must be\\ndetermined by the content, form, and context of a given statement, as revealed\\n\\n\\n\\nthought, of inquiry . . . of the academic profession.’” Robert C. Post, Democracy, Expertise,\\nand Academic Freedom: A First Amendment Jurisprudence for the Modern State 67, 80 (2012)\\n(quoting the 1915 Declaration of Principles on Academic Freedom and Academic Tenure\\nreprinted in American Association of University Professors, Policy Documents and Reports\\n291-301 (9th ed. 2001)).\\n 12 See Connick v. Myers, 461 U.S. 138, 147–50 (1983); Pickering v. Bd. of Educ., 391\\n\\nU.S. 563, 568 (1968); Martin, 805 F.2d at 584.\\n 13 Connick, 461 U.S. at 148 n.7; Tompkins v. Vickers, 26 F.3d 603, 606 (5th Cir. 1994).\\n 14 Bonnell v. Lorenzo, 241 F.3d 800, 810 (6th Cir. 2001) (citing Pickering, 391 U.S. at\\n\\n568; Dambrot v. Cent. Mich. Univ., 55 F.3d 1177, 1186 (6th Cir. 1995); Mt. Healthy City Sch.\\nDist. Bd. of Educ. v. Doyle, 429 U.S. 274, 285 (1977); Connick, 461 U.S. at 146).\\n 15 See Connick, 461 U.S. at 147–48.\\n\\n 6\\n\\f Case: 18-30148 Document: 00514885022 Page: 7 Date Filed: 03/22/2019\\n\\n\\n\\n No. 18-30148\\nby the whole record.” 16 “Speech involves a matter of public concern when it\\ninvolves an issue of social, political, or other interest to a community.” 17 When\\na public employee speaks in his capacity as an employee and on personal\\nmatters, rather than in his capacity as a citizen on a matter of public interest,\\nhis speech falls outside the protection of the First Amendment. 18 A mere\\nelement of personal concern, however, does not prevent finding that an\\nemployee’s speech as a whole includes a matter of public concern. 19\\n We agree with the district court here that Dr. Buchanan’s use of\\nprofanity and discussion of her sex life and the sex lives of her students was\\nnot related to the subject matter or purpose of training Pre-K–Third grade\\nteachers. This court has held that, in the college classroom context, speech that\\ndoes not serve an academic purpose is not of public concern. 20 Dr. Buchanan\\nwould rely on the Ninth Circuit’s holding in Cohen v. San Bernardino Valley\\n\\n\\n\\n\\n 16 Id. at 147–48.\\n 17 Adams v. Trustees of the Univ. of N.C.–Wilmington, 640 F.3d 550, 564 (4th Cir. 2011)\\n(quoting Kirby v. City of Elizabeth City, 388 F.3d 440, 446 (4th Cir. 2004)) (citing Connick,\\n461 U.S. at 146).\\n 18 Kennedy v. Tangipahoa Parish Library Bd. of Control, 224 F.3d 359, 366 (5th Cir.\\n\\n2000), abrogated on other grounds by Gibson v. Kilpatrick, 838 F.3d 476 (5th Cir. 2016) (citing\\nConnick, 461 U.S. at 147).\\n 19 Id. at 365.\\n 20 Martin, 805 F.2d at 585 (holding that a professor’s use of profanity to castigate his\\n\\nstudents was not a matter of public concern because it served no academic purpose); see also\\nBonnell, 241 F.3d at 820 (holding that a professor “may have a constitutional right to use\\nwords such as ‘pussy,’ ‘cunt,’ and ‘fuck,’ but he does not have a constitutional right to use\\nthem in a classroom setting where they are not germane to the subject matter”); Dambrot, 55\\nF.3d at 1190 (holding that “[a]n instructor’s choice of teaching methods does not rise to the\\nlevel of protected expression”); cf. Hardy v. Jefferson Cmty. Coll., 260 F.3d 671, 682 (6th Cir.\\n2001) (holding that a professor’s right to use vulgarity and racial slurs during analysis of the\\nhistorical use of oppressive and marginalizing language was protected speech); Kerr v. Hurd,\\n694 F. Supp. 2d 817, 842–43 (S.D. Ohio 2010) (holding that discussion and advocacy of a\\nmedical technique during classroom instruction was a matter of public concern because it\\nwas relevant to a national debate on best practices for delivering babies).\\n 7\\n\\f Case: 18-30148 Document: 00514885022 Page: 8 Date Filed: 03/22/2019\\n\\n\\n\\n No. 18-30148\\nCollege 21 that a university’s sexual harassment policy was “simply too vague\\nas applied . . . [because the professor’s] speech did not fall within the core region\\nof sexual harassment as defined by the Policy.” 22 Dr. Buchanan’s speech is\\neasily distinguished from Professor Cohen’s speech. In Cohen, the use of\\nprofanity and discussion of controversial viewpoints was “at least tangentially\\nrelated” to teaching college-level English. 23 Here, the use of profanity and\\ndiscussion of professors’ and students’ sex lives were clearly not related to the\\ntraining of Pre-K–Third grade teachers. Dr. Buchanan’s speech was not,\\ntherefore, a matter of public concern; we thus affirm the district court’s holding\\nthat LSU’s policies did not violate the First Amendment as applied to Dr.\\nBuchanan because her speech was not protected.\\n B. Facial Challenge\\n “Generally, we ‘proceed to an overbreadth issue’ only if ‘it is determined\\nthat the statute would be valid as applied.’” 24 Here, because Dr. Buchanan’s\\nas-applied challenge fails, we proceed to consideration of the facial overbreadth\\nchallenge.\\n Dr. Buchanan sued the wrong parties. The proper defendants to a facial\\nchallenge are the parties responsible for creating or enforcing the challenged\\nlaw or policy. 25 In Jordahl v. Democratic Party of Virginia, the Fourth Circuit\\nheld that the plaintiffs had failed to present a facial challenge. 26 Those\\n\\n\\n 21 92 F.3d 968 (9th Cir. 1996) (discussing discipline of a college professor for his use of\\nprofanity, discussion of pornography, and assertion of other controversial viewpoints during\\nclass discussion in a college-level English class).\\n 22 Id. at 972 (reasoning that the vagueness of the policy did not provide notice to the\\n\\nprofessor that it would be applied to his “longstanding teaching style”).\\n 23 Buchanan, 284 F. Supp. 3d at 834.\\n 24 Serafine, 810 F.3d at 362–63 (quoting Bd. of Trs. v. Fox, 492 U.S. 469, 484–85\\n\\n(1989)).\\n 25 See Jordahl v. Democratic Party of Va., 122 F.3d 192, 199 n.6 (4th Cir. 1997)\\n\\n(reasoning that for a facial challenge to a state law, the proper party was the state rather\\nthan the party seeking an injunction under the law).\\n 26 Id. at 199.\\n\\n 8\\n\\f Case: 18-30148 Document: 00514885022 Page: 9 Date Filed: 03/22/2019\\n\\n\\n\\n No. 18-30148\\nplaintiffs had sued the Democratic Party of Virginia (“DPV”) alleging a\\nviolation of their free speech rights after the DPV sought injunctions\\n“forbidding the plaintiffs from distributing [voter] guides.” 27 The appeals court\\nreasoned that, even though the DPV was the direct actor seeking enforcement\\nof state statutes and an injunction against plaintiffs, it was not the proper\\nparty to a facial challenge. 28 Similarly, when professors or students challenge\\na university’s policies, the proper defendant party is the university or\\nuniversity board. 29\\n Here, Dr. Buchanan has sued only employees and officials with\\nindividual and limited roles in administration of LSU’s polices, but with no\\nultimate authority to enforce them. She failed to sue the Board of Supervisors,\\nwhich is responsible for the creation and enforcement of the policies. 30 The\\nBoard, therefore, is the only proper party defendant to a facial challenge to\\nLSU’s policies. 31 We therefore vacate the district court’s ruling on the facial\\n\\n\\n\\n 27 Id. at 194.\\n 28 Id. at 194, 199 n.6.\\n 29 See e.g., DeJohn v. Temple Univ., 537 F.3d 301 (3rd Cir. 2008) (deciding graduate\\n\\nstudent’s facial challenge to university’s sexual harassment policy brought against\\nuniversity); Piggee v. Carl Sandburg Coll., 464 F.3d 667 (7th Cir. 2006) (deciding professor’s\\nchallenge to college’s sexual harassment policy brought against college); Saxe v. State Coll.\\nArea Sch. Dist., 240 F.3d 200 (3rd Cir. 2001) (deciding students’ facial challenge to school\\ndistrict’s anti-harassment policy brought against school district); Dambrot, 55 F.3d 1177\\n(deciding coach’s challenge to university’s harassment policy brought against university).\\n 30 The Louisiana Constitution grants the LSU Board of Supervisors the authority to\\n\\n“supervise and manage” the school. La. Const. art. VIII, § 7. The Board of Supervisors’ Bylaws\\nstate that the President establishes administrative and educational policies subject to the\\ndirection and control of the Board. Bylaws, Board of Supervisors, LSU, LSU.edu (Dec. 12,\\n2018, 3:01 PM), https://lsu.edu/bos/docs/bylaws-adopted-2018-10-04.pdf. LSU PS-104 states\\nthat a recommendation to dismiss a tenured faculty member for cause requires confirmation\\nby the Board.\\n 31 We distinguish this case from Esfeller v. O’Keefe, 391 F. App’x 337 (5th Cir. 2010)\\n\\n(unpublished). In Esfeller, a student brought a facial challenge to LSU’s Student Code of\\nConduct. The student sued the LSU Board of Supervisors, and the district court dismissed\\nthe Board. On appeal his court held that the Code was not facially overbroad. There, the\\nplaintiff student did not appeal dismissal of the Board, and, unlike the policy in this case, the\\nuniversity president had ultimate authority to enforce the Code.\\n 9\\n\\f Case: 18-30148 Document: 00514885022 Page: 10 Date Filed: 03/22/2019\\n\\n\\n\\n No. 18-30148\\nchallenge and dismiss that claim for Dr. Buchanan’s has failure to sue the\\nproper party.\\n C. Qualified Immunity\\n We need not address the district court’s holding on qualified immunity\\nbecause Dr. Buchanan’s claims fail. We nevertheless affirm that all\\nDefendants are entitled to qualified immunity on her damages claims.\\n The qualified immunity inquiry comprises two questions: (1) “whether\\nthe defendant violated the plaintiff’s constitutional rights” and (2) whether\\nthat right was clearly established. 32 “We now have discretion to skip the first\\ninquiry and resolve a case solely on clearly established grounds.” 33 Before this\\ncourt issued its 2018 opinion in Sims v. City of Madisonville, the law was\\nunsettled whether a nondecisionmaker defendant who only recommended that\\na plaintiff be fired could be held liable for a § 1983 First Amendment claim 34:\\n Although [Sims] clarif[ied] that Jett controls . . . , it provides\\n no recourse to [Buchanan]. That is because of the second part of\\n the qualified immunity inquiry, which requires a plaintiff to show\\n that any violation of rights was clearly established at the time the\\n conduct occurred. When [Buchanan] was terminated in [June\\n 2015] the inconsistency in our law on whether First Amendment\\n liability can attach to a public official who did not make the final\\n employment decision had not been resolved. . . . If judges have\\n mixed up principles of . . . liability in this area and failed to\\n recognize Jett as the controlling decision, [school] officials should\\n not be expected to have a more nuanced understanding of section\\n 1983 law. 35\\n\\nAlthough the district court did not discuss this unsettled matter of law in its\\nreasoning on qualified immunity, its holding that Defendants’ acts were\\n\\n\\n\\n\\n 32 Sims v. City of Madisonville, 894 F.3d 632, 638 (5th Cir. 2018).\\n 33 Id. (citing Pearson v. Callahan, 555 U.S. 223, 240 (2009)).\\n 34 Sims, 894 F.3d at 638, 640; Culbertson v. Lykos, 790 F.3d 608, 627 (5th Cir. 2015).\\n 35 Sims, 894 F.3d at 641.\\n\\n 10\\n\\f Case: 18-30148 Document: 00514885022 Page: 11 Date Filed: 03/22/2019\\n\\n\\n\\n No. 18-30148\\nobjectively reasonable considering clearly established law at the time was not\\nerror.\\n III. CONCLUSION\\n The district court correctly concluded that Dr. Buchanan’s speech was\\nnot protected by the First Amendment. The district court’s holding on the as-\\napplied challenge is AFFIRMED. On the facial challenge, Dr. Buchanan has\\nnot sued the proper party. The district court’s holding on the facial challenge\\nis VACATED and Dr. Buchanan’s claim is DISMISSED on this alternate\\nground.\\n\\n\\n\\n\\n 11\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4380337/\", \"author_raw\": \"WIENER, Circuit Judge\"}]}"},"judge1":{"kind":"string","value":"WIENER"},"judge2":{"kind":"string","value":"SOUTHWICK"},"judge3":{"kind":"string","value":"COSTA"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4603084/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Teresa BUCHANAN, Plaintiff - Appellant v. F. King ALEXANDER; Damon Andrew; A. G. Monaco; Gaston Reinoso, Defendants - Appellees\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-22\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 18-30148 Document: 00514885022 Page: 1 Date Filed: 03/22/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT United States Court of Appeals\n Fifth Circuit\n\n FILED\n No. 18-30148 March 22, 2019\n Lyle W. Cayce\n Clerk\nTERESA BUCHANAN,\n\n Plaintiff - Appellant\n\nv.\n\nF. KING ALEXANDER; DAMON ANDREW; A. G. MONACO; GASTON\nREINOSO,\n\n Defendants - Appellees\n\n\n\n\n Appeal from the United States District Court\n for the Middle District of Louisiana\n\n\nBefore WIENER, SOUTHWICK, and COSTA, Circuit Judges.\nWIENER, Circuit Judge\n Plaintiff-Appellant Dr. Teresa Buchanan (“Dr. Buchanan”) was fired\nfrom her tenured professorship by the Board of Supervisors (“the Board”) of\nLouisiana State University and Agricultural and Mechanical College (“LSU”)\nin June 2015. In January 2016, Dr. Buchanan filed the instant lawsuit against\n(1) F. King Alexander (“President Alexander”), President and Chancellor of\nLSU; (2) Damon Andrew (“Dean Andrew”), Dean of the College of Human\nSciences and Education at LSU; (3) A.G. Monaco (“Vice Chancellor Monaco”),\nVice Chancellor of the Office Human Resource Management at LSU; and (4)\nGaston Reinoso (“Director Reinoso”), Director of the Office of Human Resource\n\f Case: 18-30148 Document: 00514885022 Page: 2 Date Filed: 03/22/2019\n\n\n\n No. 18-30148\nManagement and Executive Director of Equal Employment Opportunities at\nLSU (collectively “Defendants”). Dr. Buchanan alleged (a) that Defendants\nviolated her First and Fourteenth Amendment right to free speech and\nacademic freedom (the “as-applied challenge”), (b) that Defendants violated her\nFourteenth Amendment procedural and substantive due process rights, and (c)\na facial challenge to LSU’s sexual harassment policies (the “facial challenge”).\nDr. Buchanan sought reinstatement and declaratory and injunctive relief. On\ncross-motions for summary judgment, the district court granted Defendants’\nmotion and dismissed Dr. Buchanan’s claims. Dr. Buchanan now appeals that\ndecision.\n I. FACTS AND PROCEEDINGS\n A. Factual Background\n Before she was fired, Dr. Buchanan was an associate professor at LSU\nwith tenure. She taught in the Early Childhood Program for teacher education.\nIn November 2013, LSU received a complaint from the superintendent of a\nlocal public school district regarding Dr. Buchanan’s “professionalism and her\nbehavior” when she visited schools in his district. LSU also received complaints\nfrom some of Dr. Buchanan’s students regarding her classroom behavior. One\nstudent complained about Dr. Buchanan’s comments regarding the student’s\nsexual relationship with her fiancé. 1 Another student complained that Dr.\nBuchanan recorded her crying during an assessment team meeting. 2 LSU had\nreceived a letter in 2012 from a group of students complaining that Dr.\n\n\n\n 1 “According to Student 1: ‘Dr. Buchanan had offered them condoms, had told them it\nwas unacceptable to become pregnant. And that if you chose to become a mother, that your\ngrades would suffer for that. She told them . . . enjoy the sex while the sex is – good. If you’re\ndating – if you’re dating, make sure the sex is good, something along those lines.’” Dr.\nBuchanan further told the student that her fiancé was “supportive now while the sex is good,\nbut just wait until you’re married five years.”\n 2 This student claimed that Dr. Buchanan was aggressive during the meeting and\n\nyelled at her. The student stated that she felt attacked.\n 2\n\f Case: 18-30148 Document: 00514885022 Page: 3 Date Filed: 03/22/2019\n\n\n\n No. 18-30148\nBuchanan made offensive classroom comments, such as (1) “a woman is\nthought to be a dike if she wears brown pants”; (2) “it was a choice to be in the\nprogram and it was not the fault or problem of the professors if any of us chose\nto be mommies or wives and not to expect to get an A in the class”; and (3) use\nof “extreme profanity on a regular basis.”\n These complaints were reported to Associate Dean Jennifer Curry\n(“Dean Curry”) who discussed them with Dr. Earl Cheek (“Dr. Cheek”),\nDirector of the College of Education. After learning of these incidents, Dean\nAndrew directed Dean Curry to gather the complaints; he then consulted with\nHuman Resources. 3 In December 2013, Dean Andrew told Dr. Buchanan that\nshe would be removed from the classroom during a human resources\ninvestigation. Director Reinoso investigated to determine whether Dr.\nBuchanan had violated LSU policies, interviewed witnesses, and wrote a\nreport. Dean Andrew reviewed Director Reinoso’s report and recommended\nappointment of a Faculty Senate Grievance Committee (“Faculty Committee”)\nunder LSU’s Policy Statement-104 for Dismissal for Cause of Faculty. In\nJanuary 2014, Dr. Buchanan met with Director Reinoso and other human\nresources managers to discuss the complaints.\n In May 2014, Director Reinoso sent a memorandum to Dr. Buchanan\nwhich stated that he found her “actions and behavior . . . inappropriate,\nunwelcome, and a direct violation of the University’s Policy Statements on\nSexual Harassment, PS-73 and PS-95” and her “reported communication style\nwith students, faculty, and outside administrators . . . to be inappropriate.” In\nJune 2014, Dean Andrew met with Dr. Buchanan to discuss Director Reinoso’s\nreport, and they subsequently communicated about the report in writing. In\n\n\n\n 3 While gathering the complaints, Dean Curry was informed that Dr. Buchanan “was\nno longer authorized to be on any Iberville Parish school campus.”\n 3\n\f Case: 18-30148 Document: 00514885022 Page: 4 Date Filed: 03/22/2019\n\n\n\n No. 18-30148\nJuly 2014, Dean Andrew recommended to Provost Stuart Bell that Dr.\nBuchanan be dismissed for cause. Provost Bell then requested and impaneled\na Faculty Committee.\n In March 2015, the Faculty Committee held a lengthy hearing regarding\nDr. Buchanan’s classroom behavior. The Faculty Committee concluded that\nDr. Buchanan had violated LSU’s sexual harassment policies, PS-73 and PS-\n95, “through her use of profanity, poorly worded jokes, and sometimes sexually\nexplicit ‘jokes.’” The Committee also found that Dr. Buchanan had created a\n“hostile learning environment.” The Committee recommended censure.\n In April 2015, despite the Faculty Committee’s censure recommendation,\nPresident Alexander informed Dr. Buchanan that he was going to recommend\nto the Board that she be dismissed for cause and violations of LSU’s policies\nand the Americans with Disabilities Act (“ADA”). 4 Dr. Buchanan appealed this\nrecommendation and addressed the Board. The Board fired Dr. Buchanan in\nJune 2015.\n B. Procedural Background\n Dr. Buchanan filed this lawsuit after she was fired. The parties filed\ncross-motions for summary judgment. The district court denied Dr.\nBuchanan’s motion and granted Defendants’ motion, holding that: (1) for\npurposes of these Defendants’ qualified immunity, liability for retaliation in\nviolation of the First Amendment based on a defendant’s merely causing an\nadverse employment action was not clearly established, (2) there was no\nevidence of a violation of Dr. Buchanan’s First Amendment right to academic\nfreedom, (3) LSU’s sexual harassment policies were not facially overbroad, (4)\nLSU’s sexual harassment policies as applied to Dr. Buchanan did not violate\n\n\n 4 The Faculty Committee also investigated whether Dr. Buchanan violated the ADA\nby revealing a student’s medical information to other students. The Committee found\ninsufficient evidence to establish an ADA violation.\n 4\n\f Case: 18-30148 Document: 00514885022 Page: 5 Date Filed: 03/22/2019\n\n\n\n No. 18-30148\nher First Amendment rights, and (5) Defendants did not violate Dr.\nBuchanan’s right to procedural due process. 5 Dr. Buchanan now appeals the\ndistrict court’s denial of her facial and as-applied challenges to LSU’s sexual\nharassment policies and the district court’s holdings that Defendants are not\npersonally liable.\n II. LAW AND ANALYSIS\n A. As-Applied Challenge\n When a litigant brings both as-applied and facial challenges, we\ngenerally decide the as-applied challenge first because it is the narrower\nconsideration. 6 The Fifth Circuit reviews summary judgments de novo 7 and\ncases raising First Amendment issues by examining the whole record. 8\n The Supreme Court has established that academic freedom is “a special\nconcern of the First Amendment, which does not tolerate laws that cast a pall\nof orthodoxy over the classroom.” 9 Accordingly, “classroom discussion is\nprotected activity.” 10 However, even this protection has limits: Students,\nteachers, and professors are not permitted to say anything and everything\nsimply because the words are uttered in the classroom context. 11\n\n\n 5 Buchanan v. Alexander, 284 F. Supp. 3d 792 (M.D. La. 2018).\n 6 Serafine v. Branaman, 810 F.3d 354, 362 (5th Cir. 2016).\n 7 MacLachlan v. ExxonMobil Corp., 350 F.3d 472, 478 (5th Cir. 2003), abrogated on\n\nother grounds by Crowell v. Shell Oil Co., 541 F.3d 295 (5th Cir. 2008).\n 8 Denton v. Morgan, 136 F.3d 1038, 1042–43 (5th Cir. 1998).\n 9 Keyishian v. Bd. of Regents, 385 U.S. 589, 603 (1967).\n 10 Kingsville Indep. Sch. Dist. v. Cooper, 611 F.2d 1109, 1113 (5th Cir. 1980).\n 11 See, e.g., Bethel Sch. Dist. No. 403 v. Fraser, 478 U.S. 675 (1986) (holding that\n\nstudent could not claim First Amendment protection for offensively lewd and indecent\nspeech); Martin v. Parrish, 805 F.2d 583 (5th Cir. 1986) (holding that professor had no First\nAmendment right to use profane language in the classroom). In his book, Democracy,\nExpertise, and Academic Freedom, Robert C. Post, Yale Law Professor and former Dean of\nYale Law School and general counsel for the AAUP, discusses the limits of First Amendment\nacademic freedom. He notes that the value of academic freedom depends on universities\nholding professors to professional standards in contrast with the traditional First\nAmendment value of the free marketplace of ideas. Therefore, “[t]he right question for courts\nto ask about academic freedom is how to fashion doctrine that best protects the ‘freedom of\n 5\n\f Case: 18-30148 Document: 00514885022 Page: 6 Date Filed: 03/22/2019\n\n\n\n No. 18-30148\n Public university professors are public employees. To establish a § 1983\nclaim for violation of the First Amendment right to free speech, they must show\nthat (1) they were disciplined or fired for speech that is a matter of public\nconcern, and (2) their interest in the speech outweighed the university’s\ninterest in regulating the speech. 12 The first question, asking whether the\nprofessor’s speech is protected as a matter of public concern, is a question of\nlaw. 13\n The inquiry into whether Plaintiff’s interests in speaking\n outweigh the College’s interests in regulating Plaintiff’s speech is\n a factual determination conducted under the well known\n Pickering[-Connick] balancing test. . . . If Plaintiff’s interests in the\n prohibited speech outweigh the College’s interests, then Plaintiff’s\n First Amendment rights have been violated. . . . If the First\n Amendment violation was a substantial or motivating factor in\n Defendants’ disciplinary action against Plaintiff, Defendants may\n present evidence that they would have disciplined Plaintiff in the\n absence of his protected conduct. . . . However, if Plaintiff’s speech\n does not involve a matter of public concern, it is unnecessary for\n the court to scrutinize the reason for the discipline. 14\n\n If Dr. Buchanan did not speak as a citizen on a matter of public concern,\nthen she has no First Amendment claim for LSU’s response to her speech. 15\n“[W]hether an employee’s speech addresses a matter of public concern must be\ndetermined by the content, form, and context of a given statement, as revealed\n\n\n\nthought, of inquiry . . . of the academic profession.’” Robert C. Post, Democracy, Expertise,\nand Academic Freedom: A First Amendment Jurisprudence for the Modern State 67, 80 (2012)\n(quoting the 1915 Declaration of Principles on Academic Freedom and Academic Tenure\nreprinted in American Association of University Professors, Policy Documents and Reports\n291-301 (9th ed. 2001)).\n 12 See Connick v. Myers, 461 U.S. 138, 147–50 (1983); Pickering v. Bd. of Educ., 391\n\nU.S. 563, 568 (1968); Martin, 805 F.2d at 584.\n 13 Connick, 461 U.S. at 148 n.7; Tompkins v. Vickers, 26 F.3d 603, 606 (5th Cir. 1994).\n 14 Bonnell v. Lorenzo, 241 F.3d 800, 810 (6th Cir. 2001) (citing Pickering, 391 U.S. at\n\n568; Dambrot v. Cent. Mich. Univ., 55 F.3d 1177, 1186 (6th Cir. 1995); Mt. Healthy City Sch.\nDist. Bd. of Educ. v. Doyle, 429 U.S. 274, 285 (1977); Connick, 461 U.S. at 146).\n 15 See Connick, 461 U.S. at 147–48.\n\n 6\n\f Case: 18-30148 Document: 00514885022 Page: 7 Date Filed: 03/22/2019\n\n\n\n No. 18-30148\nby the whole record.” 16 “Speech involves a matter of public concern when it\ninvolves an issue of social, political, or other interest to a community.” 17 When\na public employee speaks in his capacity as an employee and on personal\nmatters, rather than in his capacity as a citizen on a matter of public interest,\nhis speech falls outside the protection of the First Amendment. 18 A mere\nelement of personal concern, however, does not prevent finding that an\nemployee’s speech as a whole includes a matter of public concern. 19\n We agree with the district court here that Dr. Buchanan’s use of\nprofanity and discussion of her sex life and the sex lives of her students was\nnot related to the subject matter or purpose of training Pre-K–Third grade\nteachers. This court has held that, in the college classroom context, speech that\ndoes not serve an academic purpose is not of public concern. 20 Dr. Buchanan\nwould rely on the Ninth Circuit’s holding in Cohen v. San Bernardino Valley\n\n\n\n\n 16 Id. at 147–48.\n 17 Adams v. Trustees of the Univ. of N.C.–Wilmington, 640 F.3d 550, 564 (4th Cir. 2011)\n(quoting Kirby v. City of Elizabeth City, 388 F.3d 440, 446 (4th Cir. 2004)) (citing Connick,\n461 U.S. at 146).\n 18 Kennedy v. Tangipahoa Parish Library Bd. of Control, 224 F.3d 359, 366 (5th Cir.\n\n2000), abrogated on other grounds by Gibson v. Kilpatrick, 838 F.3d 476 (5th Cir. 2016) (citing\nConnick, 461 U.S. at 147).\n 19 Id. at 365.\n 20 Martin, 805 F.2d at 585 (holding that a professor’s use of profanity to castigate his\n\nstudents was not a matter of public concern because it served no academic purpose); see also\nBonnell, 241 F.3d at 820 (holding that a professor “may have a constitutional right to use\nwords such as ‘pussy,’ ‘cunt,’ and ‘fuck,’ but he does not have a constitutional right to use\nthem in a classroom setting where they are not germane to the subject matter”); Dambrot, 55\nF.3d at 1190 (holding that “[a]n instructor’s choice of teaching methods does not rise to the\nlevel of protected expression”); cf. Hardy v. Jefferson Cmty. Coll., 260 F.3d 671, 682 (6th Cir.\n2001) (holding that a professor’s right to use vulgarity and racial slurs during analysis of the\nhistorical use of oppressive and marginalizing language was protected speech); Kerr v. Hurd,\n694 F. Supp. 2d 817, 842–43 (S.D. Ohio 2010) (holding that discussion and advocacy of a\nmedical technique during classroom instruction was a matter of public concern because it\nwas relevant to a national debate on best practices for delivering babies).\n 7\n\f Case: 18-30148 Document: 00514885022 Page: 8 Date Filed: 03/22/2019\n\n\n\n No. 18-30148\nCollege 21 that a university’s sexual harassment policy was “simply too vague\nas applied . . . [because the professor’s] speech did not fall within the core region\nof sexual harassment as defined by the Policy.” 22 Dr. Buchanan’s speech is\neasily distinguished from Professor Cohen’s speech. In Cohen, the use of\nprofanity and discussion of controversial viewpoints was “at least tangentially\nrelated” to teaching college-level English. 23 Here, the use of profanity and\ndiscussion of professors’ and students’ sex lives were clearly not related to the\ntraining of Pre-K–Third grade teachers. Dr. Buchanan’s speech was not,\ntherefore, a matter of public concern; we thus affirm the district court’s holding\nthat LSU’s policies did not violate the First Amendment as applied to Dr.\nBuchanan because her speech was not protected.\n B. Facial Challenge\n “Generally, we ‘proceed to an overbreadth issue’ only if ‘it is determined\nthat the statute would be valid as applied.’” 24 Here, because Dr. Buchanan’s\nas-applied challenge fails, we proceed to consideration of the facial overbreadth\nchallenge.\n Dr. Buchanan sued the wrong parties. The proper defendants to a facial\nchallenge are the parties responsible for creating or enforcing the challenged\nlaw or policy. 25 In Jordahl v. Democratic Party of Virginia, the Fourth Circuit\nheld that the plaintiffs had failed to present a facial challenge. 26 Those\n\n\n 21 92 F.3d 968 (9th Cir. 1996) (discussing discipline of a college professor for his use of\nprofanity, discussion of pornography, and assertion of other controversial viewpoints during\nclass discussion in a college-level English class).\n 22 Id. at 972 (reasoning that the vagueness of the policy did not provide notice to the\n\nprofessor that it would be applied to his “longstanding teaching style”).\n 23 Buchanan, 284 F. Supp. 3d at 834.\n 24 Serafine, 810 F.3d at 362–63 (quoting Bd. of Trs. v. Fox, 492 U.S. 469, 484–85\n\n(1989)).\n 25 See Jordahl v. Democratic Party of Va., 122 F.3d 192, 199 n.6 (4th Cir. 1997)\n\n(reasoning that for a facial challenge to a state law, the proper party was the state rather\nthan the party seeking an injunction under the law).\n 26 Id. at 199.\n\n 8\n\f Case: 18-30148 Document: 00514885022 Page: 9 Date Filed: 03/22/2019\n\n\n\n No. 18-30148\nplaintiffs had sued the Democratic Party of Virginia (“DPV”) alleging a\nviolation of their free speech rights after the DPV sought injunctions\n“forbidding the plaintiffs from distributing [voter] guides.” 27 The appeals court\nreasoned that, even though the DPV was the direct actor seeking enforcement\nof state statutes and an injunction against plaintiffs, it was not the proper\nparty to a facial challenge. 28 Similarly, when professors or students challenge\na university’s policies, the proper defendant party is the university or\nuniversity board. 29\n Here, Dr. Buchanan has sued only employees and officials with\nindividual and limited roles in administration of LSU’s polices, but with no\nultimate authority to enforce them. She failed to sue the Board of Supervisors,\nwhich is responsible for the creation and enforcement of the policies. 30 The\nBoard, therefore, is the only proper party defendant to a facial challenge to\nLSU’s policies. 31 We therefore vacate the district court’s ruling on the facial\n\n\n\n 27 Id. at 194.\n 28 Id. at 194, 199 n.6.\n 29 See e.g., DeJohn v. Temple Univ., 537 F.3d 301 (3rd Cir. 2008) (deciding graduate\n\nstudent’s facial challenge to university’s sexual harassment policy brought against\nuniversity); Piggee v. Carl Sandburg Coll., 464 F.3d 667 (7th Cir. 2006) (deciding professor’s\nchallenge to college’s sexual harassment policy brought against college); Saxe v. State Coll.\nArea Sch. Dist., 240 F.3d 200 (3rd Cir. 2001) (deciding students’ facial challenge to school\ndistrict’s anti-harassment policy brought against school district); Dambrot, 55 F.3d 1177\n(deciding coach’s challenge to university’s harassment policy brought against university).\n 30 The Louisiana Constitution grants the LSU Board of Supervisors the authority to\n\n“supervise and manage” the school. La. Const. art. VIII, § 7. The Board of Supervisors’ Bylaws\nstate that the President establishes administrative and educational policies subject to the\ndirection and control of the Board. Bylaws, Board of Supervisors, LSU, LSU.edu (Dec. 12,\n2018, 3:01 PM), https://lsu.edu/bos/docs/bylaws-adopted-2018-10-04.pdf. LSU PS-104 states\nthat a recommendation to dismiss a tenured faculty member for cause requires confirmation\nby the Board.\n 31 We distinguish this case from Esfeller v. O’Keefe, 391 F. App’x 337 (5th Cir. 2010)\n\n(unpublished). In Esfeller, a student brought a facial challenge to LSU’s Student Code of\nConduct. The student sued the LSU Board of Supervisors, and the district court dismissed\nthe Board. On appeal his court held that the Code was not facially overbroad. There, the\nplaintiff student did not appeal dismissal of the Board, and, unlike the policy in this case, the\nuniversity president had ultimate authority to enforce the Code.\n 9\n\f Case: 18-30148 Document: 00514885022 Page: 10 Date Filed: 03/22/2019\n\n\n\n No. 18-30148\nchallenge and dismiss that claim for Dr. Buchanan’s has failure to sue the\nproper party.\n C. Qualified Immunity\n We need not address the district court’s holding on qualified immunity\nbecause Dr. Buchanan’s claims fail. We nevertheless affirm that all\nDefendants are entitled to qualified immunity on her damages claims.\n The qualified immunity inquiry comprises two questions: (1) “whether\nthe defendant violated the plaintiff’s constitutional rights” and (2) whether\nthat right was clearly established. 32 “We now have discretion to skip the first\ninquiry and resolve a case solely on clearly established grounds.” 33 Before this\ncourt issued its 2018 opinion in Sims v. City of Madisonville, the law was\nunsettled whether a nondecisionmaker defendant who only recommended that\na plaintiff be fired could be held liable for a § 1983 First Amendment claim 34:\n Although [Sims] clarif[ied] that Jett controls . . . , it provides\n no recourse to [Buchanan]. That is because of the second part of\n the qualified immunity inquiry, which requires a plaintiff to show\n that any violation of rights was clearly established at the time the\n conduct occurred. When [Buchanan] was terminated in [June\n 2015] the inconsistency in our law on whether First Amendment\n liability can attach to a public official who did not make the final\n employment decision had not been resolved. . . . If judges have\n mixed up principles of . . . liability in this area and failed to\n recognize Jett as the controlling decision, [school] officials should\n not be expected to have a more nuanced understanding of section\n 1983 law. 35\n\nAlthough the district court did not discuss this unsettled matter of law in its\nreasoning on qualified immunity, its holding that Defendants’ acts were\n\n\n\n\n 32 Sims v. City of Madisonville, 894 F.3d 632, 638 (5th Cir. 2018).\n 33 Id. (citing Pearson v. Callahan, 555 U.S. 223, 240 (2009)).\n 34 Sims, 894 F.3d at 638, 640; Culbertson v. Lykos, 790 F.3d 608, 627 (5th Cir. 2015).\n 35 Sims, 894 F.3d at 641.\n\n 10\n\f Case: 18-30148 Document: 00514885022 Page: 11 Date Filed: 03/22/2019\n\n\n\n No. 18-30148\nobjectively reasonable considering clearly established law at the time was not\nerror.\n III. CONCLUSION\n The district court correctly concluded that Dr. Buchanan’s speech was\nnot protected by the First Amendment. The district court’s holding on the as-\napplied challenge is AFFIRMED. On the facial challenge, Dr. Buchanan has\nnot sued the proper party. The district court’s holding on the facial challenge\nis VACATED and Dr. Buchanan’s claim is DISMISSED on this alternate\nground.\n\n\n\n\n 11\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Teresa BUCHANAN, Plaintiff - Appellant v. F. King ALEXANDER; Damon Andrew; A. G. Monaco; Gaston Reinoso, Defendants - Appellees\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-22\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 18-30148 Document: 00514885022 Page: 1 Date Filed: 03/22/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT United States Court of Appeals\\n Fifth Circuit\\n\\n FILED\\n No. 18-30148 March 22, 2019\\n Lyle W. Cayce\\n Clerk\\nTERESA BUCHANAN,\\n\\n Plaintiff - Appellant\\n\\nv.\\n\\nF. KING ALEXANDER; DAMON ANDREW; A. G. MONACO; GASTON\\nREINOSO,\\n\\n Defendants - Appellees\\n\\n\\n\\n\\n Appeal from the United States District Court\\n for the Middle District of Louisiana\\n\\n\\nBefore WIENER, SOUTHWICK, and COSTA, Circuit Judges.\\nWIENER, Circuit Judge\\n Plaintiff-Appellant Dr. Teresa Buchanan (“Dr. Buchanan”) was fired\\nfrom her tenured professorship by the Board of Supervisors (“the Board”) of\\nLouisiana State University and Agricultural and Mechanical College (“LSU”)\\nin June 2015. In January 2016, Dr. Buchanan filed the instant lawsuit against\\n(1) F. King Alexander (“President Alexander”), President and Chancellor of\\nLSU; (2) Damon Andrew (“Dean Andrew”), Dean of the College of Human\\nSciences and Education at LSU; (3) A.G. Monaco (“Vice Chancellor Monaco”),\\nVice Chancellor of the Office Human Resource Management at LSU; and (4)\\nGaston Reinoso (“Director Reinoso”), Director of the Office of Human Resource\\n\\f Case: 18-30148 Document: 00514885022 Page: 2 Date Filed: 03/22/2019\\n\\n\\n\\n No. 18-30148\\nManagement and Executive Director of Equal Employment Opportunities at\\nLSU (collectively “Defendants”). Dr. Buchanan alleged (a) that Defendants\\nviolated her First and Fourteenth Amendment right to free speech and\\nacademic freedom (the “as-applied challenge”), (b) that Defendants violated her\\nFourteenth Amendment procedural and substantive due process rights, and (c)\\na facial challenge to LSU’s sexual harassment policies (the “facial challenge”).\\nDr. Buchanan sought reinstatement and declaratory and injunctive relief. On\\ncross-motions for summary judgment, the district court granted Defendants’\\nmotion and dismissed Dr. Buchanan’s claims. Dr. Buchanan now appeals that\\ndecision.\\n I. FACTS AND PROCEEDINGS\\n A. Factual Background\\n Before she was fired, Dr. Buchanan was an associate professor at LSU\\nwith tenure. She taught in the Early Childhood Program for teacher education.\\nIn November 2013, LSU received a complaint from the superintendent of a\\nlocal public school district regarding Dr. Buchanan’s “professionalism and her\\nbehavior” when she visited schools in his district. LSU also received complaints\\nfrom some of Dr. Buchanan’s students regarding her classroom behavior. One\\nstudent complained about Dr. Buchanan’s comments regarding the student’s\\nsexual relationship with her fiancé. 1 Another student complained that Dr.\\nBuchanan recorded her crying during an assessment team meeting. 2 LSU had\\nreceived a letter in 2012 from a group of students complaining that Dr.\\n\\n\\n\\n 1 “According to Student 1: ‘Dr. Buchanan had offered them condoms, had told them it\\nwas unacceptable to become pregnant. And that if you chose to become a mother, that your\\ngrades would suffer for that. She told them . . . enjoy the sex while the sex is – good. If you’re\\ndating – if you’re dating, make sure the sex is good, something along those lines.’” Dr.\\nBuchanan further told the student that her fiancé was “supportive now while the sex is good,\\nbut just wait until you’re married five years.”\\n 2 This student claimed that Dr. Buchanan was aggressive during the meeting and\\n\\nyelled at her. The student stated that she felt attacked.\\n 2\\n\\f Case: 18-30148 Document: 00514885022 Page: 3 Date Filed: 03/22/2019\\n\\n\\n\\n No. 18-30148\\nBuchanan made offensive classroom comments, such as (1) “a woman is\\nthought to be a dike if she wears brown pants”; (2) “it was a choice to be in the\\nprogram and it was not the fault or problem of the professors if any of us chose\\nto be mommies or wives and not to expect to get an A in the class”; and (3) use\\nof “extreme profanity on a regular basis.”\\n These complaints were reported to Associate Dean Jennifer Curry\\n(“Dean Curry”) who discussed them with Dr. Earl Cheek (“Dr. Cheek”),\\nDirector of the College of Education. After learning of these incidents, Dean\\nAndrew directed Dean Curry to gather the complaints; he then consulted with\\nHuman Resources. 3 In December 2013, Dean Andrew told Dr. Buchanan that\\nshe would be removed from the classroom during a human resources\\ninvestigation. Director Reinoso investigated to determine whether Dr.\\nBuchanan had violated LSU policies, interviewed witnesses, and wrote a\\nreport. Dean Andrew reviewed Director Reinoso’s report and recommended\\nappointment of a Faculty Senate Grievance Committee (“Faculty Committee”)\\nunder LSU’s Policy Statement-104 for Dismissal for Cause of Faculty. In\\nJanuary 2014, Dr. Buchanan met with Director Reinoso and other human\\nresources managers to discuss the complaints.\\n In May 2014, Director Reinoso sent a memorandum to Dr. Buchanan\\nwhich stated that he found her “actions and behavior . . . inappropriate,\\nunwelcome, and a direct violation of the University’s Policy Statements on\\nSexual Harassment, PS-73 and PS-95” and her “reported communication style\\nwith students, faculty, and outside administrators . . . to be inappropriate.” In\\nJune 2014, Dean Andrew met with Dr. Buchanan to discuss Director Reinoso’s\\nreport, and they subsequently communicated about the report in writing. In\\n\\n\\n\\n 3 While gathering the complaints, Dean Curry was informed that Dr. Buchanan “was\\nno longer authorized to be on any Iberville Parish school campus.”\\n 3\\n\\f Case: 18-30148 Document: 00514885022 Page: 4 Date Filed: 03/22/2019\\n\\n\\n\\n No. 18-30148\\nJuly 2014, Dean Andrew recommended to Provost Stuart Bell that Dr.\\nBuchanan be dismissed for cause. Provost Bell then requested and impaneled\\na Faculty Committee.\\n In March 2015, the Faculty Committee held a lengthy hearing regarding\\nDr. Buchanan’s classroom behavior. The Faculty Committee concluded that\\nDr. Buchanan had violated LSU’s sexual harassment policies, PS-73 and PS-\\n95, “through her use of profanity, poorly worded jokes, and sometimes sexually\\nexplicit ‘jokes.’” The Committee also found that Dr. Buchanan had created a\\n“hostile learning environment.” The Committee recommended censure.\\n In April 2015, despite the Faculty Committee’s censure recommendation,\\nPresident Alexander informed Dr. Buchanan that he was going to recommend\\nto the Board that she be dismissed for cause and violations of LSU’s policies\\nand the Americans with Disabilities Act (“ADA”). 4 Dr. Buchanan appealed this\\nrecommendation and addressed the Board. The Board fired Dr. Buchanan in\\nJune 2015.\\n B. Procedural Background\\n Dr. Buchanan filed this lawsuit after she was fired. The parties filed\\ncross-motions for summary judgment. The district court denied Dr.\\nBuchanan’s motion and granted Defendants’ motion, holding that: (1) for\\npurposes of these Defendants’ qualified immunity, liability for retaliation in\\nviolation of the First Amendment based on a defendant’s merely causing an\\nadverse employment action was not clearly established, (2) there was no\\nevidence of a violation of Dr. Buchanan’s First Amendment right to academic\\nfreedom, (3) LSU’s sexual harassment policies were not facially overbroad, (4)\\nLSU’s sexual harassment policies as applied to Dr. Buchanan did not violate\\n\\n\\n 4 The Faculty Committee also investigated whether Dr. Buchanan violated the ADA\\nby revealing a student’s medical information to other students. The Committee found\\ninsufficient evidence to establish an ADA violation.\\n 4\\n\\f Case: 18-30148 Document: 00514885022 Page: 5 Date Filed: 03/22/2019\\n\\n\\n\\n No. 18-30148\\nher First Amendment rights, and (5) Defendants did not violate Dr.\\nBuchanan’s right to procedural due process. 5 Dr. Buchanan now appeals the\\ndistrict court’s denial of her facial and as-applied challenges to LSU’s sexual\\nharassment policies and the district court’s holdings that Defendants are not\\npersonally liable.\\n II. LAW AND ANALYSIS\\n A. As-Applied Challenge\\n When a litigant brings both as-applied and facial challenges, we\\ngenerally decide the as-applied challenge first because it is the narrower\\nconsideration. 6 The Fifth Circuit reviews summary judgments de novo 7 and\\ncases raising First Amendment issues by examining the whole record. 8\\n The Supreme Court has established that academic freedom is “a special\\nconcern of the First Amendment, which does not tolerate laws that cast a pall\\nof orthodoxy over the classroom.” 9 Accordingly, “classroom discussion is\\nprotected activity.” 10 However, even this protection has limits: Students,\\nteachers, and professors are not permitted to say anything and everything\\nsimply because the words are uttered in the classroom context. 11\\n\\n\\n 5 Buchanan v. Alexander, 284 F. Supp. 3d 792 (M.D. La. 2018).\\n 6 Serafine v. Branaman, 810 F.3d 354, 362 (5th Cir. 2016).\\n 7 MacLachlan v. ExxonMobil Corp., 350 F.3d 472, 478 (5th Cir. 2003), abrogated on\\n\\nother grounds by Crowell v. Shell Oil Co., 541 F.3d 295 (5th Cir. 2008).\\n 8 Denton v. Morgan, 136 F.3d 1038, 1042–43 (5th Cir. 1998).\\n 9 Keyishian v. Bd. of Regents, 385 U.S. 589, 603 (1967).\\n 10 Kingsville Indep. Sch. Dist. v. Cooper, 611 F.2d 1109, 1113 (5th Cir. 1980).\\n 11 See, e.g., Bethel Sch. Dist. No. 403 v. Fraser, 478 U.S. 675 (1986) (holding that\\n\\nstudent could not claim First Amendment protection for offensively lewd and indecent\\nspeech); Martin v. Parrish, 805 F.2d 583 (5th Cir. 1986) (holding that professor had no First\\nAmendment right to use profane language in the classroom). In his book, Democracy,\\nExpertise, and Academic Freedom, Robert C. Post, Yale Law Professor and former Dean of\\nYale Law School and general counsel for the AAUP, discusses the limits of First Amendment\\nacademic freedom. He notes that the value of academic freedom depends on universities\\nholding professors to professional standards in contrast with the traditional First\\nAmendment value of the free marketplace of ideas. Therefore, “[t]he right question for courts\\nto ask about academic freedom is how to fashion doctrine that best protects the ‘freedom of\\n 5\\n\\f Case: 18-30148 Document: 00514885022 Page: 6 Date Filed: 03/22/2019\\n\\n\\n\\n No. 18-30148\\n Public university professors are public employees. To establish a § 1983\\nclaim for violation of the First Amendment right to free speech, they must show\\nthat (1) they were disciplined or fired for speech that is a matter of public\\nconcern, and (2) their interest in the speech outweighed the university’s\\ninterest in regulating the speech. 12 The first question, asking whether the\\nprofessor’s speech is protected as a matter of public concern, is a question of\\nlaw. 13\\n The inquiry into whether Plaintiff’s interests in speaking\\n outweigh the College’s interests in regulating Plaintiff’s speech is\\n a factual determination conducted under the well known\\n Pickering[-Connick] balancing test. . . . If Plaintiff’s interests in the\\n prohibited speech outweigh the College’s interests, then Plaintiff’s\\n First Amendment rights have been violated. . . . If the First\\n Amendment violation was a substantial or motivating factor in\\n Defendants’ disciplinary action against Plaintiff, Defendants may\\n present evidence that they would have disciplined Plaintiff in the\\n absence of his protected conduct. . . . However, if Plaintiff’s speech\\n does not involve a matter of public concern, it is unnecessary for\\n the court to scrutinize the reason for the discipline. 14\\n\\n If Dr. Buchanan did not speak as a citizen on a matter of public concern,\\nthen she has no First Amendment claim for LSU’s response to her speech. 15\\n“[W]hether an employee’s speech addresses a matter of public concern must be\\ndetermined by the content, form, and context of a given statement, as revealed\\n\\n\\n\\nthought, of inquiry . . . of the academic profession.’” Robert C. Post, Democracy, Expertise,\\nand Academic Freedom: A First Amendment Jurisprudence for the Modern State 67, 80 (2012)\\n(quoting the 1915 Declaration of Principles on Academic Freedom and Academic Tenure\\nreprinted in American Association of University Professors, Policy Documents and Reports\\n291-301 (9th ed. 2001)).\\n 12 See Connick v. Myers, 461 U.S. 138, 147–50 (1983); Pickering v. Bd. of Educ., 391\\n\\nU.S. 563, 568 (1968); Martin, 805 F.2d at 584.\\n 13 Connick, 461 U.S. at 148 n.7; Tompkins v. Vickers, 26 F.3d 603, 606 (5th Cir. 1994).\\n 14 Bonnell v. Lorenzo, 241 F.3d 800, 810 (6th Cir. 2001) (citing Pickering, 391 U.S. at\\n\\n568; Dambrot v. Cent. Mich. Univ., 55 F.3d 1177, 1186 (6th Cir. 1995); Mt. Healthy City Sch.\\nDist. Bd. of Educ. v. Doyle, 429 U.S. 274, 285 (1977); Connick, 461 U.S. at 146).\\n 15 See Connick, 461 U.S. at 147–48.\\n\\n 6\\n\\f Case: 18-30148 Document: 00514885022 Page: 7 Date Filed: 03/22/2019\\n\\n\\n\\n No. 18-30148\\nby the whole record.” 16 “Speech involves a matter of public concern when it\\ninvolves an issue of social, political, or other interest to a community.” 17 When\\na public employee speaks in his capacity as an employee and on personal\\nmatters, rather than in his capacity as a citizen on a matter of public interest,\\nhis speech falls outside the protection of the First Amendment. 18 A mere\\nelement of personal concern, however, does not prevent finding that an\\nemployee’s speech as a whole includes a matter of public concern. 19\\n We agree with the district court here that Dr. Buchanan’s use of\\nprofanity and discussion of her sex life and the sex lives of her students was\\nnot related to the subject matter or purpose of training Pre-K–Third grade\\nteachers. This court has held that, in the college classroom context, speech that\\ndoes not serve an academic purpose is not of public concern. 20 Dr. Buchanan\\nwould rely on the Ninth Circuit’s holding in Cohen v. San Bernardino Valley\\n\\n\\n\\n\\n 16 Id. at 147–48.\\n 17 Adams v. Trustees of the Univ. of N.C.–Wilmington, 640 F.3d 550, 564 (4th Cir. 2011)\\n(quoting Kirby v. City of Elizabeth City, 388 F.3d 440, 446 (4th Cir. 2004)) (citing Connick,\\n461 U.S. at 146).\\n 18 Kennedy v. Tangipahoa Parish Library Bd. of Control, 224 F.3d 359, 366 (5th Cir.\\n\\n2000), abrogated on other grounds by Gibson v. Kilpatrick, 838 F.3d 476 (5th Cir. 2016) (citing\\nConnick, 461 U.S. at 147).\\n 19 Id. at 365.\\n 20 Martin, 805 F.2d at 585 (holding that a professor’s use of profanity to castigate his\\n\\nstudents was not a matter of public concern because it served no academic purpose); see also\\nBonnell, 241 F.3d at 820 (holding that a professor “may have a constitutional right to use\\nwords such as ‘pussy,’ ‘cunt,’ and ‘fuck,’ but he does not have a constitutional right to use\\nthem in a classroom setting where they are not germane to the subject matter”); Dambrot, 55\\nF.3d at 1190 (holding that “[a]n instructor’s choice of teaching methods does not rise to the\\nlevel of protected expression”); cf. Hardy v. Jefferson Cmty. Coll., 260 F.3d 671, 682 (6th Cir.\\n2001) (holding that a professor’s right to use vulgarity and racial slurs during analysis of the\\nhistorical use of oppressive and marginalizing language was protected speech); Kerr v. Hurd,\\n694 F. Supp. 2d 817, 842–43 (S.D. Ohio 2010) (holding that discussion and advocacy of a\\nmedical technique during classroom instruction was a matter of public concern because it\\nwas relevant to a national debate on best practices for delivering babies).\\n 7\\n\\f Case: 18-30148 Document: 00514885022 Page: 8 Date Filed: 03/22/2019\\n\\n\\n\\n No. 18-30148\\nCollege 21 that a university’s sexual harassment policy was “simply too vague\\nas applied . . . [because the professor’s] speech did not fall within the core region\\nof sexual harassment as defined by the Policy.” 22 Dr. Buchanan’s speech is\\neasily distinguished from Professor Cohen’s speech. In Cohen, the use of\\nprofanity and discussion of controversial viewpoints was “at least tangentially\\nrelated” to teaching college-level English. 23 Here, the use of profanity and\\ndiscussion of professors’ and students’ sex lives were clearly not related to the\\ntraining of Pre-K–Third grade teachers. Dr. Buchanan’s speech was not,\\ntherefore, a matter of public concern; we thus affirm the district court’s holding\\nthat LSU’s policies did not violate the First Amendment as applied to Dr.\\nBuchanan because her speech was not protected.\\n B. Facial Challenge\\n “Generally, we ‘proceed to an overbreadth issue’ only if ‘it is determined\\nthat the statute would be valid as applied.’” 24 Here, because Dr. Buchanan’s\\nas-applied challenge fails, we proceed to consideration of the facial overbreadth\\nchallenge.\\n Dr. Buchanan sued the wrong parties. The proper defendants to a facial\\nchallenge are the parties responsible for creating or enforcing the challenged\\nlaw or policy. 25 In Jordahl v. Democratic Party of Virginia, the Fourth Circuit\\nheld that the plaintiffs had failed to present a facial challenge. 26 Those\\n\\n\\n 21 92 F.3d 968 (9th Cir. 1996) (discussing discipline of a college professor for his use of\\nprofanity, discussion of pornography, and assertion of other controversial viewpoints during\\nclass discussion in a college-level English class).\\n 22 Id. at 972 (reasoning that the vagueness of the policy did not provide notice to the\\n\\nprofessor that it would be applied to his “longstanding teaching style”).\\n 23 Buchanan, 284 F. Supp. 3d at 834.\\n 24 Serafine, 810 F.3d at 362–63 (quoting Bd. of Trs. v. Fox, 492 U.S. 469, 484–85\\n\\n(1989)).\\n 25 See Jordahl v. Democratic Party of Va., 122 F.3d 192, 199 n.6 (4th Cir. 1997)\\n\\n(reasoning that for a facial challenge to a state law, the proper party was the state rather\\nthan the party seeking an injunction under the law).\\n 26 Id. at 199.\\n\\n 8\\n\\f Case: 18-30148 Document: 00514885022 Page: 9 Date Filed: 03/22/2019\\n\\n\\n\\n No. 18-30148\\nplaintiffs had sued the Democratic Party of Virginia (“DPV”) alleging a\\nviolation of their free speech rights after the DPV sought injunctions\\n“forbidding the plaintiffs from distributing [voter] guides.” 27 The appeals court\\nreasoned that, even though the DPV was the direct actor seeking enforcement\\nof state statutes and an injunction against plaintiffs, it was not the proper\\nparty to a facial challenge. 28 Similarly, when professors or students challenge\\na university’s policies, the proper defendant party is the university or\\nuniversity board. 29\\n Here, Dr. Buchanan has sued only employees and officials with\\nindividual and limited roles in administration of LSU’s polices, but with no\\nultimate authority to enforce them. She failed to sue the Board of Supervisors,\\nwhich is responsible for the creation and enforcement of the policies. 30 The\\nBoard, therefore, is the only proper party defendant to a facial challenge to\\nLSU’s policies. 31 We therefore vacate the district court’s ruling on the facial\\n\\n\\n\\n 27 Id. at 194.\\n 28 Id. at 194, 199 n.6.\\n 29 See e.g., DeJohn v. Temple Univ., 537 F.3d 301 (3rd Cir. 2008) (deciding graduate\\n\\nstudent’s facial challenge to university’s sexual harassment policy brought against\\nuniversity); Piggee v. Carl Sandburg Coll., 464 F.3d 667 (7th Cir. 2006) (deciding professor’s\\nchallenge to college’s sexual harassment policy brought against college); Saxe v. State Coll.\\nArea Sch. Dist., 240 F.3d 200 (3rd Cir. 2001) (deciding students’ facial challenge to school\\ndistrict’s anti-harassment policy brought against school district); Dambrot, 55 F.3d 1177\\n(deciding coach’s challenge to university’s harassment policy brought against university).\\n 30 The Louisiana Constitution grants the LSU Board of Supervisors the authority to\\n\\n“supervise and manage” the school. La. Const. art. VIII, § 7. The Board of Supervisors’ Bylaws\\nstate that the President establishes administrative and educational policies subject to the\\ndirection and control of the Board. Bylaws, Board of Supervisors, LSU, LSU.edu (Dec. 12,\\n2018, 3:01 PM), https://lsu.edu/bos/docs/bylaws-adopted-2018-10-04.pdf. LSU PS-104 states\\nthat a recommendation to dismiss a tenured faculty member for cause requires confirmation\\nby the Board.\\n 31 We distinguish this case from Esfeller v. O’Keefe, 391 F. App’x 337 (5th Cir. 2010)\\n\\n(unpublished). In Esfeller, a student brought a facial challenge to LSU’s Student Code of\\nConduct. The student sued the LSU Board of Supervisors, and the district court dismissed\\nthe Board. On appeal his court held that the Code was not facially overbroad. There, the\\nplaintiff student did not appeal dismissal of the Board, and, unlike the policy in this case, the\\nuniversity president had ultimate authority to enforce the Code.\\n 9\\n\\f Case: 18-30148 Document: 00514885022 Page: 10 Date Filed: 03/22/2019\\n\\n\\n\\n No. 18-30148\\nchallenge and dismiss that claim for Dr. Buchanan’s has failure to sue the\\nproper party.\\n C. Qualified Immunity\\n We need not address the district court’s holding on qualified immunity\\nbecause Dr. Buchanan’s claims fail. We nevertheless affirm that all\\nDefendants are entitled to qualified immunity on her damages claims.\\n The qualified immunity inquiry comprises two questions: (1) “whether\\nthe defendant violated the plaintiff’s constitutional rights” and (2) whether\\nthat right was clearly established. 32 “We now have discretion to skip the first\\ninquiry and resolve a case solely on clearly established grounds.” 33 Before this\\ncourt issued its 2018 opinion in Sims v. City of Madisonville, the law was\\nunsettled whether a nondecisionmaker defendant who only recommended that\\na plaintiff be fired could be held liable for a § 1983 First Amendment claim 34:\\n Although [Sims] clarif[ied] that Jett controls . . . , it provides\\n no recourse to [Buchanan]. That is because of the second part of\\n the qualified immunity inquiry, which requires a plaintiff to show\\n that any violation of rights was clearly established at the time the\\n conduct occurred. When [Buchanan] was terminated in [June\\n 2015] the inconsistency in our law on whether First Amendment\\n liability can attach to a public official who did not make the final\\n employment decision had not been resolved. . . . If judges have\\n mixed up principles of . . . liability in this area and failed to\\n recognize Jett as the controlling decision, [school] officials should\\n not be expected to have a more nuanced understanding of section\\n 1983 law. 35\\n\\nAlthough the district court did not discuss this unsettled matter of law in its\\nreasoning on qualified immunity, its holding that Defendants’ acts were\\n\\n\\n\\n\\n 32 Sims v. City of Madisonville, 894 F.3d 632, 638 (5th Cir. 2018).\\n 33 Id. (citing Pearson v. Callahan, 555 U.S. 223, 240 (2009)).\\n 34 Sims, 894 F.3d at 638, 640; Culbertson v. Lykos, 790 F.3d 608, 627 (5th Cir. 2015).\\n 35 Sims, 894 F.3d at 641.\\n\\n 10\\n\\f Case: 18-30148 Document: 00514885022 Page: 11 Date Filed: 03/22/2019\\n\\n\\n\\n No. 18-30148\\nobjectively reasonable considering clearly established law at the time was not\\nerror.\\n III. CONCLUSION\\n The district court correctly concluded that Dr. Buchanan’s speech was\\nnot protected by the First Amendment. The district court’s holding on the as-\\napplied challenge is AFFIRMED. On the facial challenge, Dr. Buchanan has\\nnot sued the proper party. The district court’s holding on the facial challenge\\nis VACATED and Dr. Buchanan’s claim is DISMISSED on this alternate\\nground.\\n\\n\\n\\n\\n 11\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1097,"cells":{"id":{"kind":"number","value":4603272,"string":"4,603,272"},"name":{"kind":"string","value":"Joseph THOMAS; Vernon Ayers; Melvin Lawson, Plaintiffs - Appellees v. Phil BRYANT, Governor of the State of Mississippi; Delbert Hosemann, Secretary of State of the State of Mississippi, Both in the Official Capacities of Their Own Offices and in Their Official Capacities as Members of the State Board of Election Commissioners, Defendants - Appellants"},"name_abbreviation":{"kind":"string","value":"Joseph Thomas v. Phil Bryant"},"decision_date":{"kind":"string","value":"2019-03-22"},"docket_number":{"kind":"string","value":"19-60133"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Dennis, Clement, Costa\", \"parties\": \"\", \"opinions\": [{\"author\": \"GREGG COSTA, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 19-60133 Document: 00514885572 Page: 1 Date Filed: 03/22/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT United States Court of Appeals\\n Fifth Circuit\\n\\n ___________________ FILED\\n March 22, 2019\\n No. 19-60133 Lyle W. Cayce\\n ___________________ Clerk\\n\\nJOSEPH THOMAS; VERNON AYERS; MELVIN LAWSON,\\n\\n Plaintiffs - Appellees\\n\\nv.\\n\\nPHIL BRYANT, Governor of the State of Mississippi,; DELBERT\\nHOSEMANN, Secretary of State of the State of Mississippi, both in the\\nofficial capacities of their own offices and in their official capacities as\\nmembers of the State Board of Election Commissioners,\\n\\n Defendants - Appellants\\n\\n _______________________\\n\\n Appeal from the United States District Court\\n for the Southern District of Mississippi\\n _______________________\\n\\nBefore DENNIS, CLEMENT, and COSTA, Circuit Judges.\\nGREGG COSTA, Circuit Judge:\\n A district court found that the boundaries for Mississippi State Senate\\nDistrict 22 dilute African-American voting strength and prevent those citizens\\nfrom having the equal opportunity “to participate in the political process and\\nto elect representatives of their choice” that the Voting Rights Act guarantees.\\n52 U.S.C. § 10301(b). To remedy the violation, the district court switched 28\\nprecincts between District 22 and a bordering district. The Governor and\\nSecretary of State seek a stay of the final judgment.\\n\\n Case: 19-60133 Document: 00514885572 Page: 2 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\n I.\\n Most of District 22 lies in the heart of the Mississippi Delta. Those\\nunfamiliar with the state’s geography might think that the Mississippi Delta\\nis in the southern portion of the state that is closer to the mouth of the\\nMississippi River. But the “Delta” refers not to the outlet of that mighty river\\ninto the Gulf of Mexico, but to the alluvial plain between the Mississippi River\\nand the Yazoo River. John M. Barry, RISING TIDE: THE GREAT MISSISSIPPI\\nFLOOD OF 1927 AND HOW IT CHANGED AMERICA 96 (1997). It is located in the\\nnorthwest section of Mississippi and looks like an “elongated diamond.” Id.\\nThe district court recited this colorful description of its boundaries: “The\\nMississippi Delta begins in the lobby of the Peabody Hotel [in Memphis] and\\nends on Catfish Row in Vicksburg.” David L. Cohn, GOD SHAKES CREATION\\n(1935).\\n The sediment that the Mississippi River deposited in this region over the\\nmillennia made Delta soil some of the richest in the world. Barry, supra, at\\n97. And that soil made the Delta one of the leading cotton-producing areas in\\nthe world. One historian compared the influence the Delta once held over\\nglobal cotton prices to the modern influence of Saudi Arabia over oil prices.\\nSven Beckert, EMPIRE OF COTTON: A GLOBAL HISTORY 113 (2014).\\n But before agriculture could prosper in the Delta its forests of hardwood\\ntrees had to be cleared. Slaves were forced to begin that process, and\\nemancipated slaves finished it in the latter part of the nineteenth century.\\nSince that time, African-Americans have been a majority in the Delta. In the\\nearly twentieth century, they made up almost 90% of the region’s population.\\nBarry, supra, at 125 (noting that in 1908 the Delta had “a black population of\\nat least 171,209” and “a white population of 24,137”). The Great Migration to\\n\\n\\n\\n 2\\n\\n Case: 19-60133 Document: 00514885572 Page: 3 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nthe north reduced the African-American percentage, but they remain a\\nsizeable majority in the region.\\n Of course, for most of their time laboring in the Delta, African-Americans\\ncould not vote. The Voting Rights Act changed that. It has resulted in\\nnumerous African-Americans being elected to office in the Delta. Indeed, the\\nState of Mississippi has more African-American elected officials than any other\\nstate. U.S. Census Bureau, STATISTICAL ABSTRACT OF THE UNITED STATES:\\n2011, 258 (130th ed.).\\n But in places like the state legislature, African-Americans have still not\\nachieved political power in Mississippi that comes close to their share of the\\npopulation. This case involves a claim that one state senate district\\ncontributed to that underrepresentation by diluting the voting strength of\\nAfrican-Americans that Delta demographics and geography should otherwise\\nsupport and contributed to that underrepresentation.\\n District 22 includes all or part of five Delta counties: Bolivar,\\nHumphreys, Sharkey, Washington, and Yazoo. It also includes parts of one\\nnon-Delta county: Madison. The addition of the white-majority Madison\\nCounty precincts in the last redistricting reduced the African-American\\npercentage in District 22. Overall the district still has an African-American\\nmajority, but just barely at 50.7%. 1 Without the non-Delta precincts from\\nMadison County, that percentage would be much higher.\\n\\n\\n\\n 1 Plaintiff Thomas told the Department of Justice that the 50.7% figure includes the\\npopulation of the Yazoo City federal prison, the majority of whose inmates he says are\\nAfrican-American. He contended that without including that prison, African-Americans\\nwould not be a majority in the district. It is questionable whether disenfranchised people\\nshould be included in the BVAP (black voting age population) calculation for purposes of the\\nVoting Rights Act. The focus is usually on those eligible to vote, thus the typical requirement\\nin our circuit that the percentage focus on those of voting age who are citizens. See Reyes v.\\nCity of Farmers Branch, Tex., 586 F.3d 1019, 1023 (5th Cir. 2009) (noting that only citizens\\nare included in population calculations).\\n 3\\n\\n Case: 19-60133 Document: 00514885572 Page: 4 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\n The candidate preferred by the black majority did not prevail in the 2015\\nelection. The losing candidate those voters did prefer (Joseph Thomas), along\\nwith two voters (Vernon Ayers and Melvin Lawson), brought this lawsuit in\\n2018 alleging that the district violated of Section 2 of the Voting Rights Act.\\n Last month, the district court held a bench trial and agreed. It concluded\\nthat the threshold Gingles factors for establishing vote dilution existed. The\\nAfrican-American population is “sufficiently large and geographically compact”\\nto constitute a majority with electoral power in the district; that racial group\\nis politically cohesive; but the white population voted as a bloc to prevent\\nAfrican-Americans from electing their chosen candidate. LULAC v. Perry, 548\\nU.S. 399, 425 (2006). The bloc voting by both racial groups was stark: in 10\\nelections within district 22, the candidate favored by African-Americans\\nreceived between 82% and 93% of their vote but only between 8% and 19% of\\nthe white vote.\\n The district court then followed the statutory directive to consider the\\n“totality of circumstances” in determining whether African-Americans “have\\nless opportunity than other members of the electorate to participate in the\\npolitical process and to elect representatives of their choice.” 52 U.S.C.\\n§ 10301(b); LULAC, 548 U.S. at 425–26. It credited Plaintiffs’ expert’s analysis\\nof voter participation as more rigorous and concluded that African-American\\nturnout was depressed in off-year elections—that is, odd-year elections without\\nfederal races—which is when Mississippi elects its legislature. The district\\ncourt also highlighted the persistent representation gap in the Mississippi\\nSenate, as well as substantial socioeconomic differences between black voters\\nand white voters in the district.\\n After finding a Voting Rights Act violation, the court initially declined to\\norder a remedy so “the Mississippi Legislature [could] consider[] whether to\\n\\n\\n 4\\n\\n Case: 19-60133 Document: 00514885572 Page: 5 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nredraw the District and extend the candidate qualification deadline.”\\nAlthough the primary and general elections were months away, the deadline\\nfor candidate filing was March 1.\\n A flurry of procedural moves followed at warp speed. Three days after\\nthe court made its trial findings, the Governor and Secretary of State\\n(Defendants) 2 filed a motion a motion to stay with the district court and also\\nfiled an appeal, arguing that the ruling was an appealable interlocutory\\ninjunction. Less than a week later, they asked this court to stay the district\\ncourt’s ruling. That same day, Plaintiffs asked the court to extend the\\nqualification deadline in District 22 and bordering District 23 (the other\\ndistrict affected by the proposed remedy) by two weeks. Later that day, the\\ndistrict court ordered Defendants to update it on any progress, if any, in\\nlegislative redrawing of District 22.\\n The next day, Defendants filed a brief opposing Plaintiffs’ motion to\\nextend the qualification deadline, in which they stated that they had contacted\\nthe leadership of the legislative chambers. The Senate leaders had said that\\n“should the stay motions pending before [the district court] and the Fifth\\nCircuit be denied, the Senate desire[d] the opportunity to enact a new\\nredistricting plan redrawing Senate District 22.” Late that same day, the\\ndistrict court ruled that, because the legislature was unwilling to act, the first\\nmap drawn by one of Plaintiffs’ experts would be adopted as the boundaries of\\nDistricts 22 and 23. The court also moved the qualification deadline to March\\n\\n\\n\\n\\n 2 The third defendant, Attorney General Jim Hood, did not join these motions or this\\nappeal.\\n 5\\n\\n Case: 19-60133 Document: 00514885572 Page: 6 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\n15 for the two affected senate districts. The court also declined to enter a stay\\nand entered final judgment.\\n The final judgment caused our court to dismiss the appeal of the\\npreliminary ruling. Thomas v. Bryant, 2019 WL 994034 (5th Cir. Feb. 28,\\n2019). But by that time the Defendants had already appealed from the final\\njudgment, and not long after that they sought a stay pending the new appeal,\\nwhich is the motion before this panel. 3\\n This is the effect of the final judgment: It switches some precincts\\nbetween Districts 22 and 23. It extends the candidate filing deadline to March\\n15. In terms of other upcoming deadlines, the primary election is August 6,\\nwith a June 22 deadline to send ballots to troops overseas. The general election\\nis November 5.\\n II.\\n The stay Defendants seek is an extraordinary remedy. Nken v. Holder,\\n556 U.S. 418, 437 (2009) (Kennedy, J., concurring). It is also an equitable one\\ncommitted to this court’s discretion. Id. at 433; Ruiz v. Estelle, 666 F.2d 854,\\n856 & n.4 (5th Cir. 1982). Four factors guide the exercise of our discretion:\\n1) whether the applicant has made a strong showing of likelihood to succeed\\non the merits; 2) whether the movant will be irreparably harmed absent a stay;\\n3) whether issuance of a stay will substantially injure other interested parties;\\nand 4) where the public interest lies. Nken, 556 U.S. at 434. The first two\\nfactors are usually the most important. Id.; ODonnell v. Goodhart, 900 F.3d\\n220, 223 (5th Cir. 2018).\\n In this case, the likelihood of success ends up being dispositive. That is\\nbecause Defendants can establish irreparable harm. A court order preventing\\n\\n\\n 3 Before seeking the stay pending appeal for the second time in our court after entry\\nof final judgment, Defendants also sought a stay in the district court for the second time. The\\ndistrict court denied that motion.\\n 6\\n\\n Case: 19-60133 Document: 00514885572 Page: 7 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nenforcement of a state law, including the drawing of legislative lines,\\nconstitutes that harm. Abbott v. Perez, 138 S. Ct. 2305, 2324 n.17 (2018). And\\nthat injury may be irreparable in light of the meaningful possibility (but not\\ncertainty) that a full appeal cannot be decided in time to provide Defendants\\nrelief before this year’s senate elections. But Plaintiffs face the same risk that\\nthe appellate ruling will prove futile should this court grant a stay. And the\\ninjury they seek to prevent—holding an election under an unlawful plan with\\ndiscriminatory effects—is also, it should go without saying, a serious one.\\nVeasey v. Abbott, 830 F.3d 216, 270 (5th Cir. 2016) (en banc) (“It would be\\nuntenable to permit a law with a discriminatory effect to remain in operation\\nfor that election.”); cf. Reynolds v. Sims, 377 U.S. 533, 585 (1964) (“[I]t would\\nbe the unusual case in which a court would be justified in not taking\\nappropriate action to insure that no further elections are conducted under the\\ninvalid plan.”). So Defendants’ entitlement to a stay turns on whether they\\nhave a strong likelihood of success.\\n III.\\n We will first address Defendants’ attempt to make that showing with a\\njurisdictional argument. They contend that a three-judge court should have\\ndecided this case. The statute says that a “district court of three judges shall\\nbe convened when otherwise required by Act of Congress, or when an action is\\nfiled challenging the constitutionality of the apportionment of congressional\\ndistricts or the apportionment of any statewide legislative body.” 28 U.S.C.\\n§ 2284(a). The Voting Rights Act does not require three-judge courts for\\nSection 2 cases (notably it does for Section 5 cases, 52 U.S.C. § 10304(a)), so\\nDefendants focus on the latter part of the statute. They contend that\\n“constitutionality” modifies only challenges to apportionment of congressional\\ndistricts, not challenges to apportionment of state legislatures. On their\\n\\n\\n 7\\n\\n Case: 19-60133 Document: 00514885572 Page: 8 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nreading, any challenge to state legislative redistricting—including the\\nstatutory Voting Rights Act one asserted here—requires a three-judge panel.\\n Defendants requested a three-judge panel late in the litigation, a week\\nbefore trial. Failing to request such a panel in their answer may have forfeited\\nthe issue unless it is a jurisdictional requirement. The three-judge statute has\\nconflicting language on whether it is one. It begins by saying “a district court\\nof three judges shall be convened” for specified cases. 28 U.S.C. § 2284(a). That\\nmandatory language sounds jurisdictional. So does the statute’s prohibition\\non a single judge taking certain actions, including granting injunctive relief.\\nId. § 2284(b)(3). But the statute also says that the procedure for convening a\\nthree-judge court kicks in “[u]pon the filing of a request for three judges.” Id.\\n§ 2284(b)(1). That does not sound jurisdictional. If the requirement is\\njurisdictional, then the single district judge first assigned the case would\\nseemingly have an obligation to convene a three-judge panel even if a party\\ndoes not ask for it.\\n Recognizing these conflicting statutory signals, the leading federal\\nprocedure treatise is ambivalent about whether Section 2284 is jurisdictional.\\nSee 17A Charles Alan Wright et al., FED. PRAC. & PROC. § 4235, at 206–08 (3d\\ned. 2007). But apparently the courts that have considered the question—\\nincluding ours in a nonbinding decision—have treated Section 2284 as\\njurisdictional. See Kalson v. Patterson, 542 F.3d 281, 287 (2nd Cir. 2008);\\nArmour v. Ohio, 925 F.2d 987, 989 (6th Cir. 1991) (en banc); LULAC of Texas\\nv. Texas, 318 F. App’x 261, 264 (5th Cir. 2009). That consensus in the caselaw\\nmeans that forfeiture is an obstacle Defendants will likely be able to overcome\\non appeal.\\n Defendants’ delay in raising this issue does, however, say something\\nabout its merits. At the outset of this lawsuit, it was not obvious to Defendants\\n\\n\\n 8\\n\\n Case: 19-60133 Document: 00514885572 Page: 9 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\n(or Plaintiffs or the district judge for that matter) that its exclusively statutory\\nclaims required a three-judge court. Indeed, no reported case has ever used a\\nthree-judge panel for a case challenging district lines only under Section 2 of\\nthe Voting Rights Act. See Rural W. Tenn. African-American Affairs Council\\nv. Sundquist, 209 F.3d 835, 838 (6th Cir. 2000) (noting case reassigned to single\\njudge after dismissal of constitutional and Section 5 claims); Chestnut v.\\nMerrill, 2019 WL 338909 (N.D. Ala. 2019) (rejecting argument that a single\\njudge could not hear Section 2 challenge); Bone Shirt v. Hazeltine, 336 F. Supp.\\n2d 976, 980 (D. S.D. 2004) (same as Rural West); Old Person v. Brown, 182 F.\\nSupp. 2d 1002, 1003 (D. Mont. 2002) (single judge hearing Section 2 challenge);\\nsee also Armour, 925 F.2d at 989 (stating the jurisdictional test for Section\\n2284 as whether “there exists a non-frivolous constitutional challenge to the\\napportionment of a statewide legislative body” (emphasis added)). 4 That no\\ncourt has adopted Defendants’ reading of the three-judge statute in the more\\nthan four decades it has been on the books alone seems enough to prevent them\\nfrom showing a strong likelihood of succeeding on this issue. To be sure, only\\nthe Chestnut opinion from earlier this year addressed an argument like the one\\nDefendants make. But that is again telling: Before this year, it apparently had\\nnever dawned on a judge or party in a Section 2-only state redistricting case\\n\\n\\n\\n 4 Though uncited by Defendants or their amicus, the dissent finds Page v. Bartels, 248\\nF.3d 175 (3d Cir. 2001), “most significant[].” Dissenting Op. at 15. But unlike the cases cited\\nabove, Page does not involve a situation in which plaintiffs only brought Section 2 claims.\\nInstead, it involved both constitutional and statutory claims. Yet a single district court judge\\nattempted to spin off the statutory claims and deny an injunction based on them. Id. at 187.\\nThe Third Circuit said that when plaintiffs bring both claims, both must be sent to a three-\\njudge panel. Id. at 191. That is consistent with the common practice when both constitutional\\nand statutory challenges to reapportionment are brought—the constitutional hook for three-\\njudge jurisdiction sweeps in the statutory claims. While the dissent tries to find support for\\nits position in some of Page’s discussion of legislative history and policy, notably the Third\\nCircuit does not adopt the textual argument the dissent and amicus push.\\n\\n\\n 9\\n\\n Case: 19-60133 Document: 00514885572 Page: 10 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nthat a three-judge panel might be required. And that is because the most\\nstraightforward reading of the three-judge statute is that it applies only when\\nthe “constitutionality” of apportionment is being challenged.\\n So why does the dissent, adopting the argument of an amicus, think the\\nthree-judge statute applies to what is only a statutory challenge when no court\\nhas ever taken that view? One word—the “the” that precedes “apportionment\\nof any statewide legislative body.” 28 U.S.C. § 2284(a). Inclusion of that article\\nmeans, in their view, that “constitutionality” applies only to what immediately\\nfollows it: challenges to the “apportionment of congressional districts.” If\\n“constitutionality” does not also modify the “apportionment of any statewide\\nlegislative body,” id., then any challenges to those districts, including statutory\\nones, require a three-judge panel.\\n The textual argument is a dispute about application of the “series\\nmodifier” canon of construction. It normally means that a modifier\\n(“constitutionality” in Section 2284) applies to an entire series of parallel\\nterms. See Scalia & Garner, READING LAW: THE INTERPRETATION OF LEGAL\\nTEXTS 147 (2012). The district court concluded that principle supports reading\\nthe statute as applying to constitutional challenges to apportionment of both\\ncongressional and state legislative seats. But an amicus supporting the\\ndefendants argues the “the” coming before “apportionment of any statewide\\nlegislative body” breaks the series modifier. The amicus notes that a\\n“determiner” word, such as the “the” in Section 2284(a), is an indication that a\\nmodifier should not reach the second element. 5 See id. at 148–49.\\n\\n\\n\\n 5 Defendants make a different textual argument in support of their position that this\\ncase belongs with a three-judge court. They focus not just on the “the,” but on “the\\napportionment” that precedes “of any statewide legislative body.” They contend it is\\nsuperfluous if it does not break off the “constitutionality” modifier. But it may be\\n“appropriate to tolerate a degree of surplusage.” United States v. Atl. Research Corp., 551\\n 10\\n\\n Case: 19-60133 Document: 00514885572 Page: 11 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\n But inferring that “the” was meant to cut off the “constitutionality”\\nmodifier ignores what may be the most important teaching about the series\\nmodifier canon from the Scalia and Garner book on statutory interpretation:\\n“Perhaps more than most of the other canons, this one is highly sensitive to\\ncontext.” Id. at 150. That context supports the natural reading that courts have\\nlong given it: that “constitutionality” modifies both “the apportionment of\\ncongressional districts” and “the apportionment of any statewide legislative\\nbody.” That Congress wanted the two phrases to sound the same—“the\\napportionment of congressional districts” and “the apportionment of any\\nstatewide legislative body” are word-for-word identical, with the exception of\\nthe type of district that they reference—is consistent with how ordinary people\\nspeak and write. See Lockhart v. United States, 136 S. Ct. 958, 970 (2016)\\n(Kagan, J., dissenting). To illustrate this, consider what a reader would think\\nafter seeing the following in the newspaper: “The NCAA is investigating the\\nrecruiting practices of the football program and the basketball program.” As\\nwith the three-judge statute, the final “the” may not be necessary. But would\\nit make the reader think the investigation into the basketball program is not\\nlimited to recruiting violations, but also might include point shaving or ticket\\nscalping violations? Of course not. The dissent’s textual argument about the\\nthree-judge statute is just as detached from common usage.\\n What is more, giving so much significance to “the” runs counter to\\nanother point Justice Scalia made about statutory interpretation: that\\nCongress “does not . . . hide elephants in mouseholes.” Whitman v. Am.\\nTrucking Ass’n, 531 U.S. 457, 468 (2001). The historical development of the\\nthree-judge statute—that is, statutory history as opposed to the more\\n\\n\\n\\nU.S. 128, 137 (2007). Indeed, one could make the case that even the first “the,” the one before\\n“apportionment of congressional districts,” is unnecessary.\\n 11\\n\\n Case: 19-60133 Document: 00514885572 Page: 12 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\ncontroversial legislative history Defendants rely on—shows why it would have\\nbeen so significant and anomalous to require three-judge panels for statutory\\nclaims. The statute was first enacted in the aftermath of Ex parte Young to\\nrequire three judges to hear what Congress thought would be an increasing\\nnumber of suits challenging state laws “upon the ground of the\\nunconstitutionality of such statute.” 28 U.S.C. § 2281 (1970); see generally\\nDavid P. Currie, The Three-Judge District Court in Constitutional Litigation,\\n32 U. CHI. L. REV. 1, 5–8 (1964). When courts later struck down many New\\nDeal reforms, one of the only aspects of President Roosevelt’s court-packing\\nplan to become law was a measure also requiring three-judge panels for suits\\nseeking to enjoin “any Act of Congress for repugnance to the Constitution of\\nthe United States.” 28 U.S.C. § 2282 (1970); see Wright, FED. PRAC. & PROC.\\n§ 4234, at 194–95. Both laws’ focus on only constitutional challenges made\\nsense as striking down democratically enacted laws is “the gravest and most\\ndelicate duty” courts are “called on to perform.” Nw. Austin Mun. Util. Dist.\\nNo. One v. Holder, 557 U.S. 193, 204 (2009) (referring to striking down an Act\\nof Congress (quoting Blodgett v. Holden, 275 U.S. 142, 147–48 (1927) (Holmes,\\nJ., concurring))). The idea of requiring three judges for this “class of cases of\\nspecial importance” was to “assure more weight and greater deliberation by\\nnot leaving the fate of such litigation to a single judge.” Phillips v. United\\nStates, 312 U.S. 246, 249–50 (1941) (first quotation from Ex parte Collins, 277\\nU.S. 565, 567 (1928)). But in the mid-1970s, Congress decided to scrap just\\nabout all of the three-judge regime because it was burdening the Supreme\\nCourt and lower courts and had resulted in procedural complexities. See\\nWright, FED. PRAC. & PROC. § 4234, at 195–98; Kalson, 542 F.3d at 287 (noting\\nthat the 1976 Act “vastly reduced the category of cases for which a three-judge\\ncourt is mandated”). It nonetheless decided to retain the procedure for a small\\n\\n\\n 12\\n\\n Case: 19-60133 Document: 00514885572 Page: 13 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nset of important cases: constitutional challenges to redistricting for\\ncongressional and state legislative seats, then-recent phenomena in the\\naftermath of the revolutionary one person, one vote line of cases. See, e.g.,\\nReynolds v. Sims, 377 U.S. 533 (1964). If Congress had intended to expand the\\nstatute it was otherwise contracting by applying it for the first time to\\nstatutory challenges there were certainly better ways to do it than by stealthily\\ninserting an extra “the.”\\n Reading the statute in the way Defendants suggest does not make sense\\nfor another reason: Why would Congress require three judges to hear statutory\\nclaims challenging state legislative redistricting but not congressional\\nredistricting? The dissent posits, without citing any authority, that perhaps\\nfederalism concerns would explain such a difference. But there are also strong\\nfederalism concerns with how a state chooses to divvy up its citizens into\\ncongressional districts. In fact, contemporary critics of the initial judicial foray\\ninto review of legislative apportionment viewed courts’ redrawing of\\ncongressional district as even more intrusive on traditional state prerogatives\\nthan judicial redrawing of state legislative districts. That is because of the\\nview that Article I, Section II of the Constitution grants “States . . . plenary\\npower to select their allotted Representatives in accordance with any method\\nof popular election they please, subject only to the supervisory power of\\nCongress.” Wesberry v. Sanders, 376 U.S. 1, 23 (1964) (Harlan, J., dissenting).\\n The other problem with the dissent’s theory—that Congress in 1976 had\\na special concern with statutory challenges to the drawing of state legislative\\ndistricts—is that it fails to grapple with the rarity of Section 2 challenges to\\nredistricting at that time. It was then not even clear that Section 2 provided a\\nprivate right of action. City of Mobile v. Bolden, 446 U.S. 55, 60 & n.8 (1980)\\n(assuming without deciding such a suit could exist). A few years later the\\n\\n\\n 13\\n\\n Case: 19-60133 Document: 00514885572 Page: 14 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nSupreme Court held Section 2 did not prohibit discriminatory effects which\\nmeant it provided no guarantee beyond what the Constitution already did. See\\nid. And the typical pre-1982 Section 2 claim that courts did consider was a\\nchallenge to at-large electoral systems, not the line drawing of single member\\ndistricts. See, e.g., id. In other words, there was no practice of statutory\\nchallenges to state legislative apportionment that Congress needed to address\\nin 1976.\\n To sum up, the dissent would give this much weight to the “the” that\\ncomes before “reapportionment of any statewide legislative body”: Insertion of\\nthat article would require three-judge panels for exclusively statutory claims—\\nfollowed by direct appeal to the Supreme Court, 28 U.S.C. § 1253—when the\\nthree-judge regime Congress was contracting in 1976 never did. It would\\nrequire those three-judge panels only for statutory challenges to\\napportionment of state legislative seats, not congressional ones. And it would\\ndo all this to address statutory challenges to apportionment of state\\nlegislatures when those claims hardly existed in 1976. An elephant indeed.\\n The dissent contends that there might have been clearer ways to\\nemphasize that the statute is limited to constitutional challenges. Dissenting\\nOp. at 12. But if Congress intended to include statutory-only challenges within\\nthe reach of the general three-judge statute for the first time, there were many\\neasy ways to make that clear. This brings up a final point on the jurisdictional\\nquestion. To the extent there is ambiguity, the longstanding principle that\\n“congressional enactments providing for the convening of three-judge courts\\nmust be strictly construed” comes into play. Allen v. State Bd. of Elections, 393\\nU.S. 544, 561 (1969); Phillips, 312 U.S. at 250 (noting the three-judge statue\\nshould be read narrowly because of its impact on the Supreme Court docket\\nand the burdens of convening three-judge courts).\\n\\n\\n 14\\n\\n Case: 19-60133 Document: 00514885572 Page: 15 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\n That rule of construction, the text of the three-judge statute, its lineage,\\nand the caselaw applying it all favor the district court’s view that three judges\\nare not required for a claim raising only statutory challenges to state\\nlegislative redistricting. Defendants thus face a steep climb in convincing this\\ncourt to be the first to ever read the statute as applying to a case challenging\\na district’s lines only under Section Two of the Voting Rights Act.\\n IV.\\n A.\\n Defendants also seek a stay on the ground that we are likely to reverse\\nthe district court’s ruling that District 22 dilutes the voting power of African-\\nAmericans. The standard of review poses an obstacle to undoing the factual\\nfindings that led the court to conclude that the district violates Section 2. An\\nappellate court “will not set aside” Section 2 factual findings “unless [it is] left\\nwith the definite and firm conviction that a mistake has been committed.”\\nMagnolia Bar Ass’n, Inc. v. Lee, 994 F.2d 1143, 1147 (5th Cir. 1993) (quotation\\nomitted); see NAACP v. Fordice, 252 F.3d 361, 365 (5th Cir. 2001) (noting that\\nclear error review applies).\\n In an attempt to avoid the clear-error standard, Defendants frame their\\nprimary challenge to liability as a legal one. They contend that a court cannot\\nfind vote dilution of a racial group that makes up a majority of the challenged\\ndistrict (recall that here that is just barely the case for District 22). This per\\nse rule they advocate—a bar on vote dilution claims whenever the racial group\\ncrosses the 50% threshold—is at odds with the reason we give such deference\\nto factual findings in Section 2 cases: the question of vote dilution is “peculiarly\\ndependent upon the facts of each case,” Thornburg v. Gingles, 478 U.S. 30, 79\\n(1986) (quoting Nevett v. Sides, 571 F.2d 209, 224 (5th Cir. 1978)), and\\n“requires an ‘intensely local appraisal’ of the challenged district,” LULAC, 548\\n\\n\\n 15\\n\\n Case: 19-60133 Document: 00514885572 Page: 16 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nU.S. at 437 (quoting Gingles, 478 U.S. at 79). The numerous local factors courts\\nconsider—including the strength of bloc voting, demographics, and voter\\nturnout—may mean that a minority group has the equal electoral opportunity\\nthe Voting Rights Act guarantees when its members make up only 40% of a\\ndistrict, but not when they make up 51%. Applying Defendants’ absolute bar\\non Section 2 scrutiny of 50%-plus districts to this case shows how it would\\narbitrarily override the numerous local considerations that Congress and the\\nSupreme Court have said courts need to consider in this important area. If\\nthere were a few hundred fewer African-Americans out of the nearly 44,000\\nvoting-age citizens in District 22, Defendants would allow courts to engage in\\nthe regular multifaceted vote dilution inquiry. But, to Defendants, just over\\n300 additional African-Americans makes the difference between that ordinary\\ninquiry and removing Section 2’s protections for tens of thousands of\\nMississippi voters.\\n Given the statutory mandate to focus on the “totality of circumstances”\\nin Section 2 cases, 52 U.S.C. § 10301(b), it is not surprising that numerous\\ncourts have found dilution of the voting power of a racial group in districts\\nwhere they make up a majority of the voting population. Most importantly,\\nour court has long rejected the argument Defendants advance. In an early vote\\ndilution case—also out of the Mississippi Delta—we explained that the “mere\\nexistence of a black population majority does not preclude a finding of dilution.”\\nMoore v. Leflore Cty. Bd. of Election Comm’rs, 502 F.2d 621, 624 (5th Cir. 1974).\\nWe echoed that more recently, stating that “a protected class that is also a\\nregistered voter majority is not foreclosed, as a matter of law, from raising a\\nvote dilution claim.” Salas v. Sw. Tex. Jr. Coll. Dist., 964 F.2d 1542, 1550 (5th\\nCir. 1992). We have even gone so far so to describe the authority on this point\\nas “unimpeachable.” Monroe v. City of Woodville, 881 F.2d 1327, 1333 (5th\\n\\n\\n 16\\n\\n Case: 19-60133 Document: 00514885572 Page: 17 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nCir. 1989) (describing the caselaw from our circuit that “has rejected any per\\nse rule that a racial minority that is a majority in a political subdivision cannot\\nexperience vote dilution”). We are not alone. Many courts of appeals, including\\none last year, have rejected the argument that a “racial minority cannot prevail\\non a Section 2 claim when it constitutes a bare numerical majority within the\\ndistrict.” Mo. St. Conf. of the NAACP v. Ferguson-Florissant Sch. Dist., 894\\nF.3d 924, 933 (8th Cir. 2018) (collecting cases from the Second, Fifth, Eleventh,\\nand D.C. Circuits).\\n Defendants try to distinguish these cases and others by arguing that\\nthey addressed at-large elections rather than single-member districts. But\\nnothing in these cases turned on that feature. And one court of appeals case\\ndirectly confronting the question rejected a bar on vote dilution claims for\\ngroups that make up more than 50% of the challenged single-member district.\\nKingman Park Civic Ass’n v. Williams, 348 F.3d 1033, 1041 (D.C. Cir. 2003)\\n(agreeing with Salas and Moore in a single-member district vote dilution case).\\nSo did a recent three-judge panel in this circuit. See Perez v. Abbott, 253 F.\\nSupp. 3d 864, 879–90 (W.D. Tex. 2017) (rejecting Defendants’ position when\\nfinding vote dilution in a congressional district with a Hispanic voting-age\\npopulation of 58.5%).\\n Against all this authority of both old and recent vintage, all Defendants\\ncan point to is Justice Kennedy’s opinion in Bartlett v. Strickland, 556 U.S. 1\\n(2009) (opinion of Kennedy, J.). 6 Here is the statement they contend supports\\na categorical rule that there can be no Voting Rights Act violation when a racial\\ngroup exceeds 50% of the district’s population: “Where an election district could\\n\\n\\n 6The defendants also cite Jeffers v. Beebe, 895 F. Supp. 2d 920, 932 (E.D. Ark. 2012),\\nas an example of a court employing their 50%+ bar on Section 2 claims. Even if they read\\nthat case correctly, that holding is no longer good law in its circuit. See Mo. St. Conf. of the\\nNAACP, 894 F.3d at 933.\\n 17\\n\\n Case: 19-60133 Document: 00514885572 Page: 18 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nbe drawn in which minority voters form a majority but such a district is not\\ndrawn,” a Section 2 claim is possible. This is an “objective, numerical test.” Id.\\nat 18. Assuming this opinion is the controlling one under Marks 7 (Justice\\nKennedy wrote for only three judges), it is addressing a different question. He\\nwas rejecting the concept of crossover districts and instead would require that\\na vote-dilution plaintiff show that a district could be drawn in which the racial\\ngroup is a majority. Id. at 15-20. In fact, that is the first showing Gingles\\nrequires. LULAC, 548 U.S. at 425 (noting the first “condition[] for establishing\\na § 2 violation” is that “the racial group is sufficiently large and geographically\\ncompact to constitute a majority in a single-member district” (cleaned up)).\\nFrom that requirement it does not follow that vote dilution cannot occur when\\nthe protected group already makes up a majority in the contested district. It\\nis thus not surprising that no court has read Bartlett to override the widely\\naccepted view that the voting strength of a protected group can still be diluted\\nwhen that group is a majority of a challenged district. Indeed, if any opinion\\nfrom Justice Kennedy addresses the question before us, it is his recognition in\\nLULAC that “it may be possible for a citizen voting-age majority to lack real\\nelectoral opportunity.” Id. at 428.\\n Recognizing this robust caselaw rejecting Defendants’ per se rule\\n(including in single-member cases), the dissent relies on an argument the\\nDefendants have never made: that there needed to be a finding of cracking or\\npacking minority voters. We typically will not consider arguments not\\nadvanced by a party. State Indus. Prods. Corp. v. Beta Tech Inc., 575 F.3d 450,\\n456 (5th Cir. 2009). That principle makes even more sense in the stay context.\\n\\n\\n 7See Marks v. United States, 430 U.S. 188, 193 (1977) (“When a fragmented Court\\ndecides a case and no single rationale explaining the result enjoys the assent of five Justices,\\nthe holding of the Court may be viewed as that position taken by those Members who\\nconcurred in the judgments on the narrowest grounds.” (quotation omitted)).\\n 18\\n\\n Case: 19-60133 Document: 00514885572 Page: 19 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nIf a “party is not entitled to a stay as a matter of right” even based on objections\\nit raised before the district court and in requesting a stay, Campaign for\\nSouthern Equality v. Bryant, 773 F.3d 55 (5th Cir. 2014), it should not be\\nentitled to that extraordinary remedy based on arguments the district court\\nnever had the chance to consider.\\n Even if we could grant a stay based on a challenge to the judgment\\nDefendants do not raise, the dissent’s position misses the marks on the merits.\\nIt argues that vote dilution can occur in a 50%-plus district only if the dilution\\nis the result of cracking or packing minority voters. The terms cracking\\n(dividing minority voters among various districts to weaken their strength)\\nand packing (concentrating minority voters in one or a small number of\\ndistricts where they make up an excessive majority and thus reduce that\\ngroup’s influence in other districts) describe gerrymandering techniques. Gill\\nv. Whitford, 138 S. Ct. 1916, 1924 (2018) (describing the practice in challenge\\nalleging partisan gerrymander); Shaw v. Reno, 509 U.S. 630, 670 (1993)\\n(White, J., dissenting) (same in challenge alleging racial gerrymander). They\\nexplain why vote dilution is occurring. Gill, 138 S. Ct. at 1931. The terms can\\nthus be used to describe types of Section 2 vote dilution claims. See, e.g.,\\nVoinovich v. Quilter, 507 U.S. 146, 153 (1993). But the “cracking” or “packing”\\ndescription does not result in a different Section 2 test or finding. Whether the\\ntheory for dilution is cracking or packing or something else, Section 2 claims\\nare evaluated by first looking at the three Gingles factors to determine whether\\ndemographics, geography, and voting behavior would allow the creation of a\\ndistrict in which the minority group has electoral power. LULAC, 548 U.S. at\\n425. If the plaintiffs satisfy that threshold, then a court considers the “totality\\nof the circumstances” to determine if “members of a racial group have less\\n\\n\\n\\n 19\\n\\n Case: 19-60133 Document: 00514885572 Page: 20 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nopportunity than do other members of the electorate.” Id. at 425–26. The\\ndistrict court faithfully followed this path. 8\\n Although cracking and packing are not official parts of the Section 2\\nanalysis, as a matter of arithmetic vote dilution will often exist because of\\ncracking or packing. Put another way, minority voting strength is often\\nweaker than demographics would allow because those voters have been\\ncrammed into one district with a very high minority percentage and thus\\ndiluted in other districts (packing) or spread among various districts when they\\ncould have formed an electoral majority in at least one (cracking). Indeed, the\\ndistrict court’s findings demonstrate cracking occurred here. 9 District 22 has\\na BVAP of 50.77% and District 23 has a BVAP of 42.00% when, as the remedy\\nadopted by the district court demonstrates, African-Americans could easily\\nform sufficient electoral strength to elect their representative of choice in at\\nleast one of these two districts.\\n The district court correctly focused on the Section 2 factors as prescribed\\nby the Supreme Court and the Voting Rights Act. Part of the reason it found\\nthat the <51% majority of African-American voters in the district did not result\\nin an ability to elect a representative of that group’s choosing was because of\\nturnout in off-year elections. So the “50%-plus” issue is largely an attempt to\\npackage Defendants’ challenge to the factual finding in a more favorable\\nstandard of review. But as with any other factual finding, the clearly\\n\\n\\n 8 It is thus not true that the district court thought that “simply because a district can\\n\\nbe drawn in a way that will guarantee a minority an election win, the Voting Rights Act\\ncompels that such a district be drawn.” Dissenting Op. at 7–8. The district court considered\\nall of the statutorily prescribed factors in finding vote dilution. The dissent is also wrong in\\nsaying that the district court thought a 62% African-American district was required. See id.\\nThat is just the demographics of the remedy it adopted that changed only 28 precincts. To\\nsay that the court thought that percentage was a requirement is to say that any time a\\ndistrict court remedies a Section 2 violation it is creating a new minimum.\\n9 There was no need to use the cracking label because Defendants never made the argument\\n\\nthe dissent advances.\\n 20\\n\\n Case: 19-60133 Document: 00514885572 Page: 21 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nerroneous standard means it is unlikely to be disturbed on appeal. That is\\nparticularly true when the factfinder gives a sound reason for crediting one\\nside’s evidence over the other’s. The district court did that in explaining why\\nit relied on Plaintiffs’ expert for turnout data rather than Census Bureau\\nfigures. The Census Bureau’s election data is for even-year elections, while\\nMississippi conducts odd-year state senate elections.\\n Defendants have not shown a high likelihood of overturning the finding\\nof vote dilution because their legal argument is at odds with “unimpeachable\\nauthority” from our court and their factual challenges must overcome\\ndeferential standards of review.\\n B.\\n\\n Defendants also argue that the district court erred by not dismissing the\\nlawsuit on laches grounds, focusing entirely on Thomas’s delay in bringing this\\nlawsuit. Even if he were the only plaintiff, the standard of review would again\\npose a substantial obstacle for Defendants to overcome on appeal. A district\\ncourt’s equitable ruling on laches is reviewed for abuse of discretion, and the\\nfactual findings of delay, inexcusability, and prejudice that underlie it are\\nreviewed for clear error. See Retractable Tech., Inc. v. Becton Dickinson & Co.,\\n842 F.3d 883, 898 (5th Cir. 2016).\\n More problematic than that for Defendants, Thomas is not the only\\nperson who brought this suit. The stay motion makes no argument for why\\nlaches should bar the lawsuit as to Plaintiffs Ayers and Lawson. As with all\\naffirmative defenses, the party asserting a laches defense bears the burden of\\nproving it. See City of El Paso, Tex. v. El Paso Entm’t, Inc., 382 F. App’x 361,\\n366 (5th Cir. 2010). Defendants did not even attempt to meet this burden for\\nAyers and Lawson. Nor is there, despite the dissent’s attempt to salvage a\\nlaches defense, an exception for the “main plaintiff,” whatever that means. Cf.\\n\\n 21\\n\\n Case: 19-60133 Document: 00514885572 Page: 22 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nMassachusetts v. EPA, 549 U.S. 497, 518 (2007) (observing that only one\\npetitioner needed to have standing to bring suit). The Voting Rights Act\\nprotects the rights of voters, not politicians. As to voters Ayers and Lawson,\\nDefendants point to nothing showing that a laches defense is likely to succeed\\non appeal.\\n V.\\n A.\\n The final ground on which Defendants seek a stay is the remedy the\\ndistrict court ordered. The standard of review again poses a challenge: the\\ndistrict court’s remedy is reviewed for abuse of discretion. Rodriguez v. Bexar\\nCnty., Tex., 385 F.3d 853, 870 (5th Cir. 2004).\\n But “whenever practicable . . . a reasonable opportunity [should be\\nafforded] the legislature to meet constitutional requirements by adopting a\\nsubstituted measure rather than for the federal court to devise and order into\\neffect its own plan.” Veasey, 830 F.3d at 270 (quoting Wise v. Lipscomb, 437\\nU.S. 535, 540 (1978) (opinion of White, J.)) (emphasis original). As recounted\\nabove, the district court first honored this principle in noting it would allow\\ntime for a legislative fix before it would redraw the district. When the court\\nwas informed that the legislature would not act until it saw the outcome of the\\nstay requests, the district court went ahead and redrew the lines given\\nconcerns about the candidate qualifying deadline. It noted, however, that the\\nlegislature always has the ability to redraw districts. Plaintiffs also point this\\nout in their response to the stay motion.\\n The legislature’s desire to wait to see the outcome of the stay ruling is\\nunderstandable. It would have been inefficient for it to remedy a violation only\\nto have this court grant a stay of the district court’s entire judgment on the\\nground that Defendants were likely to overturn the finding of vote dilution.\\n\\n\\n 22\\n\\n Case: 19-60133 Document: 00514885572 Page: 23 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nBut now that we have concluded to the contrary, the legislature should have\\nthe initial opportunity to draw new lines for District 22 that comply with the\\nVoting Rights Act. The only reason not to give it that first shot at crafting a\\nremedy is the candidate filing deadline, but the Secretary of State is requesting\\nthe legislative fix and has not indicated that a further extension of that\\ndeadline for the affected districts is problematic. And while the legislature is\\nalways able to redraw lines, the remedial preference is for it to have the first\\nchance to remedy a Section 2 violation, not for it to act only after the court\\ndraws a new district, which would result in three different districts in a short\\ntime period. United States v. Brown, 561 F.3d 420, 435 (5th Cir. 2009).\\n We thus issued an order on March 15 granting a temporary stay to allow\\nthe legislature until April 3 to remedy the Section 2 violation. The order also\\nextended the candidate filing deadline for any affected districts until April 12.\\n B.\\n Defendants otherwise are not likely to surmount the abuse of discretion\\nstandard in challenging the court’s remedy. If the legislature does not act and\\nthe judicial remedy goes into effect, it must still respect the legislature’s policy\\nobjectives as much as possible. See Perry v. Perez, 565 U.S. 38, 393 (2012). The\\nremedy is a narrowly-tailored one that does that. While redistricting cases\\noften result in redrawing the entire state or at least several districts, this\\nremedy moves just 28 precincts, less than 2% of the precincts in the state. The\\nremedy affects only 2 of Mississippi’s 52 Senate districts. The court found that\\nthe new lines met traditional redistricting criteria: compactness, contiguity,\\npreservation of political subdivisions like counties and cities, and avoiding\\npairing incumbents. It adopted the proposed map of an expert it found credible\\nwho also determined that the new map honored traditional criteria of\\ncompactness and contiguity. In fact, the new district is more consistent with\\n\\n\\n 23\\n\\n Case: 19-60133 Document: 00514885572 Page: 24 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\ntraditional geographic divisions in one important respect: it removes the\\nsuburban Madison county precincts and thus limits the district to counties in\\nthe rural and agricultural Delta.\\n The slightly altered districts are, if anything, also more compact than\\nthey were before. The following map of the new and old districts show the\\nlimited impact of the court’s remedy. The orange and pink highlighting shows\\nthe new districts; the blue lines show the old ones.\\n\\n\\n\\n\\n 24\\n\\n Case: 19-60133 Document: 00514885572 Page: 25 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\n Defendants’ main critique is that the new lines split Vicksburg between\\nthe districts. But some splitting of counties or cities is inevitable given equal\\npopulation requirements. A look at the statewide senate districts reveals this.\\nThe lines the legislature drew split at least eight cities with populations\\nbetween 23,000 and 27,000 residents (Vicksburg had a population of 26,407\\nwhen the 2012 maps were drawn) into different senate districts, including\\nClinton, whose 25,216 citizens are split among 5 districts. Having to split\\nVicksburg thus does not lack fidelity to the legislature’s redistricting policy\\nwhich often results in the same situation. Defendants have not demonstrated\\na high likelihood of showing that that district court’s narrow redraw was an\\nabuse of discretion.\\n C.\\n The dissent also contends that the district court’s remedy interferes with\\nongoing election preparation, though the Defendants—including the Secretary\\nof State—do not cite this as a reason for a stay. In a recent case denying a stay\\nin a voting rights case, we did not consider this issue when government officials\\ndid not argue that the district court’s plan would substantially disturb the\\nelection process. Patino v. City of Pasadena, 677 F. App’x 950, 951–52 (5th Cir.\\n2017).\\n The election is even further away in this case than it was in Patino. Id.\\n(denying stay sought during the candidate registration period with election\\nthree months away); see also Patino v. City of Pasadena, 229 F. Supp. 3d 582,\\n585 (S.D. Tex. 2017) (providing the relevant dates). Primary voting is more\\nthan four months away; the general election is more than seven months away.\\nThat distance to the election means the potential for voter confusion that\\n\\n\\n\\n\\n 25\\n\\n Case: 19-60133 Document: 00514885572 Page: 26 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nanimates this concern, Purcell v. Gonzalez, 549 U.S. 1, 4 (2006), is absent. 10\\nMississippi voters in the 28 affected precincts will go to the same voting\\nlocation they always have, face the same voting requirements, and have\\nmonths to research the candidates in advance of the election. Indeed, the effect\\nof redrawing some of the lines for just two state senate districts with elections\\nmonths away pales in comparison to the impact of statewide redistricting that\\nhas been implemented in a similar timeframe. See, e.g., Covington v. North\\nCarolina, 2018 WL 604732 (M.D. N.C. 2018); Common Cause v. Rucho, 284 F.\\nSupp. 3d 780 (M.D. N.C. 2018); Larios v. Cox, 305 F. Supp. 2d 1335 (N.D. Ga.\\n2004).\\n With no risk of voter confusion, and no outcry from state officials that\\nimplementing the district court’s remedy substantially disturbs its election\\nprocess, this is not a basis for a stay.\\n D.\\n One final comment is necessary to set the record straight in response to\\nthe dissent’s attack on the remedy. It irresponsibly insinuates that the district\\njudge—whom it takes the unusual step of repeatedly naming—drew new lines\\nwith the aim of eliminating partisan opposition to Plaintiff Thomas. That is\\nnot true. Importantly, the incumbent state senator in District 22 had decided\\nnot to run for reelection before the district court ruled in this case. The\\ndissent’s conjecture also ignores that primary candidates file with the political\\nparty (not the state), with the parties notifying state officials of the candidates\\n\\n\\n 10 As most of the cases cited by the dissent show, the voter confusion concern is\\ntypically greatest when a court alters election procedures (as opposed to districts) with an\\nelection quickly approaching. See Veasey v. Perry, 769 F.3d 890, 892 (5th Cir. 2014) (staying\\ndistrict court injunction striking down voter ID laws); Purcell, 549 U.S. at 1 (same); North\\nCarolina v. League of Women Voters of N.C., 135 S. Ct. 6 (2014) (staying district court order\\nthat changed voter ID requirements, voting hours, voting locations, and voter registration);\\nHusted v. Ohio State Conference of NAACP, 135 S. Ct. 42 (2014) (staying district court order\\nthat changed voting hours).\\n 26\\n\\n Case: 19-60133 Document: 00514885572 Page: 27 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nonly after the filing deadline. That had not yet occurred when the court issued\\nfinal judgment.\\n In light of these circumstances, there is no basis for believing that the\\nPlaintiffs’ expert who drew the proposed remedy back in mid-January, or the\\ndistrict court that later adopted it, knew who the new candidates would be. No\\none brought the names or residences of the candidates to the court’s attention\\nprior to its remedy ruling. And the district court issued its remedy before the\\ninitial candidate qualifying deadline, so there may have been additional\\ncandidates. Not until after the court issued its remedy, in a motion for stay,\\ndid Defendants bring to the court’s attention the fact that two candidates\\nwould no longer reside in District 22. On learning this, the district court\\nlamented that it was not told prior to its ruling. As for the competition in the\\nnew district, we do not know who has filed nor who will file prior to the new\\nqualifying deadline.\\n ***\\n Per the order issued last week, the motion for stay is GRANTED IN\\nPART and DENIED IN PART. A majority of the panel concludes Defendants\\nhave satisfied the stay factors only based on the need to give the legislature\\nand Governor an opportunity to remedy the Section 2 violation. A stay is\\nentered for that purpose until April 3, 2019. The candidate filing deadline for\\nany districts whose lines are redrawn (whether by the legislature, or if it does\\nnot act, per the district court’s remedy) is extended to April 12, 2019. The\\ndistrict court has jurisdiction to consider any challenges to the adequacy of a\\nlegislative remedy.\\n\\n\\n\\n\\n 27\\n\\n Case: 19-60133 Document: 00514885572 Page: 28 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4380525/\", \"author_raw\": \"GREGG COSTA, Circuit Judge:\"}, {\"author\": \"EDITH BROWN CLEMENT, Circuit Judge, dissenting\", \"type\": \"dissent\", \"text\": \"EDITH BROWN CLEMENT, Circuit Judge, dissenting in part.\\n\\n Joseph Thomas is a black Democrat and resident of Yazoo County,\\nMississippi. A one-time State Senator who lost in 2007 and sat out the 2011\\nelection cycle, he is trying hard to get his seat back. Thomas ran in the 2015\\nState Senate election in District 22 and lost to the Republican incumbent by a\\nthin margin. Three years later, Thomas and two voters sued the Mississippi\\nGovernor, Secretary of State, and Attorney General, accusing them of\\ngerrymandering District 22 in violation of Section 2 of the Voting Rights Act.\\nThe plaintiffs argued that black voters in District 22 are politically cohesive,\\nbut that white bloc voting prevents them from electing their candidate of\\nchoice. Although black voters already comprised a majority of the voting age\\npopulation in District 22 at 51%, the plaintiffs argued that this majority was\\ntoo narrow for them to elect a candidate. They say they need at least a 62%\\nmajority to do that. The district court agreed that 62% was necessary. And\\nbecause achieving that percentage was possible by shifting black voters from\\na neighboring district into District 22, Judge Reeves ordered it done. But he\\nalso managed to move something important out of District 22 in the process.\\nNamely, the two Republican challengers to Thomas for the 2019 election.\\n\\n I feel confident that the district court’s decision will ultimately be\\nreversed. At least, it should be. Laches may well bar the challenge. There is a\\njurisdictional issue. The theory of liability is unheard-of. The evidence is\\nsuspect. And the remedy (as even the majority acknowledges) is faulty. A\\nlikelihood of success on any one of these cascading objections is enough to\\nentitle the defendants to a stay of the district court’s redistricting plan. After\\nall, as the majority explains, the stakes are high here. When the majority\\nsays there is a “meaningful possibility” that a full appeal could come too late,\\nthat is quite the understatement. It is like saying there is a “meaningful\\n 28\\n\\n Case: 19-60133 Document: 00514885572 Page: 29 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\npossibility” that a Republican could win an election in the new District 22.\\nPossible in theory, perhaps, but contrary to common understanding and\\nexperience.\\n\\n I dissent from the panel’s refusal to grant the stay in its entirety.\\nUnless we act now, the November election in Senate District 22 is all but\\ndecided. True, predictable election results are not uncommon. What is\\nuncommon, however, is for a federal district judge to be the one to decide\\nthem.\\n\\n I. The Remedy Problem\\n\\n I begin where the district court ended, because even the majority has\\ntrouble defending that. Even if Judge Reeves was permitted to decide this\\ncase by himself and even if he was correct that District 22 violates Section 2,\\nit remains obvious that his remedy should be stayed and, ultimately,\\nreversed. It is not even a close call.\\n\\n “Federal-court review of districting legislation represents a serious\\nintrusion on the most vital of local functions.” Miller v. Johnson, 515 U.S.\\n900, 915 (1995). It is well settled that “reapportionment is primarily the duty\\nand responsibility of the State.” Id. Appropriately, therefore, our case law is\\nclear that “whenever practicable, . . . a reasonable opportunity [should be\\nafforded] for the legislature to meet constitutional requirements by adopting\\na substitute measure rather than for the federal court to devise and order\\ninto effect its own plan.” Veasey v. Abbott, 830 F.3d 216, 270 (5th Cir. 2016)\\n(en banc) (quotation omitted).\\n\\n That standard undoubtedly leaves room for a district court to act before\\nthe legislature when necessary. Given that the original candidate qualifying\\n\\n 29\\n\\n Case: 19-60133 Document: 00514885572 Page: 30 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\ndeadline has come and gone, that the ballots must be sent to overseas troops\\nby the end of June, and that the primary is scheduled for early August, I can\\nappreciate that we are operating on an abbreviated timetable. But that is all\\nthe more reason to preserve the status quo. Federal courts rarely have the\\nright to issue orders the effect of which is to dramatically interfere with\\nongoing election preparation. See Veasey v. Perry, 769 F.3d 890, 892 (5th Cir.\\n2014) (“The Supreme Court has repeatedly instructed courts to carefully\\nconsider the importance of preserving the status quo on the eve of an\\nelection.”). “[U]nder certain circumstances, such as where an impending\\nelection is imminent and a State’s election machinery is already in progress,\\nequitable considerations might justify a court in withholding the granting of\\nimmediately effective relief in a legislative apportionment case, even though\\nthe existing apportionment scheme was found invalid.” Reynolds v. Sims, 377\\nU.S. 533, 585 (1964).\\n\\n When issues are hotly contested or when the district court’s reasoning\\nor remedy are flawed, when time to act is short, and when elections hang in\\nthe balance, it is almost always better to wait than to interfere. Our court has\\nstayed district court orders in such situations in the past. See, e.g., Veasey,\\n769 F.3d 890. And when we or other appellate courts have been unwilling to\\ndo so, the Supreme Court has stepped in to preserve the status quo. See, e.g.,\\nNorth Carolina v. League of Women Voters of N.C., 135 S. Ct. 6 (2014)\\n(overturning Fourth Circuit injunction which barred implementation of the\\nstate’s voting reform laws); Husted v. Ohio State Conference of NAACP, 135\\nS. Ct. 42 (2014) (staying district court’s injunction); Perry v. Perez, 565 U.S.\\n1090 (2011) (same); Purcell v. Gonzalez, 549 U.S. 1, 4–5 (2006) (per curiam)\\n(vacating Ninth Circuit injunction, and observing that “[c]ourt orders\\n\\n\\n 30\\n\\n Case: 19-60133 Document: 00514885572 Page: 31 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\naffecting elections, especially conflicting orders, can themselves result in\\nvoter confusion and consequent incentive to remain away from the polls”).\\n\\n Curiously, the majority believes that because the Supreme Court has\\nmostly done so in cases involving “election procedures,” not redistricting, the\\nCourt’s admonitions carry less weight here. But they have it backwards.\\nAltering which candidates appear on a voter’s ballot is a much greater\\nimposition on him than changing the location of his poll or the form of ID he\\nmust have in his pocket. Indeed, I have not found a case in which a court\\naltered district boundaries during or after a candidate qualification period.\\nWe should maintain the status quo here, or else expect the country’s highest\\ncourt to once again do it for us.\\n\\n But even if Judge Reeves had little choice but to implement a remedy\\nhimself, I am deeply concerned with the remedy he chose and the way that he\\nchose it. As the majority explains, Judge Reeves adopted the first of three\\nplans submitted by the plaintiffs. He adopted it without making factual\\nfindings and without a hearing. In his single-page order adopting the plan,\\nJudge Reeves did not explain why “Plan 1” was the narrowest remedy or\\nclarify why he had rejected “Plan 2” and “Plan 3.” The only time Judge\\nReeves discussed the details of the plans was in his liability opinion, where\\nhe devoted three pages to describing them.\\n\\n The three plans are similar. All require moving several thousand\\nindividuals (27,000 for Plan 1) either into or out of District 22 from one or two\\nadjacent districts. Plans 1 and 2 only affect only Districts 22 and 23, whereas\\nPlan 3 also changes the boundary of District 13. All three plans split the city\\nof Vicksburg in half, though only Plan 2 and Plan 3 offset that splitting by\\nreuniting other cities that are currently split. Under Plan 1, the black voting\\n\\n 31\\n\\n Case: 19-60133 Document: 00514885572 Page: 32 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nage population of District 22 would increase to 62%. Under Plan 2, the\\npopulation would increase to 61%. And under Plan 3, it would increase to\\n66%. Apart from stating generically that none of the plans “dilute minority\\nvoting strength,” Judge Reeves did not discuss the effect each of the plans\\nwould have on the black voting age population of District 23 or District 13.\\nHe simply noted that Plan 1 would decrease the black voting age population\\nin neighboring District 23 from 42% to 31%.\\n\\n Looking at the record, I have no idea why Judge Reeves preferred one\\nplan over another. I do not understand why he selected the one plan in which\\nthe splitting of Vicksburg was not offset in some other way. I do not\\nunderstand how Judge Reeves could endorse increasing the black voting age\\npopulation of one district without discussing the effect that the change would\\nhave on the black voting age population of adjacent districts. And I do not\\nunderstand why Judge Reeves did not hold a hearing before making his\\ndecision. The fact remains that his order—perhaps, inadvertently—\\neliminated meaningful competition for Thomas in the upcoming election. The\\nmajority says that Judge Reeves’s plan is “narrowly tailored.” Agreed—it is\\n“narrowly tailored” to win Thomas the election. 1 In my view, our circuit’s\\nstrong preference for the legislature to have the first say on redistricting,\\ncombined with the obvious defects in Judge Reeves’s remedy, make it likely\\nthat his redistricting plan will ultimately be reversed.\\n\\n\\n\\n\\n 1 The majority thinks this observation “irresponsibl[e].” But even though the slate of\\ncandidates had not and could not have been finalized at the time of the district court’s order,\\nit does not require a crystal ball to foresee the result of Judge Reeves’s remedy. He eliminated\\nthe Republican base in District 22, essentially making the primary election dispositive. As\\nfar as we know, Thomas is the only previously-elected State Senator running in that primary\\nand as far as we know, his only two Republican challengers are now in another district.\\n 32\\n\\n Case: 19-60133 Document: 00514885572 Page: 33 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\n II. The Merits Problem\\n\\n Another problem with the remedy is that there shouldn’t be one.\\nIndeed, I also think the district court erred in finding a Voting Rights Act\\nviolation. I agree with the majority that, at least as a matter of theory, it may\\nbe possible for a state to violate Section 2 of the Act even when a protected\\ngroup forms a majority of the voting population. That option is left open by\\nour precedent. See Salas v. Southwest Texas Jr. College Dist., 964 F.2d 1542,\\n1550 (5th Cir. 1992); Moore v. Leflore County Bd. of Election Com’rs, 502 F.2d\\n621, 624 (5th Cir. 1974). But even accepting that possibility, there is a strong\\nlikelihood that Judge Reeves committed clear error by finding a Section 2\\nviolation here. Where “the ultimate finding of dilution” is based on “a\\nmisreading of the governing law,” there is reversible error. Johnson v. De\\nGrandy, 512 U.S. 997, 1022 (1994).\\n\\n As the Supreme Court has explained, “a plaintiff may allege a § 2\\nviolation in a single-member district if the manipulation of districting lines\\nfragments politically cohesive minority voters among several districts or\\npacks them into one district or a small number of districts, and thereby\\ndilutes the voting strength of members of the minority population.” Shaw v.\\nHunt, 517 U.S. 899, 914 (1996). In other words, a state can violate Section 2\\nby “cracking” the minority vote into separate districts so that the minority is\\nunable to elect its chosen representatives, or by “packing” the minority vote\\ninto supermajority-minority districts—thereby reducing the overall number\\nof representatives that the minority receives. See, e.g., Pope v. Cty. of Albany,\\n687 F.3d 565, 567 (2d Cir. 2012) (minority alleging that their population size\\nand geographical distribution warranted five majority-minority districts, not\\nfour); Kingman Park Civic Ass’n v. Williams, 348 F.3d 1033, 1038 (D.C. Cir.\\n\\n\\n 33\\n\\n Case: 19-60133 Document: 00514885572 Page: 34 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\n2003) (minority alleging that redistricting diluted the minority vote overall\\nby packing it into some districts and cracking it in others).\\n\\n It is crucial to understand this context. No court has ever found that a\\nmajority-minority single-member district violates Section 2 by itself. The idea\\nthat a majority-minority district violates Section 2 only makes sense if the\\nallegation is that packing or cracking has occurred. See Thornburg v. Gingles,\\n478 U.S. 30, 46 n.11 (1986) (“Dilution of racial minority group voting strength\\nmay be caused by the dispersal of blacks into districts in which they\\nconstitute an ineffective minority of voters or from the concentration of blacks\\ninto districts where they constitute an excessive majority.”). Both kinds of\\nviolations span district lines. A plaintiff cannot prove packing or cracking\\nwithout analyzing minority population and voter statistics for multiple\\ndistricts. See, e.g., Perez v. Abbott, 253 F. Supp. 3d 864, 879 (W.D. Tex. 2017)\\n(analyzing statistics for numerous districts and concluding that “while\\nPlaintiffs may not have submitted sufficient proof that they are entitled to\\neight [Hispanic citizen voting age population]-majority districts in\\nSouth/West Texas, they have shown that they are entitled to seven such\\ndistricts, and they may assert claims under . . . § 2 against the districts in\\n[the current plan]”).\\n\\n There was no such evidence in this case. Indeed, the complaint nowhere\\nmentions “packing” or “cracking,” and the evidence focused on District 22\\nalone. I do not understand how a majority-minority district could violate\\nSection 2 unless the district is the result of packing or cracking the minority\\nvote among a geographical area that is larger than the district itself. The\\nallegation that the minority’s majority is not large enough to overcome white\\nbloc voting would only become actionable if the minority’s majority is being\\nartificially lowered to dilute the minority vote.\\n 34\\n\\n Case: 19-60133 Document: 00514885572 Page: 35 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\n The majority opinion suggests that Section 2 vote dilution requires that\\na minority group be deprived of a district in which it has electoral strength to\\nelect a representative of its choice when such a district is possible. But\\nnothing in Section 2 “establishes a right to have members of a protected class\\nelected in numbers equal to their proportion in the population.” 52 U.S.C. §\\n10301(b). “[T]he ultimate right of § 2 is equality of opportunity, not a\\nguarantee of electoral success for minority-preferred candidates of whatever\\nrace.” De Grandy, 512 U.S. at 1014 n.11; see also Gingles, 478 U.S. at96\\n(O’Connor, J., concurring in the judgment).\\n\\n The district court and the majority seem to think that simply because a\\ndistrict can be drawn in a way that will guarantee a minority an election win,\\nthe Voting Rights Act compels that such a district be drawn. Not so. Section 2\\ndoes not grant the plaintiffs a right to a 62% majority to overcome low black\\nturnout or white bloc voting in the abstract. It is only when the drawing of\\ndistrict lines along traditional methods should have resulted in a different\\nelectoral scheme that Section 2 is violated. There must be evidence that\\npacking or cracking has taken place (whether or not it is expressly referred to\\nas such). 2 That is the difference between guaranteeing equal opportunity and\\nguaranteeing electoral success.\\n\\n The majority would avoid this reality by saying the defendants do not\\nraise the issue. But challenging the viability of Voting Rights Act claims in\\nmajority-minority single-member districts and also challenging the plaintiffs’\\n\\n\\n 2 Putting these fundamental concerns to the side, I also believe the plaintiffs did not\\noffer sufficient evidence to support their claim. I am particularly troubled by Judge Reeves’s\\ndecision to disregard Census Bureau statistics concluding that black voter turnout generally\\nexceeds white voter turnout. Even the cases relied on by the plaintiffs acknowledge that\\nCensus Bureau statistics are usually dispositive. See Mo. St. Conf. of the NAACP v. Ferguson-\\nFlorissant Sch. Dist., 894 F.3d 924, 932–33 (8th Cir. 2018).\\n 35\\n\\n Case: 19-60133 Document: 00514885572 Page: 36 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nevidence in this case—both of which defendants do—places the district court’s\\nmerits ruling in contention. It is telling that the majority, apparently\\nrecognizing the conceptual difficulty of finding vote dilution in the absence of\\npacking or cracking, ultimately attempts to recast the district court’s finding\\nin that vein. But because there was no such evidence—indeed, neither\\npacking nor cracking was even alleged—the plaintiffs have not shown a\\nSection 2 violation.\\n\\n III. The Laches Problem\\n\\n The plaintiffs are entirely to blame for the haste with which we must\\nresolve this case. The challenged redistricting occurred seven years ago.\\nDisliking what he saw from the start, Thomas contacted the Department of\\nJustice in 2012 and asked them to “look hard” at newly drawn Senate\\nDistricts 21, 22, and 34. He questioned whether the new redistricting plan as\\na whole reduced black voting strength in Mississippi. Rejecting Thomas’s\\nconcerns, the DOJ precleared the plan in September 2012.\\n\\n Thomas waited. He did not file a Voting Rights Act challenge in 2012,\\n2013, or 2014. He chose instead to run in the 2015 election, losing 54% to 46%\\nto the incumbent chairman of the State Senate Appropriations Committee.\\nThomas was “real disappointed” that despite his efforts to appeal to white\\nvoters in the 2015 election, he garnered little of the white vote. See Thomas v.\\nBryant, 2019 WL 654314, at *1 (S.D. Miss. Feb. 16, 2019).\\n\\n Still, Thomas did nothing. He did not file a Voting Rights Act challenge\\nin 2015, 2016, or 2017. Thomas has explained that he was unaware that an\\nindividual could file a Voting Rights Act challenge until his lawyer told him\\nin 2018. But “laches does not depend on subjective awareness of the legal\\nbasis on which a claim can be made.” Envtl. Def. Fund, Inc. v. Alexander, 614\\n 36\\n\\n Case: 19-60133 Document: 00514885572 Page: 37 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nF.2d 474, 479 (5th Cir. 1980). The letter to the DOJ shows that Thomas had\\nconcerns about District 22 as early as 2012, yet he waited until halfway\\nthrough 2018 to act.\\n\\n That delay prejudiced the defendants and the public. Laches is an\\ninexcusable delay on the part of the plaintiff that results in prejudice to the\\ndefendant. Conan Props., Inc. v. Conans Pizza, Inc., 752 F.2d 145, 153 (5th\\nCir. 1985). It has been applied by the Supreme Court to bar untimely Voting\\nRights Act challenges. Lopez v. Hale Cty., Tex., 506 U.S. 1042 (1993)\\n(affirming Lopez v. Hale Cty., Tex., 797 F. Supp. 547, 550 (N.D. Tex. 1992));\\nCf. White v. Daniel, 909 F.2d 99, 102 (4th Cir. 1990). By waiting until now to\\nchallenge the district, Thomas has injected needless uncertainty into the\\nNovember 2019 election. Mere months before Election Day, Mississippi voters\\nwent to bed in one district and woke up in another. Candidates suddenly find\\nthemselves running for office in a district they do not know, appealing to a\\npublic that does not know them. And the Republican Party finds itself\\nwithout a horse in the race, moments before the starting gun is fired.\\n\\n The delay has inured to the benefit only of Thomas, whose prospects\\nhave brightened noticeably since the district court redrew the political\\nlandscape. His postponement of legal action has—unless the stay is\\ngranted—all but ensured that there will be no time for reconsideration of the\\ndistrict court’s opinion before the election. Judge Reeves’s decision, made on\\nan accelerated timeline following expedited discovery, is likely to be the end\\nof the matter. The balance of the equities, in my view, is not on Thomas’s\\nside. 3\\n\\n\\n\\n The other plaintiffs, Vernon Ayers and Melvin Lawson, do not undermine this view.\\n 3\\n\\nLawson is a District 22 voter who worked on Thomas’s Senate campaign and then joined\\n 37\\n\\n Case: 19-60133 Document: 00514885572 Page: 38 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\n IV. The Jurisdiction Problem\\n\\n Assuming Thomas did not unduly delay, however, was it permissible\\nfor the district court to decide this Voting Rights Act case without convening\\na three-judge panel? As the majority notes, there is no need to get into this\\nunless 28 U.S.C. § 2284(a) is jurisdictional. That statute provides: “A district\\ncourt of three judges shall be convened when otherwise required by Act of\\nCongress, or when an action is filed challenging the constitutionality of the\\napportionment of congressional districts or the apportionment of any\\nstatewide legislative body.”\\n\\n The majority is right that the statute certainly “sounds jurisdictional.”\\nMaybe that is why every court to consider the question has said that it is. See\\nKalson v. Patterson, 542 F.3d 281, 287 (2nd Cir. 2008); Armour v. State of\\nOhio, 925 F.2d 987, 988–89 (6th Cir. 1991) (en banc); LULAC of Texas v.\\nTexas, 318 F. App’x 261, 264 (5th Cir. 2009) (per curiam). I think so too. And\\nsince the majority ultimately concedes that forfeiture is an obstacle the\\ndefendants “will likely be able to overcome on appeal,” I will get straight to\\nthe heart of the question.\\n\\n This lawsuit is indisputably an action challenging the apportionment of\\na statewide legislative body. The only question is whether the “constitutional”\\nmodifier in § 2284(a) applies to the second phrase in the sentence. The\\ndistrict court ruled that it does, giving three reasons. Thomas v. Bryant, No.\\n0190219C, 2019 WL 454598, at *2–3 (S.D. Miss. Feb. 5, 2019). First, that\\n\\n\\n\\nThomas’s lawsuit. No one seems to know anything about Ayers besides the fact that he is a\\nregistered voter in District 22. Thomas is the main plaintiff (even the district court’s opinion\\nfocused almost exclusively on Thomas). In any event, all the plaintiffs are challenging district\\nlines which were implemented seven years ago. It is that unnecessary delay, common to all\\nthe plaintiffs, which should bar the suit.\\n 38\\n\\n Case: 19-60133 Document: 00514885572 Page: 39 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nthere was no reason to treat Voting Rights Act claims and constitutional\\nclaims as identical in the statewide context. Second, that the plain language\\nof the text and statutory canons of construction compelled the court’s\\ninterpretation. Third, that the court’s decision was buttressed by other\\npersuasive decisions. The first two reasons are totally incorrect, and the third\\nis weak.\\n\\n “The task of statutory interpretation begins and, if possible, ends with\\nthe language of the statute.” United States v. Lauderdale Cty., Mississippi,\\n914 F.3d 960, 964 (5th Cir. 2019). The district court said that the “series-\\nqualifier” canon compelled its conclusion that the constitutionality modifier\\napplied to both phrases. Thomas, 2019 WL 454598 at *2–3. The book\\n“Reading Law” explains the canon as follows: “When there is a\\nstraightforward, parallel construction that involves all nouns or verbs in a\\nseries, a prepositive or postpositive modifier normally applies to the entire\\nseries.” ANTONIN SCALIA & BRYAN A. GARNER, READING LAW: THE\\nINTERPRETATION OF LEGAL TEXTS 147 (2012). A typical example is the phrase\\n“Forcibly assaults, resists, opposes, impedes, intimidates, or interferes with,”\\nin which the modifier “forcibly modifies each verb in the list.” Id. at 148.\\nCrucially for our purposes, however, the authors also explain when the\\nmodifier does not apply:\\n\\n The typical way in which syntax would suggest no\\n carryover modification is that a determiner (a, the, some, etc.) will\\n be repeated before the second element: [for example,] The\\n charitable institutions or the societies (the presence of the second\\n the suggests that the societies need not be charitable).\\n\\n\\nId.\\n\\n\\n 39\\n\\n Case: 19-60133 Document: 00514885572 Page: 40 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\n That is exactly the situation we have here. The statute provides for a\\nthree-judge court “when an action is filed challenging the constitutionality of\\nthe apportionment of congressional districts or the apportionment of any\\nstatewide legislative body.” 28 U.S.C. § 2284(a) (emphasis added). The\\ndeterminer “the” (or the determining phrase “the apportionment”) cuts off the\\ncontinued application of the word “constitutionality” to the second phrase.\\nThat the sentence has a parallel structure, as the majority harps on, is not\\ndispositive. After all, if the statute did not have a parallel structure, we\\nwould not be discussing the series-qualifier canon in the first place. The\\nwhole point of the canon is to describe when a modifier applies to a parallel\\nseries, and when it does not. The canon and the context both answer that\\nquestion in the negative.\\n\\n If Congress intended the majority’s interpretation, there would have\\nbeen much clearer ways to say so. Here are just three examples:\\n\\n • A district court of three judges shall be convened . . . when an\\n action is filed challenging the constitutionality of the\\n apportionment of congressional districts or [the\\n apportionment] of any statewide legislative body.\\n\\n\\n • A district court of three judges shall be convened . . . when an\\n action is filed challenging the constitutionality of [either] the\\n apportionment of congressional districts or the apportionment\\n of any statewide legislative body.\\n\\n\\n • A district court of three judges shall be convened . . . when an\\n action is filed challenging the constitutionality of the\\n apportionment of congressional districts or [of] the\\n apportionment of any statewide legislative body.\\n\\n\\n\\n\\n 40\\n\\n Case: 19-60133 Document: 00514885572 Page: 41 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nNotably, Congress said none of those things. At the risk of quoting someone\\nother than the late Justice Scalia, the Supreme Court has observed time and\\nagain that we “must presume that a legislature says in a statute what it\\nmeans and means in a statute what it says.” Connecticut Nat. Bank v.\\nGermain, 503 U.S. 249, 253–54 (1992); see also, e.g., Arlington Cent. Sch.\\nDist. Bd. of Educ. v. Murphy, 548 U.S. 291, 296 (2006); In re Camp, 631 F.3d\\n757, 759 (5th Cir. 2011).\\n\\n This may seem overly technical. But the district court explicitly noted\\nthat “[d]espite its ‘fancy name,’ the series-qualifier canon ‘reflects the\\ncompletely ordinary way that people speak and listen, write and read.’”\\nThomas, 2019 WL 454598 at *2 n.5 (quoting Lockhart v. United States, 136 S.\\nCt. 958, 970 (2016) (Kagan, J., dissenting)). And the canon supports the\\nopposite interpretation from the one adopted by the district court. It is this\\nreading, and not the majority’s reading, which reflects the plain meaning of\\nthe statute. Further, the district court admitted the defendants had a “fair\\npoint” that the court’s interpretation resulted in the statute containing\\nneedless words. Id. at *2. “If ‘the constitutionality of’ is indeed carried over to\\nall following phrases, the second use of ‘the apportionment of’ is rendered\\nunnecessary.” Id. The correct application of the series-qualifier canon has the\\nadded benefit of avoiding that contradiction and giving meaning to every\\nword in the statute. This is consistent with yet another canon: the surplusage\\ncanon. See SCALIA & GARNER, at 174–79.\\n\\n The district court could not understand why Congress would treat\\nVoting Rights Act and constitutional claims as identical, focusing on the fact\\nthat they have different evidentiary requirements and that a plaintiff is\\nmaster of his complaint. Thomas, 2019 WL 454598 at *2. But the differing\\nburdens of proof and the plaintiff’s undenied ability to select the claims he\\n 41\\n\\n Case: 19-60133 Document: 00514885572 Page: 42 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nwishes to bring do not undermine the rationale for treating all challenges to\\nstatewide legislative apportionment the same. Both constitutional and\\nstatutory attacks on legislative redistricting implicate the same fundamental\\nconcern: balancing judicial respect for a state’s decision regarding the best\\nmanner of selecting its representatives with the need to ensure equal\\nopportunity within the electorate. Whether court-ordered redistricting is\\nbased on the Constitution or the Voting Rights Act makes little difference to\\nthe state whose actions have been curtailed.\\n\\n Indeed, a more relevant question than the one asked by the district\\ncourt is why the statute would treat challenges to congressional redistricting\\ndifferently from challenges to statewide legislative redistricting. The answer\\nto that challenge may well lie in federalism. It is entirely plausible that\\nCongress wanted federal courts to show more deference to state\\nreapportionment plans that only affect state interests than to state\\nreapportionment plans which affect national interests. The majority suggests\\nthat federalism would actually support the opposite inference, considering\\nthat a state’s power to select its congressional representatives stems directly\\nfrom Article I, Section II of the Constitution. But that line of reasoning is\\nundermined by Supreme Court precedent, which has allowed the states\\ngreater latitude in creating state legislative districts than in creating\\ncongressional districts. See Gaffney v. Cummings, 412 U.S. 735, 742–44\\n(1973).\\n\\n In any event, I am not arguing that federalism compels the statutory\\ninterpretation for which I advocate. I simply offer a plausible explanation for\\nwhy the plain text says what it does. The truth is that most of the time, the\\nopposing interpretations of § 2284(a) will not matter, as Voting Rights Act\\nclaims and constitutional claims are usually asserted together. That is why—\\n 42\\n\\n Case: 19-60133 Document: 00514885572 Page: 43 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nfar from hiding an elephant in a mousehole—the correct interpretation\\nmerely ensures equal treatment for stand-alone Voting Rights Act claims\\nwhose implications can be quite as severe as constitutional ones. My view has\\nthe additional benefit of avoiding the forum-shopping concerns implicit in the\\nmajority’s reading.\\n\\n Finally, the district court’s conclusion that non-binding cases\\n“buttress[]” its decision is weak. See Thomas, 2019 WL 454598 at *3. The\\ndistrict court cited a Sixth Circuit decision, a Third Circuit decision, and a\\ndecision from the Northern District of Georgia. Id. The majority adds a\\ncitation from the Northern District of Alabama, the District of South Dakota,\\nand the District of Montana. The sum of persuasive authority on this point is\\ntwo circuit court opinions and four district court opinions. And as the\\nmajority admits, these cases really aren’t on point to begin with. The Sixth\\nCircuit opinion does not mention § 2284(a)—it simply affirmed a single-judge\\ndecision. Rural West Tennessee African-American Affairs Council v.\\nSundquist, 209 F.3d 835 (6th Cir. 2000). Of the district court opinions, only\\nthe Northern District of Alabama addresses the question head-on, and it fails\\nto mention the series-qualifier canon or the superfluous language that all\\nparties admit results from the district court’s reading. See Chestnut v.\\nMerrill, 2019 WL 338909 (N.D. Ala. 2019).\\n\\n Most significantly, the Third Circuit decision supports the opposite\\nconclusion from that reached by the district court. In Page, the court was\\nconsidering whether a single judge may decide a Voting Rights Act claim\\nwhen statutory and constitutional claims are brought together. See Page v.\\nBartels, 248 F.3d 175, 186–94 (3d Cir. 2001). While the opinion says that §\\n2284(a) “only requires a three-judge district court for certain constitutionally-\\nbased apportionment challenges,” the court further stated that Congress\\n 43\\n\\n Case: 19-60133 Document: 00514885572 Page: 44 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nlikely did not make a “deliberate choice to distinguish between constitutional\\napportionment challenges and apportionment challenges brought under § 2 of\\nthe Voting Rights Act.” Id. at 189.\\n\\n Indeed, most redistricting challenges at the time of the 1976\\namendment were constitutional, meaning the distinction carried less\\nimportance in 1976 than it does today. And “the legislative history of the\\n1976 revisions to 28 U.S.C. § 2284 clearly demonstrates that Congress was\\nconcerned less with the source of the law on which an apportionment\\nchallenge was based than on the unique importance of apportionment cases\\ngenerally.” Id. at 190. Because all cases attacking “the legitimacy of the state\\nlegislative apportionment” are “highly sensitive matters,” the Third Circuit\\nconcluded that practical and policy considerations weighed in favor of three-\\njudge review irrespective of the nature of the claims asserted. Id. So in its\\nsurvey of the caselaw, the majority seems to have missed that the only circuit\\ncourt opinion to address the issue in any depth goes the other way. 4\\n\\n Of course, none of these opinions (and there are not very many of them)\\nare binding on this court. As noted earlier, the issue does not come up often\\nsince plaintiffs normally bring suit using all the potential weapons in their\\narsenal. To the extent that the opinions that have considered this question\\ncut in any direction, however, I’d submit they cut in favor of the three-judge\\npanel for Voting Rights Act claims. The district court was wrong to read §\\n2284(a) in the manner it did. A three-judge panel should have decided this\\ncase.\\n\\n\\n\\n The majority acknowledges Page in a footnote, noting that it “does not adopt the\\n 4\\n\\ntextual argument” I am advocating here. That is unsurprising, considering that no one\\nadvocated for such an interpretation in Page. It is the reasoning from the opinion which\\nsupports my view—not the opinion’s different answer to a different question.\\n 44\\n\\n Case: 19-60133 Document: 00514885572 Page: 45 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\n * * *\\n\\n This case presents several extraordinary issues. Unfortunately, this\\ncourt’s usual procedures do not appear to permit en banc review of this denial\\nof a stay even if a majority of the active judges would otherwise grant it. I am\\nafraid defendants have simply had the poor luck of drawing a majority-\\nminority panel. I trust that in light of this, the State will pursue a stay in the\\nSupreme Court because of the injustice that results from the joint efforts of\\nthe district judge and the motions panel majority. I also encourage the State\\nto move for an expedited appellate process before this court, preferably\\nseeking an April or May sitting—it might yet be possible for this court to\\nundo its own mistake.\\n\\n\\n\\n\\n 45\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4380525/\", \"author_raw\": \"EDITH BROWN CLEMENT, Circuit Judge, dissenting\"}]}"},"judge1":{"kind":"string","value":"DENNIS"},"judge2":{"kind":"string","value":"CLEMENT"},"judge3":{"kind":"string","value":"COSTA"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":2,"string":"2"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":1,"string":"1"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4603272/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Joseph THOMAS; Vernon Ayers; Melvin Lawson, Plaintiffs - Appellees v. Phil BRYANT, Governor of the State of Mississippi; Delbert Hosemann, Secretary of State of the State of Mississippi, Both in the Official Capacities of Their Own Offices and in Their Official Capacities as Members of the State Board of Election Commissioners, Defendants - Appellants\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-22\nOpinion type: majority\nHas dissenting opinion: Yes\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 19-60133 Document: 00514885572 Page: 1 Date Filed: 03/22/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT United States Court of Appeals\n Fifth Circuit\n\n ___________________ FILED\n March 22, 2019\n No. 19-60133 Lyle W. Cayce\n ___________________ Clerk\n\nJOSEPH THOMAS; VERNON AYERS; MELVIN LAWSON,\n\n Plaintiffs - Appellees\n\nv.\n\nPHIL BRYANT, Governor of the State of Mississippi,; DELBERT\nHOSEMANN, Secretary of State of the State of Mississippi, both in the\nofficial capacities of their own offices and in their official capacities as\nmembers of the State Board of Election Commissioners,\n\n Defendants - Appellants\n\n _______________________\n\n Appeal from the United States District Court\n for the Southern District of Mississippi\n _______________________\n\nBefore DENNIS, CLEMENT, and COSTA, Circuit Judges.\nGREGG COSTA, Circuit Judge:\n A district court found that the boundaries for Mississippi State Senate\nDistrict 22 dilute African-American voting strength and prevent those citizens\nfrom having the equal opportunity “to participate in the political process and\nto elect representatives of their choice” that the Voting Rights Act guarantees.\n52 U.S.C. § 10301(b). To remedy the violation, the district court switched 28\nprecincts between District 22 and a bordering district. The Governor and\nSecretary of State seek a stay of the final judgment.\n\n Case: 19-60133 Document: 00514885572 Page: 2 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\n I.\n Most of District 22 lies in the heart of the Mississippi Delta. Those\nunfamiliar with the state’s geography might think that the Mississippi Delta\nis in the southern portion of the state that is closer to the mouth of the\nMississippi River. But the “Delta” refers not to the outlet of that mighty river\ninto the Gulf of Mexico, but to the alluvial plain between the Mississippi River\nand the Yazoo River. John M. Barry, RISING TIDE: THE GREAT MISSISSIPPI\nFLOOD OF 1927 AND HOW IT CHANGED AMERICA 96 (1997). It is located in the\nnorthwest section of Mississippi and looks like an “elongated diamond.” Id.\nThe district court recited this colorful description of its boundaries: “The\nMississippi Delta begins in the lobby of the Peabody Hotel [in Memphis] and\nends on Catfish Row in Vicksburg.” David L. Cohn, GOD SHAKES CREATION\n(1935).\n The sediment that the Mississippi River deposited in this region over the\nmillennia made Delta soil some of the richest in the world. Barry, supra, at\n97. And that soil made the Delta one of the leading cotton-producing areas in\nthe world. One historian compared the influence the Delta once held over\nglobal cotton prices to the modern influence of Saudi Arabia over oil prices.\nSven Beckert, EMPIRE OF COTTON: A GLOBAL HISTORY 113 (2014).\n But before agriculture could prosper in the Delta its forests of hardwood\ntrees had to be cleared. Slaves were forced to begin that process, and\nemancipated slaves finished it in the latter part of the nineteenth century.\nSince that time, African-Americans have been a majority in the Delta. In the\nearly twentieth century, they made up almost 90% of the region’s population.\nBarry, supra, at 125 (noting that in 1908 the Delta had “a black population of\nat least 171,209” and “a white population of 24,137”). The Great Migration to\n\n\n\n 2\n\n Case: 19-60133 Document: 00514885572 Page: 3 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\nthe north reduced the African-American percentage, but they remain a\nsizeable majority in the region.\n Of course, for most of their time laboring in the Delta, African-Americans\ncould not vote. The Voting Rights Act changed that. It has resulted in\nnumerous African-Americans being elected to office in the Delta. Indeed, the\nState of Mississippi has more African-American elected officials than any other\nstate. U.S. Census Bureau, STATISTICAL ABSTRACT OF THE UNITED STATES:\n2011, 258 (130th ed.).\n But in places like the state legislature, African-Americans have still not\nachieved political power in Mississippi that comes close to their share of the\npopulation. This case involves a claim that one state senate district\ncontributed to that underrepresentation by diluting the voting strength of\nAfrican-Americans that Delta demographics and geography should otherwise\nsupport and contributed to that underrepresentation.\n District 22 includes all or part of five Delta counties: Bolivar,\nHumphreys, Sharkey, Washington, and Yazoo. It also includes parts of one\nnon-Delta county: Madison. The addition of the white-majority Madison\nCounty precincts in the last redistricting reduced the African-American\npercentage in District 22. Overall the district still has an African-American\nmajority, but just barely at 50.7%. 1 Without the non-Delta precincts from\nMadison County, that percentage would be much higher.\n\n\n\n 1 Plaintiff Thomas told the Department of Justice that the 50.7% figure includes the\npopulation of the Yazoo City federal prison, the majority of whose inmates he says are\nAfrican-American. He contended that without including that prison, African-Americans\nwould not be a majority in the district. It is questionable whether disenfranchised people\nshould be included in the BVAP (black voting age population) calculation for purposes of the\nVoting Rights Act. The focus is usually on those eligible to vote, thus the typical requirement\nin our circuit that the percentage focus on those of voting age who are citizens. See Reyes v.\nCity of Farmers Branch, Tex., 586 F.3d 1019, 1023 (5th Cir. 2009) (noting that only citizens\nare included in population calculations).\n 3\n\n Case: 19-60133 Document: 00514885572 Page: 4 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\n The candidate preferred by the black majority did not prevail in the 2015\nelection. The losing candidate those voters did prefer (Joseph Thomas), along\nwith two voters (Vernon Ayers and Melvin Lawson), brought this lawsuit in\n2018 alleging that the district violated of Section 2 of the Voting Rights Act.\n Last month, the district court held a bench trial and agreed. It concluded\nthat the threshold Gingles factors for establishing vote dilution existed. The\nAfrican-American population is “sufficiently large and geographically compact”\nto constitute a majority with electoral power in the district; that racial group\nis politically cohesive; but the white population voted as a bloc to prevent\nAfrican-Americans from electing their chosen candidate. LULAC v. Perry, 548\nU.S. 399, 425 (2006). The bloc voting by both racial groups was stark: in 10\nelections within district 22, the candidate favored by African-Americans\nreceived between 82% and 93% of their vote but only between 8% and 19% of\nthe white vote.\n The district court then followed the statutory directive to consider the\n“totality of circumstances” in determining whether African-Americans “have\nless opportunity than other members of the electorate to participate in the\npolitical process and to elect representatives of their choice.” 52 U.S.C.\n§ 10301(b); LULAC, 548 U.S. at 425–26. It credited Plaintiffs’ expert’s analysis\nof voter participation as more rigorous and concluded that African-American\nturnout was depressed in off-year elections—that is, odd-year elections without\nfederal races—which is when Mississippi elects its legislature. The district\ncourt also highlighted the persistent representation gap in the Mississippi\nSenate, as well as substantial socioeconomic differences between black voters\nand white voters in the district.\n After finding a Voting Rights Act violation, the court initially declined to\norder a remedy so “the Mississippi Legislature [could] consider[] whether to\n\n\n 4\n\n Case: 19-60133 Document: 00514885572 Page: 5 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\nredraw the District and extend the candidate qualification deadline.”\nAlthough the primary and general elections were months away, the deadline\nfor candidate filing was March 1.\n A flurry of procedural moves followed at warp speed. Three days after\nthe court made its trial findings, the Governor and Secretary of State\n(Defendants) 2 filed a motion a motion to stay with the district court and also\nfiled an appeal, arguing that the ruling was an appealable interlocutory\ninjunction. Less than a week later, they asked this court to stay the district\ncourt’s ruling. That same day, Plaintiffs asked the court to extend the\nqualification deadline in District 22 and bordering District 23 (the other\ndistrict affected by the proposed remedy) by two weeks. Later that day, the\ndistrict court ordered Defendants to update it on any progress, if any, in\nlegislative redrawing of District 22.\n The next day, Defendants filed a brief opposing Plaintiffs’ motion to\nextend the qualification deadline, in which they stated that they had contacted\nthe leadership of the legislative chambers. The Senate leaders had said that\n“should the stay motions pending before [the district court] and the Fifth\nCircuit be denied, the Senate desire[d] the opportunity to enact a new\nredistricting plan redrawing Senate District 22.” Late that same day, the\ndistrict court ruled that, because the legislature was unwilling to act, the first\nmap drawn by one of Plaintiffs’ experts would be adopted as the boundaries of\nDistricts 22 and 23. The court also moved the qualification deadline to March\n\n\n\n\n 2 The third defendant, Attorney General Jim Hood, did not join these motions or this\nappeal.\n 5\n\n Case: 19-60133 Document: 00514885572 Page: 6 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\n15 for the two affected senate districts. The court also declined to enter a stay\nand entered final judgment.\n The final judgment caused our court to dismiss the appeal of the\npreliminary ruling. Thomas v. Bryant, 2019 WL 994034 (5th Cir. Feb. 28,\n2019). But by that time the Defendants had already appealed from the final\njudgment, and not long after that they sought a stay pending the new appeal,\nwhich is the motion before this panel. 3\n This is the effect of the final judgment: It switches some precincts\nbetween Districts 22 and 23. It extends the candidate filing deadline to March\n15. In terms of other upcoming deadlines, the primary election is August 6,\nwith a June 22 deadline to send ballots to troops overseas. The general election\nis November 5.\n II.\n The stay Defendants seek is an extraordinary remedy. Nken v. Holder,\n556 U.S. 418, 437 (2009) (Kennedy, J., concurring). It is also an equitable one\ncommitted to this court’s discretion. Id. at 433; Ruiz v. Estelle, 666 F.2d 854,\n856 & n.4 (5th Cir. 1982). Four factors guide the exercise of our discretion:\n1) whether the applicant has made a strong showing of likelihood to succeed\non the merits; 2) whether the movant will be irreparably harmed absent a stay;\n3) whether issuance of a stay will substantially injure other interested parties;\nand 4) where the public interest lies. Nken, 556 U.S. at 434. The first two\nfactors are usually the most important. Id.; ODonnell v. Goodhart, 900 F.3d\n220, 223 (5th Cir. 2018).\n In this case, the likelihood of success ends up being dispositive. That is\nbecause Defendants can establish irreparable harm. A court order preventing\n\n\n 3 Before seeking the stay pending appeal for the second time in our court after entry\nof final judgment, Defendants also sought a stay in the district court for the second time. The\ndistrict court denied that motion.\n 6\n\n Case: 19-60133 Document: 00514885572 Page: 7 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\nenforcement of a state law, including the drawing of legislative lines,\nconstitutes that harm. Abbott v. Perez, 138 S. Ct. 2305, 2324 n.17 (2018). And\nthat injury may be irreparable in light of the meaningful possibility (but not\ncertainty) that a full appeal cannot be decided in time to provide Defendants\nrelief before this year’s senate elections. But Plaintiffs face the same risk that\nthe appellate ruling will prove futile should this court grant a stay. And the\ninjury they seek to prevent—holding an election under an unlawful plan with\ndiscriminatory effects—is also, it should go without saying, a serious one.\nVeasey v. Abbott, 830 F.3d 216, 270 (5th Cir. 2016) (en banc) (“It would be\nuntenable to permit a law with a discriminatory effect to remain in operation\nfor that election.”); cf. Reynolds v. Sims, 377 U.S. 533, 585 (1964) (“[I]t would\nbe the unusual case in which a court would be justified in not taking\nappropriate action to insure that no further elections are conducted under the\ninvalid plan.”). So Defendants’ entitlement to a stay turns on whether they\nhave a strong likelihood of success.\n III.\n We will first address Defendants’ attempt to make that showing with a\njurisdictional argument. They contend that a three-judge court should have\ndecided this case. The statute says that a “district court of three judges shall\nbe convened when otherwise required by Act of Congress, or when an action is\nfiled challenging the constitutionality of the apportionment of congressional\ndistricts or the apportionment of any statewide legislative body.” 28 U.S.C.\n§ 2284(a). The Voting Rights Act does not require three-judge courts for\nSection 2 cases (notably it does for Section 5 cases, 52 U.S.C. § 10304(a)), so\nDefendants focus on the latter part of the statute. They contend that\n“constitutionality” modifies only challenges to apportionment of congressional\ndistricts, not challenges to apportionment of state legislatures. On their\n\n\n 7\n\n Case: 19-60133 Document: 00514885572 Page: 8 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\nreading, any challenge to state legislative redistricting—including the\nstatutory Voting Rights Act one asserted here—requires a three-judge panel.\n Defendants requested a three-judge panel late in the litigation, a week\nbefore trial. Failing to request such a panel in their answer may have forfeited\nthe issue unless it is a jurisdictional requirement. The three-judge statute has\nconflicting language on whether it is one. It begins by saying “a district court\nof three judges shall be convened” for specified cases. 28 U.S.C. § 2284(a). That\nmandatory language sounds jurisdictional. So does the statute’s prohibition\non a single judge taking certain actions, including granting injunctive relief.\nId. § 2284(b)(3). But the statute also says that the procedure for convening a\nthree-judge court kicks in “[u]pon the filing of a request for three judges.” Id.\n§ 2284(b)(1). That does not sound jurisdictional. If the requirement is\njurisdictional, then the single district judge first assigned the case would\nseemingly have an obligation to convene a three-judge panel even if a party\ndoes not ask for it.\n Recognizing these conflicting statutory signals, the leading federal\nprocedure treatise is ambivalent about whether Section 2284 is jurisdictional.\nSee 17A Charles Alan Wright et al., FED. PRAC. & PROC. § 4235, at 206–08 (3d\ned. 2007). But apparently the courts that have considered the question—\nincluding ours in a nonbinding decision—have treated Section 2284 as\njurisdictional. See Kalson v. Patterson, 542 F.3d 281, 287 (2nd Cir. 2008);\nArmour v. Ohio, 925 F.2d 987, 989 (6th Cir. 1991) (en banc); LULAC of Texas\nv. Texas, 318 F. App’x 261, 264 (5th Cir. 2009). That consensus in the caselaw\nmeans that forfeiture is an obstacle Defendants will likely be able to overcome\non appeal.\n Defendants’ delay in raising this issue does, however, say something\nabout its merits. At the outset of this lawsuit, it was not obvious to Defendants\n\n\n 8\n\n Case: 19-60133 Document: 00514885572 Page: 9 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\n(or Plaintiffs or the district judge for that matter) that its exclusively statutory\nclaims required a three-judge court. Indeed, no reported case has ever used a\nthree-judge panel for a case challenging district lines only under Section 2 of\nthe Voting Rights Act. See Rural W. Tenn. African-American Affairs Council\nv. Sundquist, 209 F.3d 835, 838 (6th Cir. 2000) (noting case reassigned to single\njudge after dismissal of constitutional and Section 5 claims); Chestnut v.\nMerrill, 2019 WL 338909 (N.D. Ala. 2019) (rejecting argument that a single\njudge could not hear Section 2 challenge); Bone Shirt v. Hazeltine, 336 F. Supp.\n2d 976, 980 (D. S.D. 2004) (same as Rural West); Old Person v. Brown, 182 F.\nSupp. 2d 1002, 1003 (D. Mont. 2002) (single judge hearing Section 2 challenge);\nsee also Armour, 925 F.2d at 989 (stating the jurisdictional test for Section\n2284 as whether “there exists a non-frivolous constitutional challenge to the\napportionment of a statewide legislative body” (emphasis added)). 4 That no\ncourt has adopted Defendants’ reading of the three-judge statute in the more\nthan four decades it has been on the books alone seems enough to prevent them\nfrom showing a strong likelihood of succeeding on this issue. To be sure, only\nthe Chestnut opinion from earlier this year addressed an argument like the one\nDefendants make. But that is again telling: Before this year, it apparently had\nnever dawned on a judge or party in a Section 2-only state redistricting case\n\n\n\n 4 Though uncited by Defendants or their amicus, the dissent finds Page v. Bartels, 248\nF.3d 175 (3d Cir. 2001), “most significant[].” Dissenting Op. at 15. But unlike the cases cited\nabove, Page does not involve a situation in which plaintiffs only brought Section 2 claims.\nInstead, it involved both constitutional and statutory claims. Yet a single district court judge\nattempted to spin off the statutory claims and deny an injunction based on them. Id. at 187.\nThe Third Circuit said that when plaintiffs bring both claims, both must be sent to a three-\njudge panel. Id. at 191. That is consistent with the common practice when both constitutional\nand statutory challenges to reapportionment are brought—the constitutional hook for three-\njudge jurisdiction sweeps in the statutory claims. While the dissent tries to find support for\nits position in some of Page’s discussion of legislative history and policy, notably the Third\nCircuit does not adopt the textual argument the dissent and amicus push.\n\n\n 9\n\n Case: 19-60133 Document: 00514885572 Page: 10 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\nthat a three-judge panel might be required. And that is because the most\nstraightforward reading of the three-judge statute is that it applies only when\nthe “constitutionality” of apportionment is being challenged.\n So why does the dissent, adopting the argument of an amicus, think the\nthree-judge statute applies to what is only a statutory challenge when no court\nhas ever taken that view? One word—the “the” that precedes “apportionment\nof any statewide legislative body.” 28 U.S.C. § 2284(a). Inclusion of that article\nmeans, in their view, that “constitutionality” applies only to what immediately\nfollows it: challenges to the “apportionment of congressional districts.” If\n“constitutionality” does not also modify the “apportionment of any statewide\nlegislative body,” id., then any challenges to those districts, including statutory\nones, require a three-judge panel.\n The textual argument is a dispute about application of the “series\nmodifier” canon of construction. It normally means that a modifier\n(“constitutionality” in Section 2284) applies to an entire series of parallel\nterms. See Scalia & Garner, READING LAW: THE INTERPRETATION OF LEGAL\nTEXTS 147 (2012). The district court concluded that principle supports reading\nthe statute as applying to constitutional challenges to apportionment of both\ncongressional and state legislative seats. But an amicus supporting the\ndefendants argues the “the” coming before “apportionment of any statewide\nlegislative body” breaks the series modifier. The amicus notes that a\n“determiner” word, such as the “the” in Section 2284(a), is an indication that a\nmodifier should not reach the second element. 5 See id. at 148–49.\n\n\n\n 5 Defendants make a different textual argument in support of their position that this\ncase belongs with a three-judge court. They focus not just on the “the,” but on “the\napportionment” that precedes “of any statewide legislative body.” They contend it is\nsuperfluous if it does not break off the “constitutionality” modifier. But it may be\n“appropriate to tolerate a degree of surplusage.” United States v. Atl. Research Corp., 551\n 10\n\n Case: 19-60133 Document: 00514885572 Page: 11 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\n But inferring that “the” was meant to cut off the “constitutionality”\nmodifier ignores what may be the most important teaching about the series\nmodifier canon from the Scalia and Garner book on statutory interpretation:\n“Perhaps more than most of the other canons, this one is highly sensitive to\ncontext.” Id. at 150. That context supports the natural reading that courts have\nlong given it: that “constitutionality” modifies both “the apportionment of\ncongressional districts” and “the apportionment of any statewide legislative\nbody.” That Congress wanted the two phrases to sound the same—“the\napportionment of congressional districts” and “the apportionment of any\nstatewide legislative body” are word-for-word identical, with the exception of\nthe type of district that they reference—is consistent with how ordinary people\nspeak and write. See Lockhart v. United States, 136 S. Ct. 958, 970 (2016)\n(Kagan, J., dissenting). To illustrate this, consider what a reader would think\nafter seeing the following in the newspaper: “The NCAA is investigating the\nrecruiting practices of the football program and the basketball program.” As\nwith the three-judge statute, the final “the” may not be necessary. But would\nit make the reader think the investigation into the basketball program is not\nlimited to recruiting violations, but also might include point shaving or ticket\nscalping violations? Of course not. The dissent’s textual argument about the\nthree-judge statute is just as detached from common usage.\n What is more, giving so much significance to “the” runs counter to\nanother point Justice Scalia made about statutory interpretation: that\nCongress “does not . . . hide elephants in mouseholes.” Whitman v. Am.\nTrucking Ass’n, 531 U.S. 457, 468 (2001). The historical development of the\nthree-judge statute—that is, statutory history as opposed to the more\n\n\n\nU.S. 128, 137 (2007). Indeed, one could make the case that even the first “the,” the one before\n“apportionment of congressional districts,” is unnecessary.\n 11\n\n Case: 19-60133 Document: 00514885572 Page: 12 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\ncontroversial legislative history Defendants rely on—shows why it would have\nbeen so significant and anomalous to require three-judge panels for statutory\nclaims. The statute was first enacted in the aftermath of Ex parte Young to\nrequire three judges to hear what Congress thought would be an increasing\nnumber of suits challenging state laws “upon the ground of the\nunconstitutionality of such statute.” 28 U.S.C. § 2281 (1970); see generally\nDavid P. Currie, The Three-Judge District Court in Constitutional Litigation,\n32 U. CHI. L. REV. 1, 5–8 (1964). When courts later struck down many New\nDeal reforms, one of the only aspects of President Roosevelt’s court-packing\nplan to become law was a measure also requiring three-judge panels for suits\nseeking to enjoin “any Act of Congress for repugnance to the Constitution of\nthe United States.” 28 U.S.C. § 2282 (1970); see Wright, FED. PRAC. & PROC.\n§ 4234, at 194–95. Both laws’ focus on only constitutional challenges made\nsense as striking down democratically enacted laws is “the gravest and most\ndelicate duty” courts are “called on to perform.” Nw. Austin Mun. Util. Dist.\nNo. One v. Holder, 557 U.S. 193, 204 (2009) (referring to striking down an Act\nof Congress (quoting Blodgett v. Holden, 275 U.S. 142, 147–48 (1927) (Holmes,\nJ., concurring))). The idea of requiring three judges for this “class of cases of\nspecial importance” was to “assure more weight and greater deliberation by\nnot leaving the fate of such litigation to a single judge.” Phillips v. United\nStates, 312 U.S. 246, 249–50 (1941) (first quotation from Ex parte Collins, 277\nU.S. 565, 567 (1928)). But in the mid-1970s, Congress decided to scrap just\nabout all of the three-judge regime because it was burdening the Supreme\nCourt and lower courts and had resulted in procedural complexities. See\nWright, FED. PRAC. & PROC. § 4234, at 195–98; Kalson, 542 F.3d at 287 (noting\nthat the 1976 Act “vastly reduced the category of cases for which a three-judge\ncourt is mandated”). It nonetheless decided to retain the procedure for a small\n\n\n 12\n\n Case: 19-60133 Document: 00514885572 Page: 13 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\nset of important cases: constitutional challenges to redistricting for\ncongressional and state legislative seats, then-recent phenomena in the\naftermath of the revolutionary one person, one vote line of cases. See, e.g.,\nReynolds v. Sims, 377 U.S. 533 (1964). If Congress had intended to expand the\nstatute it was otherwise contracting by applying it for the first time to\nstatutory challenges there were certainly better ways to do it than by stealthily\ninserting an extra “the.”\n Reading the statute in the way Defendants suggest does not make sense\nfor another reason: Why would Congress require three judges to hear statutory\nclaims challenging state legislative redistricting but not congressional\nredistricting? The dissent posits, without citing any authority, that perhaps\nfederalism concerns would explain such a difference. But there are also strong\nfederalism concerns with how a state chooses to divvy up its citizens into\ncongressional districts. In fact, contemporary critics of the initial judicial foray\ninto review of legislative apportionment viewed courts’ redrawing of\ncongressional district as even more intrusive on traditional state prerogatives\nthan judicial redrawing of state legislative districts. That is because of the\nview that Article I, Section II of the Constitution grants “States . . . plenary\npower to select their allotted Representatives in accordance with any method\nof popular election they please, subject only to the supervisory power of\nCongress.” Wesberry v. Sanders, 376 U.S. 1, 23 (1964) (Harlan, J., dissenting).\n The other problem with the dissent’s theory—that Congress in 1976 had\na special concern with statutory challenges to the drawing of state legislative\ndistricts—is that it fails to grapple with the rarity of Section 2 challenges to\nredistricting at that time. It was then not even clear that Section 2 provided a\nprivate right of action. City of Mobile v. Bolden, 446 U.S. 55, 60 & n.8 (1980)\n(assuming without deciding such a suit could exist). A few years later the\n\n\n 13\n\n Case: 19-60133 Document: 00514885572 Page: 14 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\nSupreme Court held Section 2 did not prohibit discriminatory effects which\nmeant it provided no guarantee beyond what the Constitution already did. See\nid. And the typical pre-1982 Section 2 claim that courts did consider was a\nchallenge to at-large electoral systems, not the line drawing of single member\ndistricts. See, e.g., id. In other words, there was no practice of statutory\nchallenges to state legislative apportionment that Congress needed to address\nin 1976.\n To sum up, the dissent would give this much weight to the “the” that\ncomes before “reapportionment of any statewide legislative body”: Insertion of\nthat article would require three-judge panels for exclusively statutory claims—\nfollowed by direct appeal to the Supreme Court, 28 U.S.C. § 1253—when the\nthree-judge regime Congress was contracting in 1976 never did. It would\nrequire those three-judge panels only for statutory challenges to\napportionment of state legislative seats, not congressional ones. And it would\ndo all this to address statutory challenges to apportionment of state\nlegislatures when those claims hardly existed in 1976. An elephant indeed.\n The dissent contends that there might have been clearer ways to\nemphasize that the statute is limited to constitutional challenges. Dissenting\nOp. at 12. But if Congress intended to include statutory-only challenges within\nthe reach of the general three-judge statute for the first time, there were many\neasy ways to make that clear. This brings up a final point on the jurisdictional\nquestion. To the extent there is ambiguity, the longstanding principle that\n“congressional enactments providing for the convening of three-judge courts\nmust be strictly construed” comes into play. Allen v. State Bd. of Elections, 393\nU.S. 544, 561 (1969); Phillips, 312 U.S. at 250 (noting the three-judge statue\nshould be read narrowly because of its impact on the Supreme Court docket\nand the burdens of convening three-judge courts).\n\n\n 14\n\n Case: 19-60133 Document: 00514885572 Page: 15 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\n That rule of construction, the text of the three-judge statute, its lineage,\nand the caselaw applying it all favor the district court’s view that three judges\nare not required for a claim raising only statutory challenges to state\nlegislative redistricting. Defendants thus face a steep climb in convincing this\ncourt to be the first to ever read the statute as applying to a case challenging\na district’s lines only under Section Two of the Voting Rights Act.\n IV.\n A.\n Defendants also seek a stay on the ground that we are likely to reverse\nthe district court’s ruling that District 22 dilutes the voting power of African-\nAmericans. The standard of review poses an obstacle to undoing the factual\nfindings that led the court to conclude that the district violates Section 2. An\nappellate court “will not set aside” Section 2 factual findings “unless [it is] left\nwith the definite and firm conviction that a mistake has been committed.”\nMagnolia Bar Ass’n, Inc. v. Lee, 994 F.2d 1143, 1147 (5th Cir. 1993) (quotation\nomitted); see NAACP v. Fordice, 252 F.3d 361, 365 (5th Cir. 2001) (noting that\nclear error review applies).\n In an attempt to avoid the clear-error standard, Defendants frame their\nprimary challenge to liability as a legal one. They contend that a court cannot\nfind vote dilution of a racial group that makes up a majority of the challenged\ndistrict (recall that here that is just barely the case for District 22). This per\nse rule they advocate—a bar on vote dilution claims whenever the racial group\ncrosses the 50% threshold—is at odds with the reason we give such deference\nto factual findings in Section 2 cases: the question of vote dilution is “peculiarly\ndependent upon the facts of each case,” Thornburg v. Gingles, 478 U.S. 30, 79\n(1986) (quoting Nevett v. Sides, 571 F.2d 209, 224 (5th Cir. 1978)), and\n“requires an ‘intensely local appraisal’ of the challenged district,” LULAC, 548\n\n\n 15\n\n Case: 19-60133 Document: 00514885572 Page: 16 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\nU.S. at 437 (quoting Gingles, 478 U.S. at 79). The numerous local factors courts\nconsider—including the strength of bloc voting, demographics, and voter\nturnout—may mean that a minority group has the equal electoral opportunity\nthe Voting Rights Act guarantees when its members make up only 40% of a\ndistrict, but not when they make up 51%. Applying Defendants’ absolute bar\non Section 2 scrutiny of 50%-plus districts to this case shows how it would\narbitrarily override the numerous local considerations that Congress and the\nSupreme Court have said courts need to consider in this important area. If\nthere were a few hundred fewer African-Americans out of the nearly 44,000\nvoting-age citizens in District 22, Defendants would allow courts to engage in\nthe regular multifaceted vote dilution inquiry. But, to Defendants, just over\n300 additional African-Americans makes the difference between that ordinary\ninquiry and removing Section 2’s protections for tens of thousands of\nMississippi voters.\n Given the statutory mandate to focus on the “totality of circumstances”\nin Section 2 cases, 52 U.S.C. § 10301(b), it is not surprising that numerous\ncourts have found dilution of the voting power of a racial group in districts\nwhere they make up a majority of the voting population. Most importantly,\nour court has long rejected the argument Defendants advance. In an early vote\ndilution case—also out of the Mississippi Delta—we explained that the “mere\nexistence of a black population majority does not preclude a finding of dilution.”\nMoore v. Leflore Cty. Bd. of Election Comm’rs, 502 F.2d 621, 624 (5th Cir. 1974).\nWe echoed that more recently, stating that “a protected class that is also a\nregistered voter majority is not foreclosed, as a matter of law, from raising a\nvote dilution claim.” Salas v. Sw. Tex. Jr. Coll. Dist., 964 F.2d 1542, 1550 (5th\nCir. 1992). We have even gone so far so to describe the authority on this point\nas “unimpeachable.” Monroe v. City of Woodville, 881 F.2d 1327, 1333 (5th\n\n\n 16\n\n Case: 19-60133 Document: 00514885572 Page: 17 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\nCir. 1989) (describing the caselaw from our circuit that “has rejected any per\nse rule that a racial minority that is a majority in a political subdivision cannot\nexperience vote dilution”). We are not alone. Many courts of appeals, including\none last year, have rejected the argument that a “racial minority cannot prevail\non a Section 2 claim when it constitutes a bare numerical majority within the\ndistrict.” Mo. St. Conf. of the NAACP v. Ferguson-Florissant Sch. Dist., 894\nF.3d 924, 933 (8th Cir. 2018) (collecting cases from the Second, Fifth, Eleventh,\nand D.C. Circuits).\n Defendants try to distinguish these cases and others by arguing that\nthey addressed at-large elections rather than single-member districts. But\nnothing in these cases turned on that feature. And one court of appeals case\ndirectly confronting the question rejected a bar on vote dilution claims for\ngroups that make up more than 50% of the challenged single-member district.\nKingman Park Civic Ass’n v. Williams, 348 F.3d 1033, 1041 (D.C. Cir. 2003)\n(agreeing with Salas and Moore in a single-member district vote dilution case).\nSo did a recent three-judge panel in this circuit. See Perez v. Abbott, 253 F.\nSupp. 3d 864, 879–90 (W.D. Tex. 2017) (rejecting Defendants’ position when\nfinding vote dilution in a congressional district with a Hispanic voting-age\npopulation of 58.5%).\n Against all this authority of both old and recent vintage, all Defendants\ncan point to is Justice Kennedy’s opinion in Bartlett v. Strickland, 556 U.S. 1\n(2009) (opinion of Kennedy, J.). 6 Here is the statement they contend supports\na categorical rule that there can be no Voting Rights Act violation when a racial\ngroup exceeds 50% of the district’s population: “Where an election district could\n\n\n 6The defendants also cite Jeffers v. Beebe, 895 F. Supp. 2d 920, 932 (E.D. Ark. 2012),\nas an example of a court employing their 50%+ bar on Section 2 claims. Even if they read\nthat case correctly, that holding is no longer good law in its circuit. See Mo. St. Conf. of the\nNAACP, 894 F.3d at 933.\n 17\n\n Case: 19-60133 Document: 00514885572 Page: 18 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\nbe drawn in which minority voters form a majority but such a district is not\ndrawn,” a Section 2 claim is possible. This is an “objective, numerical test.” Id.\nat 18. Assuming this opinion is the controlling one under Marks 7 (Justice\nKennedy wrote for only three judges), it is addressing a different question. He\nwas rejecting the concept of crossover districts and instead would require that\na vote-dilution plaintiff show that a district could be drawn in which the racial\ngroup is a majority. Id. at 15-20. In fact, that is the first showing Gingles\nrequires. LULAC, 548 U.S. at 425 (noting the first “condition[] for establishing\na § 2 violation” is that “the racial group is sufficiently large and geographically\ncompact to constitute a majority in a single-member district” (cleaned up)).\nFrom that requirement it does not follow that vote dilution cannot occur when\nthe protected group already makes up a majority in the contested district. It\nis thus not surprising that no court has read Bartlett to override the widely\naccepted view that the voting strength of a protected group can still be diluted\nwhen that group is a majority of a challenged district. Indeed, if any opinion\nfrom Justice Kennedy addresses the question before us, it is his recognition in\nLULAC that “it may be possible for a citizen voting-age majority to lack real\nelectoral opportunity.” Id. at 428.\n Recognizing this robust caselaw rejecting Defendants’ per se rule\n(including in single-member cases), the dissent relies on an argument the\nDefendants have never made: that there needed to be a finding of cracking or\npacking minority voters. We typically will not consider arguments not\nadvanced by a party. State Indus. Prods. Corp. v. Beta Tech Inc., 575 F.3d 450,\n456 (5th Cir. 2009). That principle makes even more sense in the stay context.\n\n\n 7See Marks v. United States, 430 U.S. 188, 193 (1977) (“When a fragmented Court\ndecides a case and no single rationale explaining the result enjoys the assent of five Justices,\nthe holding of the Court may be viewed as that position taken by those Members who\nconcurred in the judgments on the narrowest grounds.” (quotation omitted)).\n 18\n\n Case: 19-60133 Document: 00514885572 Page: 19 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\nIf a “party is not entitled to a stay as a matter of right” even based on objections\nit raised before the district court and in requesting a stay, Campaign for\nSouthern Equality v. Bryant, 773 F.3d 55 (5th Cir. 2014), it should not be\nentitled to that extraordinary remedy based on arguments the district court\nnever had the chance to consider.\n Even if we could grant a stay based on a challenge to the judgment\nDefendants do not raise, the dissent’s position misses the marks on the merits.\nIt argues that vote dilution can occur in a 50%-plus district only if the dilution\nis the result of cracking or packing minority voters. The terms cracking\n(dividing minority voters among various districts to weaken their strength)\nand packing (concentrating minority voters in one or a small number of\ndistricts where they make up an excessive majority and thus reduce that\ngroup’s influence in other districts) describe gerrymandering techniques. Gill\nv. Whitford, 138 S. Ct. 1916, 1924 (2018) (describing the practice in challenge\nalleging partisan gerrymander); Shaw v. Reno, 509 U.S. 630, 670 (1993)\n(White, J., dissenting) (same in challenge alleging racial gerrymander). They\nexplain why vote dilution is occurring. Gill, 138 S. Ct. at 1931. The terms can\nthus be used to describe types of Section 2 vote dilution claims. See, e.g.,\nVoinovich v. Quilter, 507 U.S. 146, 153 (1993). But the “cracking” or “packing”\ndescription does not result in a different Section 2 test or finding. Whether the\ntheory for dilution is cracking or packing or something else, Section 2 claims\nare evaluated by first looking at the three Gingles factors to determine whether\ndemographics, geography, and voting behavior would allow the creation of a\ndistrict in which the minority group has electoral power. LULAC, 548 U.S. at\n425. If the plaintiffs satisfy that threshold, then a court considers the “totality\nof the circumstances” to determine if “members of a racial group have less\n\n\n\n 19\n\n Case: 19-60133 Document: 00514885572 Page: 20 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\nopportunity than do other members of the electorate.” Id. at 425–26. The\ndistrict court faithfully followed this path. 8\n Although cracking and packing are not official parts of the Section 2\nanalysis, as a matter of arithmetic vote dilution will often exist because of\ncracking or packing. Put another way, minority voting strength is often\nweaker than demographics would allow because those voters have been\ncrammed into one district with a very high minority percentage and thus\ndiluted in other districts (packing) or spread among various districts when they\ncould have formed an electoral majority in at least one (cracking). Indeed, the\ndistrict court’s findings demonstrate cracking occurred here. 9 District 22 has\na BVAP of 50.77% and District 23 has a BVAP of 42.00% when, as the remedy\nadopted by the district court demonstrates, African-Americans could easily\nform sufficient electoral strength to elect their representative of choice in at\nleast one of these two districts.\n The district court correctly focused on the Section 2 factors as prescribed\nby the Supreme Court and the Voting Rights Act. Part of the reason it found\nthat the <51% majority of African-American voters in the district did not result\nin an ability to elect a representative of that group’s choosing was because of\nturnout in off-year elections. So the “50%-plus” issue is largely an attempt to\npackage Defendants’ challenge to the factual finding in a more favorable\nstandard of review. But as with any other factual finding, the clearly\n\n\n 8 It is thus not true that the district court thought that “simply because a district can\n\nbe drawn in a way that will guarantee a minority an election win, the Voting Rights Act\ncompels that such a district be drawn.” Dissenting Op. at 7–8. The district court considered\nall of the statutorily prescribed factors in finding vote dilution. The dissent is also wrong in\nsaying that the district court thought a 62% African-American district was required. See id.\nThat is just the demographics of the remedy it adopted that changed only 28 precincts. To\nsay that the court thought that percentage was a requirement is to say that any time a\ndistrict court remedies a Section 2 violation it is creating a new minimum.\n9 There was no need to use the cracking label because Defendants never made the argument\n\nthe dissent advances.\n 20\n\n Case: 19-60133 Document: 00514885572 Page: 21 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\nerroneous standard means it is unlikely to be disturbed on appeal. That is\nparticularly true when the factfinder gives a sound reason for crediting one\nside’s evidence over the other’s. The district court did that in explaining why\nit relied on Plaintiffs’ expert for turnout data rather than Census Bureau\nfigures. The Census Bureau’s election data is for even-year elections, while\nMississippi conducts odd-year state senate elections.\n Defendants have not shown a high likelihood of overturning the finding\nof vote dilution because their legal argument is at odds with “unimpeachable\nauthority” from our court and their factual challenges must overcome\ndeferential standards of review.\n B.\n\n Defendants also argue that the district court erred by not dismissing the\nlawsuit on laches grounds, focusing entirely on Thomas’s delay in bringing this\nlawsuit. Even if he were the only plaintiff, the standard of review would again\npose a substantial obstacle for Defendants to overcome on appeal. A district\ncourt’s equitable ruling on laches is reviewed for abuse of discretion, and the\nfactual findings of delay, inexcusability, and prejudice that underlie it are\nreviewed for clear error. See Retractable Tech., Inc. v. Becton Dickinson & Co.,\n842 F.3d 883, 898 (5th Cir. 2016).\n More problematic than that for Defendants, Thomas is not the only\nperson who brought this suit. The stay motion makes no argument for why\nlaches should bar the lawsuit as to Plaintiffs Ayers and Lawson. As with all\naffirmative defenses, the party asserting a laches defense bears the burden of\nproving it. See City of El Paso, Tex. v. El Paso Entm’t, Inc., 382 F. App’x 361,\n366 (5th Cir. 2010). Defendants did not even attempt to meet this burden for\nAyers and Lawson. Nor is there, despite the dissent’s attempt to salvage a\nlaches defense, an exception for the “main plaintiff,” whatever that means. Cf.\n\n 21\n\n Case: 19-60133 Document: 00514885572 Page: 22 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\nMassachusetts v. EPA, 549 U.S. 497, 518 (2007) (observing that only one\npetitioner needed to have standing to bring suit). The Voting Rights Act\nprotects the rights of voters, not politicians. As to voters Ayers and Lawson,\nDefendants point to nothing showing that a laches defense is likely to succeed\non appeal.\n V.\n A.\n The final ground on which Defendants seek a stay is the remedy the\ndistrict court ordered. The standard of review again poses a challenge: the\ndistrict court’s remedy is reviewed for abuse of discretion. Rodriguez v. Bexar\nCnty., Tex., 385 F.3d 853, 870 (5th Cir. 2004).\n But “whenever practicable . . . a reasonable opportunity [should be\nafforded] the legislature to meet constitutional requirements by adopting a\nsubstituted measure rather than for the federal court to devise and order into\neffect its own plan.” Veasey, 830 F.3d at 270 (quoting Wise v. Lipscomb, 437\nU.S. 535, 540 (1978) (opinion of White, J.)) (emphasis original). As recounted\nabove, the district court first honored this principle in noting it would allow\ntime for a legislative fix before it would redraw the district. When the court\nwas informed that the legislature would not act until it saw the outcome of the\nstay requests, the district court went ahead and redrew the lines given\nconcerns about the candidate qualifying deadline. It noted, however, that the\nlegislature always has the ability to redraw districts. Plaintiffs also point this\nout in their response to the stay motion.\n The legislature’s desire to wait to see the outcome of the stay ruling is\nunderstandable. It would have been inefficient for it to remedy a violation only\nto have this court grant a stay of the district court’s entire judgment on the\nground that Defendants were likely to overturn the finding of vote dilution.\n\n\n 22\n\n Case: 19-60133 Document: 00514885572 Page: 23 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\nBut now that we have concluded to the contrary, the legislature should have\nthe initial opportunity to draw new lines for District 22 that comply with the\nVoting Rights Act. The only reason not to give it that first shot at crafting a\nremedy is the candidate filing deadline, but the Secretary of State is requesting\nthe legislative fix and has not indicated that a further extension of that\ndeadline for the affected districts is problematic. And while the legislature is\nalways able to redraw lines, the remedial preference is for it to have the first\nchance to remedy a Section 2 violation, not for it to act only after the court\ndraws a new district, which would result in three different districts in a short\ntime period. United States v. Brown, 561 F.3d 420, 435 (5th Cir. 2009).\n We thus issued an order on March 15 granting a temporary stay to allow\nthe legislature until April 3 to remedy the Section 2 violation. The order also\nextended the candidate filing deadline for any affected districts until April 12.\n B.\n Defendants otherwise are not likely to surmount the abuse of discretion\nstandard in challenging the court’s remedy. If the legislature does not act and\nthe judicial remedy goes into effect, it must still respect the legislature’s policy\nobjectives as much as possible. See Perry v. Perez, 565 U.S. 38, 393 (2012). The\nremedy is a narrowly-tailored one that does that. While redistricting cases\noften result in redrawing the entire state or at least several districts, this\nremedy moves just 28 precincts, less than 2% of the precincts in the state. The\nremedy affects only 2 of Mississippi’s 52 Senate districts. The court found that\nthe new lines met traditional redistricting criteria: compactness, contiguity,\npreservation of political subdivisions like counties and cities, and avoiding\npairing incumbents. It adopted the proposed map of an expert it found credible\nwho also determined that the new map honored traditional criteria of\ncompactness and contiguity. In fact, the new district is more consistent with\n\n\n 23\n\n Case: 19-60133 Document: 00514885572 Page: 24 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\ntraditional geographic divisions in one important respect: it removes the\nsuburban Madison county precincts and thus limits the district to counties in\nthe rural and agricultural Delta.\n The slightly altered districts are, if anything, also more compact than\nthey were before. The following map of the new and old districts show the\nlimited impact of the court’s remedy. The orange and pink highlighting shows\nthe new districts; the blue lines show the old ones.\n\n\n\n\n 24\n\n Case: 19-60133 Document: 00514885572 Page: 25 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\n Defendants’ main critique is that the new lines split Vicksburg between\nthe districts. But some splitting of counties or cities is inevitable given equal\npopulation requirements. A look at the statewide senate districts reveals this.\nThe lines the legislature drew split at least eight cities with populations\nbetween 23,000 and 27,000 residents (Vicksburg had a population of 26,407\nwhen the 2012 maps were drawn) into different senate districts, including\nClinton, whose 25,216 citizens are split among 5 districts. Having to split\nVicksburg thus does not lack fidelity to the legislature’s redistricting policy\nwhich often results in the same situation. Defendants have not demonstrated\na high likelihood of showing that that district court’s narrow redraw was an\nabuse of discretion.\n C.\n The dissent also contends that the district court’s remedy interferes with\nongoing election preparation, though the Defendants—including the Secretary\nof State—do not cite this as a reason for a stay. In a recent case denying a stay\nin a voting rights case, we did not consider this issue when government officials\ndid not argue that the district court’s plan would substantially disturb the\nelection process. Patino v. City of Pasadena, 677 F. App’x 950, 951–52 (5th Cir.\n2017).\n The election is even further away in this case than it was in Patino. Id.\n(denying stay sought during the candidate registration period with election\nthree months away); see also Patino v. City of Pasadena, 229 F. Supp. 3d 582,\n585 (S.D. Tex. 2017) (providing the relevant dates). Primary voting is more\nthan four months away; the general election is more than seven months away.\nThat distance to the election means the potential for voter confusion that\n\n\n\n\n 25\n\n Case: 19-60133 Document: 00514885572 Page: 26 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\nanimates this concern, Purcell v. Gonzalez, 549 U.S. 1, 4 (2006), is absent. 10\nMississippi voters in the 28 affected precincts will go to the same voting\nlocation they always have, face the same voting requirements, and have\nmonths to research the candidates in advance of the election. Indeed, the effect\nof redrawing some of the lines for just two state senate districts with elections\nmonths away pales in comparison to the impact of statewide redistricting that\nhas been implemented in a similar timeframe. See, e.g., Covington v. North\nCarolina, 2018 WL 604732 (M.D. N.C. 2018); Common Cause v. Rucho, 284 F.\nSupp. 3d 780 (M.D. N.C. 2018); Larios v. Cox, 305 F. Supp. 2d 1335 (N.D. Ga.\n2004).\n With no risk of voter confusion, and no outcry from state officials that\nimplementing the district court’s remedy substantially disturbs its election\nprocess, this is not a basis for a stay.\n D.\n One final comment is necessary to set the record straight in response to\nthe dissent’s attack on the remedy. It irresponsibly insinuates that the district\njudge—whom it takes the unusual step of repeatedly naming—drew new lines\nwith the aim of eliminating partisan opposition to Plaintiff Thomas. That is\nnot true. Importantly, the incumbent state senator in District 22 had decided\nnot to run for reelection before the district court ruled in this case. The\ndissent’s conjecture also ignores that primary candidates file with the political\nparty (not the state), with the parties notifying state officials of the candidates\n\n\n 10 As most of the cases cited by the dissent show, the voter confusion concern is\ntypically greatest when a court alters election procedures (as opposed to districts) with an\nelection quickly approaching. See Veasey v. Perry, 769 F.3d 890, 892 (5th Cir. 2014) (staying\ndistrict court injunction striking down voter ID laws); Purcell, 549 U.S. at 1 (same); North\nCarolina v. League of Women Voters of N.C., 135 S. Ct. 6 (2014) (staying district court order\nthat changed voter ID requirements, voting hours, voting locations, and voter registration);\nHusted v. Ohio State Conference of NAACP, 135 S. Ct. 42 (2014) (staying district court order\nthat changed voting hours).\n 26\n\n Case: 19-60133 Document: 00514885572 Page: 27 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\nonly after the filing deadline. That had not yet occurred when the court issued\nfinal judgment.\n In light of these circumstances, there is no basis for believing that the\nPlaintiffs’ expert who drew the proposed remedy back in mid-January, or the\ndistrict court that later adopted it, knew who the new candidates would be. No\none brought the names or residences of the candidates to the court’s attention\nprior to its remedy ruling. And the district court issued its remedy before the\ninitial candidate qualifying deadline, so there may have been additional\ncandidates. Not until after the court issued its remedy, in a motion for stay,\ndid Defendants bring to the court’s attention the fact that two candidates\nwould no longer reside in District 22. On learning this, the district court\nlamented that it was not told prior to its ruling. As for the competition in the\nnew district, we do not know who has filed nor who will file prior to the new\nqualifying deadline.\n ***\n Per the order issued last week, the motion for stay is GRANTED IN\nPART and DENIED IN PART. A majority of the panel concludes Defendants\nhave satisfied the stay factors only based on the need to give the legislature\nand Governor an opportunity to remedy the Section 2 violation. A stay is\nentered for that purpose until April 3, 2019. The candidate filing deadline for\nany districts whose lines are redrawn (whether by the legislature, or if it does\nnot act, per the district court’s remedy) is extended to April 12, 2019. The\ndistrict court has jurisdiction to consider any challenges to the adequacy of a\nlegislative remedy.\n\n\n\n\n 27\n\n Case: 19-60133 Document: 00514885572 Page: 28 Date Filed: 03/22/2019\n\n\n\n No. 19-60133\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Joseph THOMAS; Vernon Ayers; Melvin Lawson, Plaintiffs - Appellees v. Phil BRYANT, Governor of the State of Mississippi; Delbert Hosemann, Secretary of State of the State of Mississippi, Both in the Official Capacities of Their Own Offices and in Their Official Capacities as Members of the State Board of Election Commissioners, Defendants - Appellants\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-22\\nOpinion type: majority\\nHas dissenting opinion: Yes\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 19-60133 Document: 00514885572 Page: 1 Date Filed: 03/22/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT United States Court of Appeals\\n Fifth Circuit\\n\\n ___________________ FILED\\n March 22, 2019\\n No. 19-60133 Lyle W. Cayce\\n ___________________ Clerk\\n\\nJOSEPH THOMAS; VERNON AYERS; MELVIN LAWSON,\\n\\n Plaintiffs - Appellees\\n\\nv.\\n\\nPHIL BRYANT, Governor of the State of Mississippi,; DELBERT\\nHOSEMANN, Secretary of State of the State of Mississippi, both in the\\nofficial capacities of their own offices and in their official capacities as\\nmembers of the State Board of Election Commissioners,\\n\\n Defendants - Appellants\\n\\n _______________________\\n\\n Appeal from the United States District Court\\n for the Southern District of Mississippi\\n _______________________\\n\\nBefore DENNIS, CLEMENT, and COSTA, Circuit Judges.\\nGREGG COSTA, Circuit Judge:\\n A district court found that the boundaries for Mississippi State Senate\\nDistrict 22 dilute African-American voting strength and prevent those citizens\\nfrom having the equal opportunity “to participate in the political process and\\nto elect representatives of their choice” that the Voting Rights Act guarantees.\\n52 U.S.C. § 10301(b). To remedy the violation, the district court switched 28\\nprecincts between District 22 and a bordering district. The Governor and\\nSecretary of State seek a stay of the final judgment.\\n\\n Case: 19-60133 Document: 00514885572 Page: 2 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\n I.\\n Most of District 22 lies in the heart of the Mississippi Delta. Those\\nunfamiliar with the state’s geography might think that the Mississippi Delta\\nis in the southern portion of the state that is closer to the mouth of the\\nMississippi River. But the “Delta” refers not to the outlet of that mighty river\\ninto the Gulf of Mexico, but to the alluvial plain between the Mississippi River\\nand the Yazoo River. John M. Barry, RISING TIDE: THE GREAT MISSISSIPPI\\nFLOOD OF 1927 AND HOW IT CHANGED AMERICA 96 (1997). It is located in the\\nnorthwest section of Mississippi and looks like an “elongated diamond.” Id.\\nThe district court recited this colorful description of its boundaries: “The\\nMississippi Delta begins in the lobby of the Peabody Hotel [in Memphis] and\\nends on Catfish Row in Vicksburg.” David L. Cohn, GOD SHAKES CREATION\\n(1935).\\n The sediment that the Mississippi River deposited in this region over the\\nmillennia made Delta soil some of the richest in the world. Barry, supra, at\\n97. And that soil made the Delta one of the leading cotton-producing areas in\\nthe world. One historian compared the influence the Delta once held over\\nglobal cotton prices to the modern influence of Saudi Arabia over oil prices.\\nSven Beckert, EMPIRE OF COTTON: A GLOBAL HISTORY 113 (2014).\\n But before agriculture could prosper in the Delta its forests of hardwood\\ntrees had to be cleared. Slaves were forced to begin that process, and\\nemancipated slaves finished it in the latter part of the nineteenth century.\\nSince that time, African-Americans have been a majority in the Delta. In the\\nearly twentieth century, they made up almost 90% of the region’s population.\\nBarry, supra, at 125 (noting that in 1908 the Delta had “a black population of\\nat least 171,209” and “a white population of 24,137”). The Great Migration to\\n\\n\\n\\n 2\\n\\n Case: 19-60133 Document: 00514885572 Page: 3 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nthe north reduced the African-American percentage, but they remain a\\nsizeable majority in the region.\\n Of course, for most of their time laboring in the Delta, African-Americans\\ncould not vote. The Voting Rights Act changed that. It has resulted in\\nnumerous African-Americans being elected to office in the Delta. Indeed, the\\nState of Mississippi has more African-American elected officials than any other\\nstate. U.S. Census Bureau, STATISTICAL ABSTRACT OF THE UNITED STATES:\\n2011, 258 (130th ed.).\\n But in places like the state legislature, African-Americans have still not\\nachieved political power in Mississippi that comes close to their share of the\\npopulation. This case involves a claim that one state senate district\\ncontributed to that underrepresentation by diluting the voting strength of\\nAfrican-Americans that Delta demographics and geography should otherwise\\nsupport and contributed to that underrepresentation.\\n District 22 includes all or part of five Delta counties: Bolivar,\\nHumphreys, Sharkey, Washington, and Yazoo. It also includes parts of one\\nnon-Delta county: Madison. The addition of the white-majority Madison\\nCounty precincts in the last redistricting reduced the African-American\\npercentage in District 22. Overall the district still has an African-American\\nmajority, but just barely at 50.7%. 1 Without the non-Delta precincts from\\nMadison County, that percentage would be much higher.\\n\\n\\n\\n 1 Plaintiff Thomas told the Department of Justice that the 50.7% figure includes the\\npopulation of the Yazoo City federal prison, the majority of whose inmates he says are\\nAfrican-American. He contended that without including that prison, African-Americans\\nwould not be a majority in the district. It is questionable whether disenfranchised people\\nshould be included in the BVAP (black voting age population) calculation for purposes of the\\nVoting Rights Act. The focus is usually on those eligible to vote, thus the typical requirement\\nin our circuit that the percentage focus on those of voting age who are citizens. See Reyes v.\\nCity of Farmers Branch, Tex., 586 F.3d 1019, 1023 (5th Cir. 2009) (noting that only citizens\\nare included in population calculations).\\n 3\\n\\n Case: 19-60133 Document: 00514885572 Page: 4 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\n The candidate preferred by the black majority did not prevail in the 2015\\nelection. The losing candidate those voters did prefer (Joseph Thomas), along\\nwith two voters (Vernon Ayers and Melvin Lawson), brought this lawsuit in\\n2018 alleging that the district violated of Section 2 of the Voting Rights Act.\\n Last month, the district court held a bench trial and agreed. It concluded\\nthat the threshold Gingles factors for establishing vote dilution existed. The\\nAfrican-American population is “sufficiently large and geographically compact”\\nto constitute a majority with electoral power in the district; that racial group\\nis politically cohesive; but the white population voted as a bloc to prevent\\nAfrican-Americans from electing their chosen candidate. LULAC v. Perry, 548\\nU.S. 399, 425 (2006). The bloc voting by both racial groups was stark: in 10\\nelections within district 22, the candidate favored by African-Americans\\nreceived between 82% and 93% of their vote but only between 8% and 19% of\\nthe white vote.\\n The district court then followed the statutory directive to consider the\\n“totality of circumstances” in determining whether African-Americans “have\\nless opportunity than other members of the electorate to participate in the\\npolitical process and to elect representatives of their choice.” 52 U.S.C.\\n§ 10301(b); LULAC, 548 U.S. at 425–26. It credited Plaintiffs’ expert’s analysis\\nof voter participation as more rigorous and concluded that African-American\\nturnout was depressed in off-year elections—that is, odd-year elections without\\nfederal races—which is when Mississippi elects its legislature. The district\\ncourt also highlighted the persistent representation gap in the Mississippi\\nSenate, as well as substantial socioeconomic differences between black voters\\nand white voters in the district.\\n After finding a Voting Rights Act violation, the court initially declined to\\norder a remedy so “the Mississippi Legislature [could] consider[] whether to\\n\\n\\n 4\\n\\n Case: 19-60133 Document: 00514885572 Page: 5 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nredraw the District and extend the candidate qualification deadline.”\\nAlthough the primary and general elections were months away, the deadline\\nfor candidate filing was March 1.\\n A flurry of procedural moves followed at warp speed. Three days after\\nthe court made its trial findings, the Governor and Secretary of State\\n(Defendants) 2 filed a motion a motion to stay with the district court and also\\nfiled an appeal, arguing that the ruling was an appealable interlocutory\\ninjunction. Less than a week later, they asked this court to stay the district\\ncourt’s ruling. That same day, Plaintiffs asked the court to extend the\\nqualification deadline in District 22 and bordering District 23 (the other\\ndistrict affected by the proposed remedy) by two weeks. Later that day, the\\ndistrict court ordered Defendants to update it on any progress, if any, in\\nlegislative redrawing of District 22.\\n The next day, Defendants filed a brief opposing Plaintiffs’ motion to\\nextend the qualification deadline, in which they stated that they had contacted\\nthe leadership of the legislative chambers. The Senate leaders had said that\\n“should the stay motions pending before [the district court] and the Fifth\\nCircuit be denied, the Senate desire[d] the opportunity to enact a new\\nredistricting plan redrawing Senate District 22.” Late that same day, the\\ndistrict court ruled that, because the legislature was unwilling to act, the first\\nmap drawn by one of Plaintiffs’ experts would be adopted as the boundaries of\\nDistricts 22 and 23. The court also moved the qualification deadline to March\\n\\n\\n\\n\\n 2 The third defendant, Attorney General Jim Hood, did not join these motions or this\\nappeal.\\n 5\\n\\n Case: 19-60133 Document: 00514885572 Page: 6 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\n15 for the two affected senate districts. The court also declined to enter a stay\\nand entered final judgment.\\n The final judgment caused our court to dismiss the appeal of the\\npreliminary ruling. Thomas v. Bryant, 2019 WL 994034 (5th Cir. Feb. 28,\\n2019). But by that time the Defendants had already appealed from the final\\njudgment, and not long after that they sought a stay pending the new appeal,\\nwhich is the motion before this panel. 3\\n This is the effect of the final judgment: It switches some precincts\\nbetween Districts 22 and 23. It extends the candidate filing deadline to March\\n15. In terms of other upcoming deadlines, the primary election is August 6,\\nwith a June 22 deadline to send ballots to troops overseas. The general election\\nis November 5.\\n II.\\n The stay Defendants seek is an extraordinary remedy. Nken v. Holder,\\n556 U.S. 418, 437 (2009) (Kennedy, J., concurring). It is also an equitable one\\ncommitted to this court’s discretion. Id. at 433; Ruiz v. Estelle, 666 F.2d 854,\\n856 & n.4 (5th Cir. 1982). Four factors guide the exercise of our discretion:\\n1) whether the applicant has made a strong showing of likelihood to succeed\\non the merits; 2) whether the movant will be irreparably harmed absent a stay;\\n3) whether issuance of a stay will substantially injure other interested parties;\\nand 4) where the public interest lies. Nken, 556 U.S. at 434. The first two\\nfactors are usually the most important. Id.; ODonnell v. Goodhart, 900 F.3d\\n220, 223 (5th Cir. 2018).\\n In this case, the likelihood of success ends up being dispositive. That is\\nbecause Defendants can establish irreparable harm. A court order preventing\\n\\n\\n 3 Before seeking the stay pending appeal for the second time in our court after entry\\nof final judgment, Defendants also sought a stay in the district court for the second time. The\\ndistrict court denied that motion.\\n 6\\n\\n Case: 19-60133 Document: 00514885572 Page: 7 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nenforcement of a state law, including the drawing of legislative lines,\\nconstitutes that harm. Abbott v. Perez, 138 S. Ct. 2305, 2324 n.17 (2018). And\\nthat injury may be irreparable in light of the meaningful possibility (but not\\ncertainty) that a full appeal cannot be decided in time to provide Defendants\\nrelief before this year’s senate elections. But Plaintiffs face the same risk that\\nthe appellate ruling will prove futile should this court grant a stay. And the\\ninjury they seek to prevent—holding an election under an unlawful plan with\\ndiscriminatory effects—is also, it should go without saying, a serious one.\\nVeasey v. Abbott, 830 F.3d 216, 270 (5th Cir. 2016) (en banc) (“It would be\\nuntenable to permit a law with a discriminatory effect to remain in operation\\nfor that election.”); cf. Reynolds v. Sims, 377 U.S. 533, 585 (1964) (“[I]t would\\nbe the unusual case in which a court would be justified in not taking\\nappropriate action to insure that no further elections are conducted under the\\ninvalid plan.”). So Defendants’ entitlement to a stay turns on whether they\\nhave a strong likelihood of success.\\n III.\\n We will first address Defendants’ attempt to make that showing with a\\njurisdictional argument. They contend that a three-judge court should have\\ndecided this case. The statute says that a “district court of three judges shall\\nbe convened when otherwise required by Act of Congress, or when an action is\\nfiled challenging the constitutionality of the apportionment of congressional\\ndistricts or the apportionment of any statewide legislative body.” 28 U.S.C.\\n§ 2284(a). The Voting Rights Act does not require three-judge courts for\\nSection 2 cases (notably it does for Section 5 cases, 52 U.S.C. § 10304(a)), so\\nDefendants focus on the latter part of the statute. They contend that\\n“constitutionality” modifies only challenges to apportionment of congressional\\ndistricts, not challenges to apportionment of state legislatures. On their\\n\\n\\n 7\\n\\n Case: 19-60133 Document: 00514885572 Page: 8 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nreading, any challenge to state legislative redistricting—including the\\nstatutory Voting Rights Act one asserted here—requires a three-judge panel.\\n Defendants requested a three-judge panel late in the litigation, a week\\nbefore trial. Failing to request such a panel in their answer may have forfeited\\nthe issue unless it is a jurisdictional requirement. The three-judge statute has\\nconflicting language on whether it is one. It begins by saying “a district court\\nof three judges shall be convened” for specified cases. 28 U.S.C. § 2284(a). That\\nmandatory language sounds jurisdictional. So does the statute’s prohibition\\non a single judge taking certain actions, including granting injunctive relief.\\nId. § 2284(b)(3). But the statute also says that the procedure for convening a\\nthree-judge court kicks in “[u]pon the filing of a request for three judges.” Id.\\n§ 2284(b)(1). That does not sound jurisdictional. If the requirement is\\njurisdictional, then the single district judge first assigned the case would\\nseemingly have an obligation to convene a three-judge panel even if a party\\ndoes not ask for it.\\n Recognizing these conflicting statutory signals, the leading federal\\nprocedure treatise is ambivalent about whether Section 2284 is jurisdictional.\\nSee 17A Charles Alan Wright et al., FED. PRAC. & PROC. § 4235, at 206–08 (3d\\ned. 2007). But apparently the courts that have considered the question—\\nincluding ours in a nonbinding decision—have treated Section 2284 as\\njurisdictional. See Kalson v. Patterson, 542 F.3d 281, 287 (2nd Cir. 2008);\\nArmour v. Ohio, 925 F.2d 987, 989 (6th Cir. 1991) (en banc); LULAC of Texas\\nv. Texas, 318 F. App’x 261, 264 (5th Cir. 2009). That consensus in the caselaw\\nmeans that forfeiture is an obstacle Defendants will likely be able to overcome\\non appeal.\\n Defendants’ delay in raising this issue does, however, say something\\nabout its merits. At the outset of this lawsuit, it was not obvious to Defendants\\n\\n\\n 8\\n\\n Case: 19-60133 Document: 00514885572 Page: 9 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\n(or Plaintiffs or the district judge for that matter) that its exclusively statutory\\nclaims required a three-judge court. Indeed, no reported case has ever used a\\nthree-judge panel for a case challenging district lines only under Section 2 of\\nthe Voting Rights Act. See Rural W. Tenn. African-American Affairs Council\\nv. Sundquist, 209 F.3d 835, 838 (6th Cir. 2000) (noting case reassigned to single\\njudge after dismissal of constitutional and Section 5 claims); Chestnut v.\\nMerrill, 2019 WL 338909 (N.D. Ala. 2019) (rejecting argument that a single\\njudge could not hear Section 2 challenge); Bone Shirt v. Hazeltine, 336 F. Supp.\\n2d 976, 980 (D. S.D. 2004) (same as Rural West); Old Person v. Brown, 182 F.\\nSupp. 2d 1002, 1003 (D. Mont. 2002) (single judge hearing Section 2 challenge);\\nsee also Armour, 925 F.2d at 989 (stating the jurisdictional test for Section\\n2284 as whether “there exists a non-frivolous constitutional challenge to the\\napportionment of a statewide legislative body” (emphasis added)). 4 That no\\ncourt has adopted Defendants’ reading of the three-judge statute in the more\\nthan four decades it has been on the books alone seems enough to prevent them\\nfrom showing a strong likelihood of succeeding on this issue. To be sure, only\\nthe Chestnut opinion from earlier this year addressed an argument like the one\\nDefendants make. But that is again telling: Before this year, it apparently had\\nnever dawned on a judge or party in a Section 2-only state redistricting case\\n\\n\\n\\n 4 Though uncited by Defendants or their amicus, the dissent finds Page v. Bartels, 248\\nF.3d 175 (3d Cir. 2001), “most significant[].” Dissenting Op. at 15. But unlike the cases cited\\nabove, Page does not involve a situation in which plaintiffs only brought Section 2 claims.\\nInstead, it involved both constitutional and statutory claims. Yet a single district court judge\\nattempted to spin off the statutory claims and deny an injunction based on them. Id. at 187.\\nThe Third Circuit said that when plaintiffs bring both claims, both must be sent to a three-\\njudge panel. Id. at 191. That is consistent with the common practice when both constitutional\\nand statutory challenges to reapportionment are brought—the constitutional hook for three-\\njudge jurisdiction sweeps in the statutory claims. While the dissent tries to find support for\\nits position in some of Page’s discussion of legislative history and policy, notably the Third\\nCircuit does not adopt the textual argument the dissent and amicus push.\\n\\n\\n 9\\n\\n Case: 19-60133 Document: 00514885572 Page: 10 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nthat a three-judge panel might be required. And that is because the most\\nstraightforward reading of the three-judge statute is that it applies only when\\nthe “constitutionality” of apportionment is being challenged.\\n So why does the dissent, adopting the argument of an amicus, think the\\nthree-judge statute applies to what is only a statutory challenge when no court\\nhas ever taken that view? One word—the “the” that precedes “apportionment\\nof any statewide legislative body.” 28 U.S.C. § 2284(a). Inclusion of that article\\nmeans, in their view, that “constitutionality” applies only to what immediately\\nfollows it: challenges to the “apportionment of congressional districts.” If\\n“constitutionality” does not also modify the “apportionment of any statewide\\nlegislative body,” id., then any challenges to those districts, including statutory\\nones, require a three-judge panel.\\n The textual argument is a dispute about application of the “series\\nmodifier” canon of construction. It normally means that a modifier\\n(“constitutionality” in Section 2284) applies to an entire series of parallel\\nterms. See Scalia & Garner, READING LAW: THE INTERPRETATION OF LEGAL\\nTEXTS 147 (2012). The district court concluded that principle supports reading\\nthe statute as applying to constitutional challenges to apportionment of both\\ncongressional and state legislative seats. But an amicus supporting the\\ndefendants argues the “the” coming before “apportionment of any statewide\\nlegislative body” breaks the series modifier. The amicus notes that a\\n“determiner” word, such as the “the” in Section 2284(a), is an indication that a\\nmodifier should not reach the second element. 5 See id. at 148–49.\\n\\n\\n\\n 5 Defendants make a different textual argument in support of their position that this\\ncase belongs with a three-judge court. They focus not just on the “the,” but on “the\\napportionment” that precedes “of any statewide legislative body.” They contend it is\\nsuperfluous if it does not break off the “constitutionality” modifier. But it may be\\n“appropriate to tolerate a degree of surplusage.” United States v. Atl. Research Corp., 551\\n 10\\n\\n Case: 19-60133 Document: 00514885572 Page: 11 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\n But inferring that “the” was meant to cut off the “constitutionality”\\nmodifier ignores what may be the most important teaching about the series\\nmodifier canon from the Scalia and Garner book on statutory interpretation:\\n“Perhaps more than most of the other canons, this one is highly sensitive to\\ncontext.” Id. at 150. That context supports the natural reading that courts have\\nlong given it: that “constitutionality” modifies both “the apportionment of\\ncongressional districts” and “the apportionment of any statewide legislative\\nbody.” That Congress wanted the two phrases to sound the same—“the\\napportionment of congressional districts” and “the apportionment of any\\nstatewide legislative body” are word-for-word identical, with the exception of\\nthe type of district that they reference—is consistent with how ordinary people\\nspeak and write. See Lockhart v. United States, 136 S. Ct. 958, 970 (2016)\\n(Kagan, J., dissenting). To illustrate this, consider what a reader would think\\nafter seeing the following in the newspaper: “The NCAA is investigating the\\nrecruiting practices of the football program and the basketball program.” As\\nwith the three-judge statute, the final “the” may not be necessary. But would\\nit make the reader think the investigation into the basketball program is not\\nlimited to recruiting violations, but also might include point shaving or ticket\\nscalping violations? Of course not. The dissent’s textual argument about the\\nthree-judge statute is just as detached from common usage.\\n What is more, giving so much significance to “the” runs counter to\\nanother point Justice Scalia made about statutory interpretation: that\\nCongress “does not . . . hide elephants in mouseholes.” Whitman v. Am.\\nTrucking Ass’n, 531 U.S. 457, 468 (2001). The historical development of the\\nthree-judge statute—that is, statutory history as opposed to the more\\n\\n\\n\\nU.S. 128, 137 (2007). Indeed, one could make the case that even the first “the,” the one before\\n“apportionment of congressional districts,” is unnecessary.\\n 11\\n\\n Case: 19-60133 Document: 00514885572 Page: 12 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\ncontroversial legislative history Defendants rely on—shows why it would have\\nbeen so significant and anomalous to require three-judge panels for statutory\\nclaims. The statute was first enacted in the aftermath of Ex parte Young to\\nrequire three judges to hear what Congress thought would be an increasing\\nnumber of suits challenging state laws “upon the ground of the\\nunconstitutionality of such statute.” 28 U.S.C. § 2281 (1970); see generally\\nDavid P. Currie, The Three-Judge District Court in Constitutional Litigation,\\n32 U. CHI. L. REV. 1, 5–8 (1964). When courts later struck down many New\\nDeal reforms, one of the only aspects of President Roosevelt’s court-packing\\nplan to become law was a measure also requiring three-judge panels for suits\\nseeking to enjoin “any Act of Congress for repugnance to the Constitution of\\nthe United States.” 28 U.S.C. § 2282 (1970); see Wright, FED. PRAC. & PROC.\\n§ 4234, at 194–95. Both laws’ focus on only constitutional challenges made\\nsense as striking down democratically enacted laws is “the gravest and most\\ndelicate duty” courts are “called on to perform.” Nw. Austin Mun. Util. Dist.\\nNo. One v. Holder, 557 U.S. 193, 204 (2009) (referring to striking down an Act\\nof Congress (quoting Blodgett v. Holden, 275 U.S. 142, 147–48 (1927) (Holmes,\\nJ., concurring))). The idea of requiring three judges for this “class of cases of\\nspecial importance” was to “assure more weight and greater deliberation by\\nnot leaving the fate of such litigation to a single judge.” Phillips v. United\\nStates, 312 U.S. 246, 249–50 (1941) (first quotation from Ex parte Collins, 277\\nU.S. 565, 567 (1928)). But in the mid-1970s, Congress decided to scrap just\\nabout all of the three-judge regime because it was burdening the Supreme\\nCourt and lower courts and had resulted in procedural complexities. See\\nWright, FED. PRAC. & PROC. § 4234, at 195–98; Kalson, 542 F.3d at 287 (noting\\nthat the 1976 Act “vastly reduced the category of cases for which a three-judge\\ncourt is mandated”). It nonetheless decided to retain the procedure for a small\\n\\n\\n 12\\n\\n Case: 19-60133 Document: 00514885572 Page: 13 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nset of important cases: constitutional challenges to redistricting for\\ncongressional and state legislative seats, then-recent phenomena in the\\naftermath of the revolutionary one person, one vote line of cases. See, e.g.,\\nReynolds v. Sims, 377 U.S. 533 (1964). If Congress had intended to expand the\\nstatute it was otherwise contracting by applying it for the first time to\\nstatutory challenges there were certainly better ways to do it than by stealthily\\ninserting an extra “the.”\\n Reading the statute in the way Defendants suggest does not make sense\\nfor another reason: Why would Congress require three judges to hear statutory\\nclaims challenging state legislative redistricting but not congressional\\nredistricting? The dissent posits, without citing any authority, that perhaps\\nfederalism concerns would explain such a difference. But there are also strong\\nfederalism concerns with how a state chooses to divvy up its citizens into\\ncongressional districts. In fact, contemporary critics of the initial judicial foray\\ninto review of legislative apportionment viewed courts’ redrawing of\\ncongressional district as even more intrusive on traditional state prerogatives\\nthan judicial redrawing of state legislative districts. That is because of the\\nview that Article I, Section II of the Constitution grants “States . . . plenary\\npower to select their allotted Representatives in accordance with any method\\nof popular election they please, subject only to the supervisory power of\\nCongress.” Wesberry v. Sanders, 376 U.S. 1, 23 (1964) (Harlan, J., dissenting).\\n The other problem with the dissent’s theory—that Congress in 1976 had\\na special concern with statutory challenges to the drawing of state legislative\\ndistricts—is that it fails to grapple with the rarity of Section 2 challenges to\\nredistricting at that time. It was then not even clear that Section 2 provided a\\nprivate right of action. City of Mobile v. Bolden, 446 U.S. 55, 60 & n.8 (1980)\\n(assuming without deciding such a suit could exist). A few years later the\\n\\n\\n 13\\n\\n Case: 19-60133 Document: 00514885572 Page: 14 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nSupreme Court held Section 2 did not prohibit discriminatory effects which\\nmeant it provided no guarantee beyond what the Constitution already did. See\\nid. And the typical pre-1982 Section 2 claim that courts did consider was a\\nchallenge to at-large electoral systems, not the line drawing of single member\\ndistricts. See, e.g., id. In other words, there was no practice of statutory\\nchallenges to state legislative apportionment that Congress needed to address\\nin 1976.\\n To sum up, the dissent would give this much weight to the “the” that\\ncomes before “reapportionment of any statewide legislative body”: Insertion of\\nthat article would require three-judge panels for exclusively statutory claims—\\nfollowed by direct appeal to the Supreme Court, 28 U.S.C. § 1253—when the\\nthree-judge regime Congress was contracting in 1976 never did. It would\\nrequire those three-judge panels only for statutory challenges to\\napportionment of state legislative seats, not congressional ones. And it would\\ndo all this to address statutory challenges to apportionment of state\\nlegislatures when those claims hardly existed in 1976. An elephant indeed.\\n The dissent contends that there might have been clearer ways to\\nemphasize that the statute is limited to constitutional challenges. Dissenting\\nOp. at 12. But if Congress intended to include statutory-only challenges within\\nthe reach of the general three-judge statute for the first time, there were many\\neasy ways to make that clear. This brings up a final point on the jurisdictional\\nquestion. To the extent there is ambiguity, the longstanding principle that\\n“congressional enactments providing for the convening of three-judge courts\\nmust be strictly construed” comes into play. Allen v. State Bd. of Elections, 393\\nU.S. 544, 561 (1969); Phillips, 312 U.S. at 250 (noting the three-judge statue\\nshould be read narrowly because of its impact on the Supreme Court docket\\nand the burdens of convening three-judge courts).\\n\\n\\n 14\\n\\n Case: 19-60133 Document: 00514885572 Page: 15 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\n That rule of construction, the text of the three-judge statute, its lineage,\\nand the caselaw applying it all favor the district court’s view that three judges\\nare not required for a claim raising only statutory challenges to state\\nlegislative redistricting. Defendants thus face a steep climb in convincing this\\ncourt to be the first to ever read the statute as applying to a case challenging\\na district’s lines only under Section Two of the Voting Rights Act.\\n IV.\\n A.\\n Defendants also seek a stay on the ground that we are likely to reverse\\nthe district court’s ruling that District 22 dilutes the voting power of African-\\nAmericans. The standard of review poses an obstacle to undoing the factual\\nfindings that led the court to conclude that the district violates Section 2. An\\nappellate court “will not set aside” Section 2 factual findings “unless [it is] left\\nwith the definite and firm conviction that a mistake has been committed.”\\nMagnolia Bar Ass’n, Inc. v. Lee, 994 F.2d 1143, 1147 (5th Cir. 1993) (quotation\\nomitted); see NAACP v. Fordice, 252 F.3d 361, 365 (5th Cir. 2001) (noting that\\nclear error review applies).\\n In an attempt to avoid the clear-error standard, Defendants frame their\\nprimary challenge to liability as a legal one. They contend that a court cannot\\nfind vote dilution of a racial group that makes up a majority of the challenged\\ndistrict (recall that here that is just barely the case for District 22). This per\\nse rule they advocate—a bar on vote dilution claims whenever the racial group\\ncrosses the 50% threshold—is at odds with the reason we give such deference\\nto factual findings in Section 2 cases: the question of vote dilution is “peculiarly\\ndependent upon the facts of each case,” Thornburg v. Gingles, 478 U.S. 30, 79\\n(1986) (quoting Nevett v. Sides, 571 F.2d 209, 224 (5th Cir. 1978)), and\\n“requires an ‘intensely local appraisal’ of the challenged district,” LULAC, 548\\n\\n\\n 15\\n\\n Case: 19-60133 Document: 00514885572 Page: 16 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nU.S. at 437 (quoting Gingles, 478 U.S. at 79). The numerous local factors courts\\nconsider—including the strength of bloc voting, demographics, and voter\\nturnout—may mean that a minority group has the equal electoral opportunity\\nthe Voting Rights Act guarantees when its members make up only 40% of a\\ndistrict, but not when they make up 51%. Applying Defendants’ absolute bar\\non Section 2 scrutiny of 50%-plus districts to this case shows how it would\\narbitrarily override the numerous local considerations that Congress and the\\nSupreme Court have said courts need to consider in this important area. If\\nthere were a few hundred fewer African-Americans out of the nearly 44,000\\nvoting-age citizens in District 22, Defendants would allow courts to engage in\\nthe regular multifaceted vote dilution inquiry. But, to Defendants, just over\\n300 additional African-Americans makes the difference between that ordinary\\ninquiry and removing Section 2’s protections for tens of thousands of\\nMississippi voters.\\n Given the statutory mandate to focus on the “totality of circumstances”\\nin Section 2 cases, 52 U.S.C. § 10301(b), it is not surprising that numerous\\ncourts have found dilution of the voting power of a racial group in districts\\nwhere they make up a majority of the voting population. Most importantly,\\nour court has long rejected the argument Defendants advance. In an early vote\\ndilution case—also out of the Mississippi Delta—we explained that the “mere\\nexistence of a black population majority does not preclude a finding of dilution.”\\nMoore v. Leflore Cty. Bd. of Election Comm’rs, 502 F.2d 621, 624 (5th Cir. 1974).\\nWe echoed that more recently, stating that “a protected class that is also a\\nregistered voter majority is not foreclosed, as a matter of law, from raising a\\nvote dilution claim.” Salas v. Sw. Tex. Jr. Coll. Dist., 964 F.2d 1542, 1550 (5th\\nCir. 1992). We have even gone so far so to describe the authority on this point\\nas “unimpeachable.” Monroe v. City of Woodville, 881 F.2d 1327, 1333 (5th\\n\\n\\n 16\\n\\n Case: 19-60133 Document: 00514885572 Page: 17 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nCir. 1989) (describing the caselaw from our circuit that “has rejected any per\\nse rule that a racial minority that is a majority in a political subdivision cannot\\nexperience vote dilution”). We are not alone. Many courts of appeals, including\\none last year, have rejected the argument that a “racial minority cannot prevail\\non a Section 2 claim when it constitutes a bare numerical majority within the\\ndistrict.” Mo. St. Conf. of the NAACP v. Ferguson-Florissant Sch. Dist., 894\\nF.3d 924, 933 (8th Cir. 2018) (collecting cases from the Second, Fifth, Eleventh,\\nand D.C. Circuits).\\n Defendants try to distinguish these cases and others by arguing that\\nthey addressed at-large elections rather than single-member districts. But\\nnothing in these cases turned on that feature. And one court of appeals case\\ndirectly confronting the question rejected a bar on vote dilution claims for\\ngroups that make up more than 50% of the challenged single-member district.\\nKingman Park Civic Ass’n v. Williams, 348 F.3d 1033, 1041 (D.C. Cir. 2003)\\n(agreeing with Salas and Moore in a single-member district vote dilution case).\\nSo did a recent three-judge panel in this circuit. See Perez v. Abbott, 253 F.\\nSupp. 3d 864, 879–90 (W.D. Tex. 2017) (rejecting Defendants’ position when\\nfinding vote dilution in a congressional district with a Hispanic voting-age\\npopulation of 58.5%).\\n Against all this authority of both old and recent vintage, all Defendants\\ncan point to is Justice Kennedy’s opinion in Bartlett v. Strickland, 556 U.S. 1\\n(2009) (opinion of Kennedy, J.). 6 Here is the statement they contend supports\\na categorical rule that there can be no Voting Rights Act violation when a racial\\ngroup exceeds 50% of the district’s population: “Where an election district could\\n\\n\\n 6The defendants also cite Jeffers v. Beebe, 895 F. Supp. 2d 920, 932 (E.D. Ark. 2012),\\nas an example of a court employing their 50%+ bar on Section 2 claims. Even if they read\\nthat case correctly, that holding is no longer good law in its circuit. See Mo. St. Conf. of the\\nNAACP, 894 F.3d at 933.\\n 17\\n\\n Case: 19-60133 Document: 00514885572 Page: 18 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nbe drawn in which minority voters form a majority but such a district is not\\ndrawn,” a Section 2 claim is possible. This is an “objective, numerical test.” Id.\\nat 18. Assuming this opinion is the controlling one under Marks 7 (Justice\\nKennedy wrote for only three judges), it is addressing a different question. He\\nwas rejecting the concept of crossover districts and instead would require that\\na vote-dilution plaintiff show that a district could be drawn in which the racial\\ngroup is a majority. Id. at 15-20. In fact, that is the first showing Gingles\\nrequires. LULAC, 548 U.S. at 425 (noting the first “condition[] for establishing\\na § 2 violation” is that “the racial group is sufficiently large and geographically\\ncompact to constitute a majority in a single-member district” (cleaned up)).\\nFrom that requirement it does not follow that vote dilution cannot occur when\\nthe protected group already makes up a majority in the contested district. It\\nis thus not surprising that no court has read Bartlett to override the widely\\naccepted view that the voting strength of a protected group can still be diluted\\nwhen that group is a majority of a challenged district. Indeed, if any opinion\\nfrom Justice Kennedy addresses the question before us, it is his recognition in\\nLULAC that “it may be possible for a citizen voting-age majority to lack real\\nelectoral opportunity.” Id. at 428.\\n Recognizing this robust caselaw rejecting Defendants’ per se rule\\n(including in single-member cases), the dissent relies on an argument the\\nDefendants have never made: that there needed to be a finding of cracking or\\npacking minority voters. We typically will not consider arguments not\\nadvanced by a party. State Indus. Prods. Corp. v. Beta Tech Inc., 575 F.3d 450,\\n456 (5th Cir. 2009). That principle makes even more sense in the stay context.\\n\\n\\n 7See Marks v. United States, 430 U.S. 188, 193 (1977) (“When a fragmented Court\\ndecides a case and no single rationale explaining the result enjoys the assent of five Justices,\\nthe holding of the Court may be viewed as that position taken by those Members who\\nconcurred in the judgments on the narrowest grounds.” (quotation omitted)).\\n 18\\n\\n Case: 19-60133 Document: 00514885572 Page: 19 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nIf a “party is not entitled to a stay as a matter of right” even based on objections\\nit raised before the district court and in requesting a stay, Campaign for\\nSouthern Equality v. Bryant, 773 F.3d 55 (5th Cir. 2014), it should not be\\nentitled to that extraordinary remedy based on arguments the district court\\nnever had the chance to consider.\\n Even if we could grant a stay based on a challenge to the judgment\\nDefendants do not raise, the dissent’s position misses the marks on the merits.\\nIt argues that vote dilution can occur in a 50%-plus district only if the dilution\\nis the result of cracking or packing minority voters. The terms cracking\\n(dividing minority voters among various districts to weaken their strength)\\nand packing (concentrating minority voters in one or a small number of\\ndistricts where they make up an excessive majority and thus reduce that\\ngroup’s influence in other districts) describe gerrymandering techniques. Gill\\nv. Whitford, 138 S. Ct. 1916, 1924 (2018) (describing the practice in challenge\\nalleging partisan gerrymander); Shaw v. Reno, 509 U.S. 630, 670 (1993)\\n(White, J., dissenting) (same in challenge alleging racial gerrymander). They\\nexplain why vote dilution is occurring. Gill, 138 S. Ct. at 1931. The terms can\\nthus be used to describe types of Section 2 vote dilution claims. See, e.g.,\\nVoinovich v. Quilter, 507 U.S. 146, 153 (1993). But the “cracking” or “packing”\\ndescription does not result in a different Section 2 test or finding. Whether the\\ntheory for dilution is cracking or packing or something else, Section 2 claims\\nare evaluated by first looking at the three Gingles factors to determine whether\\ndemographics, geography, and voting behavior would allow the creation of a\\ndistrict in which the minority group has electoral power. LULAC, 548 U.S. at\\n425. If the plaintiffs satisfy that threshold, then a court considers the “totality\\nof the circumstances” to determine if “members of a racial group have less\\n\\n\\n\\n 19\\n\\n Case: 19-60133 Document: 00514885572 Page: 20 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nopportunity than do other members of the electorate.” Id. at 425–26. The\\ndistrict court faithfully followed this path. 8\\n Although cracking and packing are not official parts of the Section 2\\nanalysis, as a matter of arithmetic vote dilution will often exist because of\\ncracking or packing. Put another way, minority voting strength is often\\nweaker than demographics would allow because those voters have been\\ncrammed into one district with a very high minority percentage and thus\\ndiluted in other districts (packing) or spread among various districts when they\\ncould have formed an electoral majority in at least one (cracking). Indeed, the\\ndistrict court’s findings demonstrate cracking occurred here. 9 District 22 has\\na BVAP of 50.77% and District 23 has a BVAP of 42.00% when, as the remedy\\nadopted by the district court demonstrates, African-Americans could easily\\nform sufficient electoral strength to elect their representative of choice in at\\nleast one of these two districts.\\n The district court correctly focused on the Section 2 factors as prescribed\\nby the Supreme Court and the Voting Rights Act. Part of the reason it found\\nthat the <51% majority of African-American voters in the district did not result\\nin an ability to elect a representative of that group’s choosing was because of\\nturnout in off-year elections. So the “50%-plus” issue is largely an attempt to\\npackage Defendants’ challenge to the factual finding in a more favorable\\nstandard of review. But as with any other factual finding, the clearly\\n\\n\\n 8 It is thus not true that the district court thought that “simply because a district can\\n\\nbe drawn in a way that will guarantee a minority an election win, the Voting Rights Act\\ncompels that such a district be drawn.” Dissenting Op. at 7–8. The district court considered\\nall of the statutorily prescribed factors in finding vote dilution. The dissent is also wrong in\\nsaying that the district court thought a 62% African-American district was required. See id.\\nThat is just the demographics of the remedy it adopted that changed only 28 precincts. To\\nsay that the court thought that percentage was a requirement is to say that any time a\\ndistrict court remedies a Section 2 violation it is creating a new minimum.\\n9 There was no need to use the cracking label because Defendants never made the argument\\n\\nthe dissent advances.\\n 20\\n\\n Case: 19-60133 Document: 00514885572 Page: 21 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nerroneous standard means it is unlikely to be disturbed on appeal. That is\\nparticularly true when the factfinder gives a sound reason for crediting one\\nside’s evidence over the other’s. The district court did that in explaining why\\nit relied on Plaintiffs’ expert for turnout data rather than Census Bureau\\nfigures. The Census Bureau’s election data is for even-year elections, while\\nMississippi conducts odd-year state senate elections.\\n Defendants have not shown a high likelihood of overturning the finding\\nof vote dilution because their legal argument is at odds with “unimpeachable\\nauthority” from our court and their factual challenges must overcome\\ndeferential standards of review.\\n B.\\n\\n Defendants also argue that the district court erred by not dismissing the\\nlawsuit on laches grounds, focusing entirely on Thomas’s delay in bringing this\\nlawsuit. Even if he were the only plaintiff, the standard of review would again\\npose a substantial obstacle for Defendants to overcome on appeal. A district\\ncourt’s equitable ruling on laches is reviewed for abuse of discretion, and the\\nfactual findings of delay, inexcusability, and prejudice that underlie it are\\nreviewed for clear error. See Retractable Tech., Inc. v. Becton Dickinson & Co.,\\n842 F.3d 883, 898 (5th Cir. 2016).\\n More problematic than that for Defendants, Thomas is not the only\\nperson who brought this suit. The stay motion makes no argument for why\\nlaches should bar the lawsuit as to Plaintiffs Ayers and Lawson. As with all\\naffirmative defenses, the party asserting a laches defense bears the burden of\\nproving it. See City of El Paso, Tex. v. El Paso Entm’t, Inc., 382 F. App’x 361,\\n366 (5th Cir. 2010). Defendants did not even attempt to meet this burden for\\nAyers and Lawson. Nor is there, despite the dissent’s attempt to salvage a\\nlaches defense, an exception for the “main plaintiff,” whatever that means. Cf.\\n\\n 21\\n\\n Case: 19-60133 Document: 00514885572 Page: 22 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nMassachusetts v. EPA, 549 U.S. 497, 518 (2007) (observing that only one\\npetitioner needed to have standing to bring suit). The Voting Rights Act\\nprotects the rights of voters, not politicians. As to voters Ayers and Lawson,\\nDefendants point to nothing showing that a laches defense is likely to succeed\\non appeal.\\n V.\\n A.\\n The final ground on which Defendants seek a stay is the remedy the\\ndistrict court ordered. The standard of review again poses a challenge: the\\ndistrict court’s remedy is reviewed for abuse of discretion. Rodriguez v. Bexar\\nCnty., Tex., 385 F.3d 853, 870 (5th Cir. 2004).\\n But “whenever practicable . . . a reasonable opportunity [should be\\nafforded] the legislature to meet constitutional requirements by adopting a\\nsubstituted measure rather than for the federal court to devise and order into\\neffect its own plan.” Veasey, 830 F.3d at 270 (quoting Wise v. Lipscomb, 437\\nU.S. 535, 540 (1978) (opinion of White, J.)) (emphasis original). As recounted\\nabove, the district court first honored this principle in noting it would allow\\ntime for a legislative fix before it would redraw the district. When the court\\nwas informed that the legislature would not act until it saw the outcome of the\\nstay requests, the district court went ahead and redrew the lines given\\nconcerns about the candidate qualifying deadline. It noted, however, that the\\nlegislature always has the ability to redraw districts. Plaintiffs also point this\\nout in their response to the stay motion.\\n The legislature’s desire to wait to see the outcome of the stay ruling is\\nunderstandable. It would have been inefficient for it to remedy a violation only\\nto have this court grant a stay of the district court’s entire judgment on the\\nground that Defendants were likely to overturn the finding of vote dilution.\\n\\n\\n 22\\n\\n Case: 19-60133 Document: 00514885572 Page: 23 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nBut now that we have concluded to the contrary, the legislature should have\\nthe initial opportunity to draw new lines for District 22 that comply with the\\nVoting Rights Act. The only reason not to give it that first shot at crafting a\\nremedy is the candidate filing deadline, but the Secretary of State is requesting\\nthe legislative fix and has not indicated that a further extension of that\\ndeadline for the affected districts is problematic. And while the legislature is\\nalways able to redraw lines, the remedial preference is for it to have the first\\nchance to remedy a Section 2 violation, not for it to act only after the court\\ndraws a new district, which would result in three different districts in a short\\ntime period. United States v. Brown, 561 F.3d 420, 435 (5th Cir. 2009).\\n We thus issued an order on March 15 granting a temporary stay to allow\\nthe legislature until April 3 to remedy the Section 2 violation. The order also\\nextended the candidate filing deadline for any affected districts until April 12.\\n B.\\n Defendants otherwise are not likely to surmount the abuse of discretion\\nstandard in challenging the court’s remedy. If the legislature does not act and\\nthe judicial remedy goes into effect, it must still respect the legislature’s policy\\nobjectives as much as possible. See Perry v. Perez, 565 U.S. 38, 393 (2012). The\\nremedy is a narrowly-tailored one that does that. While redistricting cases\\noften result in redrawing the entire state or at least several districts, this\\nremedy moves just 28 precincts, less than 2% of the precincts in the state. The\\nremedy affects only 2 of Mississippi’s 52 Senate districts. The court found that\\nthe new lines met traditional redistricting criteria: compactness, contiguity,\\npreservation of political subdivisions like counties and cities, and avoiding\\npairing incumbents. It adopted the proposed map of an expert it found credible\\nwho also determined that the new map honored traditional criteria of\\ncompactness and contiguity. In fact, the new district is more consistent with\\n\\n\\n 23\\n\\n Case: 19-60133 Document: 00514885572 Page: 24 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\ntraditional geographic divisions in one important respect: it removes the\\nsuburban Madison county precincts and thus limits the district to counties in\\nthe rural and agricultural Delta.\\n The slightly altered districts are, if anything, also more compact than\\nthey were before. The following map of the new and old districts show the\\nlimited impact of the court’s remedy. The orange and pink highlighting shows\\nthe new districts; the blue lines show the old ones.\\n\\n\\n\\n\\n 24\\n\\n Case: 19-60133 Document: 00514885572 Page: 25 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\n Defendants’ main critique is that the new lines split Vicksburg between\\nthe districts. But some splitting of counties or cities is inevitable given equal\\npopulation requirements. A look at the statewide senate districts reveals this.\\nThe lines the legislature drew split at least eight cities with populations\\nbetween 23,000 and 27,000 residents (Vicksburg had a population of 26,407\\nwhen the 2012 maps were drawn) into different senate districts, including\\nClinton, whose 25,216 citizens are split among 5 districts. Having to split\\nVicksburg thus does not lack fidelity to the legislature’s redistricting policy\\nwhich often results in the same situation. Defendants have not demonstrated\\na high likelihood of showing that that district court’s narrow redraw was an\\nabuse of discretion.\\n C.\\n The dissent also contends that the district court’s remedy interferes with\\nongoing election preparation, though the Defendants—including the Secretary\\nof State—do not cite this as a reason for a stay. In a recent case denying a stay\\nin a voting rights case, we did not consider this issue when government officials\\ndid not argue that the district court’s plan would substantially disturb the\\nelection process. Patino v. City of Pasadena, 677 F. App’x 950, 951–52 (5th Cir.\\n2017).\\n The election is even further away in this case than it was in Patino. Id.\\n(denying stay sought during the candidate registration period with election\\nthree months away); see also Patino v. City of Pasadena, 229 F. Supp. 3d 582,\\n585 (S.D. Tex. 2017) (providing the relevant dates). Primary voting is more\\nthan four months away; the general election is more than seven months away.\\nThat distance to the election means the potential for voter confusion that\\n\\n\\n\\n\\n 25\\n\\n Case: 19-60133 Document: 00514885572 Page: 26 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nanimates this concern, Purcell v. Gonzalez, 549 U.S. 1, 4 (2006), is absent. 10\\nMississippi voters in the 28 affected precincts will go to the same voting\\nlocation they always have, face the same voting requirements, and have\\nmonths to research the candidates in advance of the election. Indeed, the effect\\nof redrawing some of the lines for just two state senate districts with elections\\nmonths away pales in comparison to the impact of statewide redistricting that\\nhas been implemented in a similar timeframe. See, e.g., Covington v. North\\nCarolina, 2018 WL 604732 (M.D. N.C. 2018); Common Cause v. Rucho, 284 F.\\nSupp. 3d 780 (M.D. N.C. 2018); Larios v. Cox, 305 F. Supp. 2d 1335 (N.D. Ga.\\n2004).\\n With no risk of voter confusion, and no outcry from state officials that\\nimplementing the district court’s remedy substantially disturbs its election\\nprocess, this is not a basis for a stay.\\n D.\\n One final comment is necessary to set the record straight in response to\\nthe dissent’s attack on the remedy. It irresponsibly insinuates that the district\\njudge—whom it takes the unusual step of repeatedly naming—drew new lines\\nwith the aim of eliminating partisan opposition to Plaintiff Thomas. That is\\nnot true. Importantly, the incumbent state senator in District 22 had decided\\nnot to run for reelection before the district court ruled in this case. The\\ndissent’s conjecture also ignores that primary candidates file with the political\\nparty (not the state), with the parties notifying state officials of the candidates\\n\\n\\n 10 As most of the cases cited by the dissent show, the voter confusion concern is\\ntypically greatest when a court alters election procedures (as opposed to districts) with an\\nelection quickly approaching. See Veasey v. Perry, 769 F.3d 890, 892 (5th Cir. 2014) (staying\\ndistrict court injunction striking down voter ID laws); Purcell, 549 U.S. at 1 (same); North\\nCarolina v. League of Women Voters of N.C., 135 S. Ct. 6 (2014) (staying district court order\\nthat changed voter ID requirements, voting hours, voting locations, and voter registration);\\nHusted v. Ohio State Conference of NAACP, 135 S. Ct. 42 (2014) (staying district court order\\nthat changed voting hours).\\n 26\\n\\n Case: 19-60133 Document: 00514885572 Page: 27 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\nonly after the filing deadline. That had not yet occurred when the court issued\\nfinal judgment.\\n In light of these circumstances, there is no basis for believing that the\\nPlaintiffs’ expert who drew the proposed remedy back in mid-January, or the\\ndistrict court that later adopted it, knew who the new candidates would be. No\\none brought the names or residences of the candidates to the court’s attention\\nprior to its remedy ruling. And the district court issued its remedy before the\\ninitial candidate qualifying deadline, so there may have been additional\\ncandidates. Not until after the court issued its remedy, in a motion for stay,\\ndid Defendants bring to the court’s attention the fact that two candidates\\nwould no longer reside in District 22. On learning this, the district court\\nlamented that it was not told prior to its ruling. As for the competition in the\\nnew district, we do not know who has filed nor who will file prior to the new\\nqualifying deadline.\\n ***\\n Per the order issued last week, the motion for stay is GRANTED IN\\nPART and DENIED IN PART. A majority of the panel concludes Defendants\\nhave satisfied the stay factors only based on the need to give the legislature\\nand Governor an opportunity to remedy the Section 2 violation. A stay is\\nentered for that purpose until April 3, 2019. The candidate filing deadline for\\nany districts whose lines are redrawn (whether by the legislature, or if it does\\nnot act, per the district court’s remedy) is extended to April 12, 2019. The\\ndistrict court has jurisdiction to consider any challenges to the adequacy of a\\nlegislative remedy.\\n\\n\\n\\n\\n 27\\n\\n Case: 19-60133 Document: 00514885572 Page: 28 Date Filed: 03/22/2019\\n\\n\\n\\n No. 19-60133\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1098,"cells":{"id":{"kind":"number","value":4603529,"string":"4,603,529"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"Joseph Thomas v. Phil Bryant"},"decision_date":{"kind":"string","value":"2019-03-25"},"docket_number":{"kind":"string","value":"19-60133"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before DENNIS, CLEMENT, and COSTA, Circuit Judges.\", \"parties\": \"\", \"opinions\": [{\"author\": \"GREGG COSTA, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 19-60133 Document: 00514887045 Page: 1 Date Filed: 03/25/2019\\n\\n\\n\\n\\n REVISED March 25, 2019\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT United States Court of Appeals\\n Fifth Circuit\\n\\n ___________________ FILED\\n March 22, 2019\\n No. 19-60133 Lyle W. Cayce\\n ___________________ Clerk\\n\\nJOSEPH THOMAS; VERNON AYERS; MELVIN LAWSON,\\n\\n Plaintiffs - Appellees\\n\\nv.\\n\\nPHIL BRYANT, Governor of the State of Mississippi,; DELBERT\\nHOSEMANN, Secretary of State of the State of Mississippi, both in the\\nofficial capacities of their own offices and in their official capacities as\\nmembers of the State Board of Election Commissioners,\\n\\n Defendants - Appellants\\n\\n _______________________\\n\\n Appeal from the United States District Court\\n for the Southern District of Mississippi\\n _______________________\\n\\nBefore DENNIS, CLEMENT, and COSTA, Circuit Judges.\\nGREGG COSTA, Circuit Judge:\\n A district court found that the boundaries for Mississippi State Senate\\nDistrict 22 dilute African-American voting strength and prevent those citizens\\nfrom having the equal opportunity “to participate in the political process and\\nto elect representatives of their choice” that the Voting Rights Act guarantees.\\n52 U.S.C. § 10301(b). To remedy the violation, the district court switched 28\\n\\n Case: 19-60133 Document: 00514887045 Page: 2 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nprecincts between District 22 and a bordering district. The Governor and\\nSecretary of State seek a stay of the final judgment.\\n I.\\n Most of District 22 lies in the heart of the Mississippi Delta. Those\\nunfamiliar with the state’s geography might think that the Mississippi Delta\\nis in the southern portion of the state that is closer to the mouth of the\\nMississippi River. But the “Delta” refers not to the outlet of that mighty river\\ninto the Gulf of Mexico, but to the alluvial plain between the Mississippi River\\nand the Yazoo River. John M. Barry, RISING TIDE: THE GREAT MISSISSIPPI\\nFLOOD OF 1927 AND HOW IT CHANGED AMERICA 96 (1997). It is located in the\\nnorthwest section of Mississippi and looks like an “elongated diamond.” Id.\\nThe district court recited this colorful description of its boundaries: “The\\nMississippi Delta begins in the lobby of the Peabody Hotel [in Memphis] and\\nends on Catfish Row in Vicksburg.” David L. Cohn, GOD SHAKES CREATION\\n(1935).\\n The sediment that the Mississippi River deposited in this region over the\\nmillennia made Delta soil some of the richest in the world. Barry, supra, at\\n97. And that soil made the Delta one of the leading cotton-producing areas in\\nthe world. One historian compared the influence the Delta once held over\\nglobal cotton prices to the modern influence of Saudi Arabia over oil prices.\\nSven Beckert, EMPIRE OF COTTON: A GLOBAL HISTORY 113 (2014).\\n But before agriculture could prosper in the Delta its forests of hardwood\\ntrees had to be cleared. Slaves were forced to begin that process, and\\nemancipated slaves finished it in the latter part of the nineteenth century.\\nSince that time, African-Americans have been a majority in the Delta. In the\\nearly twentieth century, they made up almost 90% of the region’s population.\\nBarry, supra, at 125 (noting that in 1908 the Delta had “a black population of\\n\\n\\n 2\\n\\n Case: 19-60133 Document: 00514887045 Page: 3 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nat least 171,209” and “a white population of 24,137”). The Great Migration to\\nthe north reduced the African-American percentage, but they remain a\\nsizeable majority in the region.\\n Of course, for most of their time laboring in the Delta, African-Americans\\ncould not vote. The Voting Rights Act changed that. It has resulted in\\nnumerous African-Americans being elected to office in the Delta. Indeed, the\\nState of Mississippi has more African-American elected officials than any other\\nstate. U.S. Census Bureau, STATISTICAL ABSTRACT OF THE UNITED STATES:\\n2011, 258 (130th ed.).\\n But in places like the state legislature, African-Americans have still not\\nachieved political power in Mississippi that comes close to their share of the\\npopulation. This case involves a claim that one state senate district\\ncontributed to that underrepresentation by diluting the voting strength of\\nAfrican-Americans that Delta demographics and geography should otherwise\\nsupport.\\n District 22 includes all or part of five Delta counties: Bolivar,\\nHumphreys, Sharkey, Washington, and Yazoo. It also includes parts of one\\nnon-Delta county: Madison. The addition of the white-majority Madison\\nCounty precincts in the last redistricting reduced the African-American\\npercentage in District 22. Overall the district still has an African-American\\nmajority, but just barely at 50.7%. 1 Without the non-Delta precincts from\\n\\n\\n\\n 1 Plaintiff Thomas told the Department of Justice that the 50.7% figure includes the\\npopulation of the Yazoo City federal prison, the majority of whose inmates he says are\\nAfrican-American. He contended that without including that prison, African-Americans\\nwould not be a majority in the district. It is questionable whether disenfranchised people\\nshould be included in the BVAP (black voting age population) calculation for purposes of the\\nVoting Rights Act. The focus is usually on those eligible to vote, thus the typical requirement\\nin our circuit that the percentage focus on those of voting age who are citizens. See Reyes v.\\nCity of Farmers Branch, Tex., 586 F.3d 1019, 1023 (5th Cir. 2009) (noting that only citizens\\nare included in population calculations).\\n 3\\n\\n Case: 19-60133 Document: 00514887045 Page: 4 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nMadison County, that percentage would be much higher.\\n The candidate preferred by the black majority did not prevail in the 2015\\nelection. The losing candidate those voters did prefer (Joseph Thomas), along\\nwith two voters (Vernon Ayers and Melvin Lawson), brought this lawsuit in\\n2018 alleging that the district violated of Section 2 of the Voting Rights Act.\\n Last month, the district court held a bench trial and agreed. It concluded\\nthat the threshold Gingles factors for establishing vote dilution existed. The\\nAfrican-American population is “sufficiently large and geographically compact”\\nto constitute a majority with electoral power in the district; that racial group\\nis politically cohesive; but the white population voted as a bloc to prevent\\nAfrican-Americans from electing their chosen candidate. LULAC v. Perry, 548\\nU.S. 399, 425 (2006). The bloc voting by both racial groups was stark: in 10\\nelections within district 22, the candidate favored by African-Americans\\nreceived between 82% and 93% of their vote but only between 8% and 19% of\\nthe white vote.\\n The district court then followed the statutory directive to consider the\\n“totality of circumstances” in determining whether African-Americans “have\\nless opportunity than other members of the electorate to participate in the\\npolitical process and to elect representatives of their choice.” 52 U.S.C.\\n§ 10301(b); LULAC, 548 U.S. at 425–26. It credited Plaintiffs’ expert’s analysis\\nof voter participation as more rigorous and concluded that African-American\\nturnout was depressed in off-year elections—that is, odd-year elections without\\nfederal races—which is when Mississippi elects its legislature. The district\\ncourt also highlighted the persistent representation gap in the Mississippi\\nSenate, as well as substantial socioeconomic differences between black voters\\nand white voters in the district.\\n After finding a Voting Rights Act violation, the court initially declined to\\n\\n\\n 4\\n\\n Case: 19-60133 Document: 00514887045 Page: 5 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\norder a remedy so “the Mississippi Legislature [could] consider[] whether to\\nredraw the District and extend the candidate qualification deadline.”\\nAlthough the primary and general elections were months away, the deadline\\nfor candidate filing was March 1.\\n A flurry of procedural moves followed at warp speed. Three days after\\nthe court made its trial findings, the Governor and Secretary of State\\n(Defendants) 2 filed a motion a motion to stay with the district court and also\\nfiled an appeal, arguing that the ruling was an appealable interlocutory\\ninjunction. Less than a week later, they asked this court to stay the district\\ncourt’s ruling. That same day, Plaintiffs asked the court to extend the\\nqualification deadline in District 22 and bordering District 23 (the other\\ndistrict affected by the proposed remedy) by two weeks. Later that day, the\\ndistrict court ordered Defendants to update it on any progress, if any, in\\nlegislative redrawing of District 22.\\n The next day, Defendants filed a brief opposing Plaintiffs’ motion to\\nextend the qualification deadline, in which they stated that they had contacted\\nthe leadership of the legislative chambers. The Senate leaders had said that\\n“should the stay motions pending before [the district court] and the Fifth\\nCircuit be denied, the Senate desire[d] the opportunity to enact a new\\nredistricting plan redrawing Senate District 22.” Late that same day, the\\ndistrict court ruled that, because the legislature was unwilling to act, the first\\nmap drawn by one of Plaintiffs’ experts would be adopted as the boundaries of\\nDistricts 22 and 23. The court also moved the qualification deadline to March\\n\\n\\n\\n\\n 2 The third defendant, Attorney General Jim Hood, did not join these motions or this\\nappeal.\\n 5\\n\\n Case: 19-60133 Document: 00514887045 Page: 6 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\n15 for the two affected senate districts. The court also declined to enter a stay\\nand entered final judgment.\\n The final judgment caused our court to dismiss the appeal of the\\npreliminary ruling. Thomas v. Bryant, 2019 WL 994034 (5th Cir. Feb. 28,\\n2019). But by that time the Defendants had already appealed from the final\\njudgment, and not long after that they sought a stay pending the new appeal,\\nwhich is the motion before this panel. 3\\n This is the effect of the final judgment: It switches some precincts\\nbetween Districts 22 and 23. It extends the candidate filing deadline to March\\n15. In terms of other upcoming deadlines, the primary election is August 6,\\nwith a June 22 deadline to send ballots to troops overseas. The general election\\nis November 5.\\n II.\\n The stay Defendants seek is an extraordinary remedy. Nken v. Holder,\\n556 U.S. 418, 437 (2009) (Kennedy, J., concurring). It is also an equitable one\\ncommitted to this court’s discretion. Id. at 433; Ruiz v. Estelle, 666 F.2d 854,\\n856 & n.4 (5th Cir. 1982). Four factors guide the exercise of our discretion:\\n1) whether the applicant has made a strong showing of likelihood to succeed\\non the merits; 2) whether the movant will be irreparably harmed absent a stay;\\n3) whether issuance of a stay will substantially injure other interested parties;\\nand 4) where the public interest lies. Nken, 556 U.S. at 434. The first two\\nfactors are usually the most important. Id.; ODonnell v. Goodhart, 900 F.3d\\n220, 223 (5th Cir. 2018).\\n In this case, the likelihood of success ends up being dispositive. That is\\nbecause Defendants can establish irreparable harm. A court order preventing\\n\\n\\n 3 Before seeking the stay pending appeal for the second time in our court after entry\\nof final judgment, Defendants also sought a stay in the district court for the second time. The\\ndistrict court denied that motion.\\n 6\\n\\n Case: 19-60133 Document: 00514887045 Page: 7 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nenforcement of a state law, including the drawing of legislative lines,\\nconstitutes that harm. Abbott v. Perez, 138 S. Ct. 2305, 2324 n.17 (2018). And\\nthat injury may be irreparable in light of the meaningful possibility (but not\\ncertainty) that a full appeal cannot be decided in time to provide Defendants\\nrelief before this year’s senate elections. But Plaintiffs face the same risk that\\nthe appellate ruling will prove futile should this court grant a stay. And the\\ninjury they seek to prevent—holding an election under an unlawful plan with\\ndiscriminatory effects—is also, it should go without saying, a serious one.\\nVeasey v. Abbott, 830 F.3d 216, 270 (5th Cir. 2016) (en banc) (“It would be\\nuntenable to permit a law with a discriminatory effect to remain in operation\\nfor that election.”); cf. Reynolds v. Sims, 377 U.S. 533, 585 (1964) (“[I]t would\\nbe the unusual case in which a court would be justified in not taking\\nappropriate action to insure that no further elections are conducted under the\\ninvalid plan.”). So Defendants’ entitlement to a stay turns on whether they\\nhave a strong likelihood of success.\\n III.\\n We will first address Defendants’ attempt to make that showing with a\\njurisdictional argument. They contend that a three-judge court should have\\ndecided this case. The statute says that a “district court of three judges shall\\nbe convened when otherwise required by Act of Congress, or when an action is\\nfiled challenging the constitutionality of the apportionment of congressional\\ndistricts or the apportionment of any statewide legislative body.” 28 U.S.C.\\n§ 2284(a). The Voting Rights Act does not require three-judge courts for\\nSection 2 cases (notably it does for Section 5 cases, 52 U.S.C. § 10304(a)), so\\nDefendants focus on the latter part of the statute. They contend that\\n“constitutionality” modifies only challenges to apportionment of congressional\\ndistricts, not challenges to apportionment of state legislatures. On their\\n\\n\\n 7\\n\\n Case: 19-60133 Document: 00514887045 Page: 8 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nreading, any challenge to state legislative redistricting—including the\\nstatutory Voting Rights Act one asserted here—requires a three-judge panel.\\n Defendants requested a three-judge panel late in the litigation, a week\\nbefore trial. Failing to request such a panel in their answer may have forfeited\\nthe issue unless it is a jurisdictional requirement. The three-judge statute has\\nconflicting language on whether it is one. It begins by saying “a district court\\nof three judges shall be convened” for specified cases. 28 U.S.C. § 2284(a). That\\nmandatory language sounds jurisdictional. So does the statute’s prohibition\\non a single judge taking certain actions, including granting injunctive relief.\\nId. § 2284(b)(3). But the statute also says that the procedure for convening a\\nthree-judge court kicks in “[u]pon the filing of a request for three judges.” Id.\\n§ 2284(b)(1). That does not sound jurisdictional. If the requirement is\\njurisdictional, then the single district judge first assigned the case would\\nseemingly have an obligation to convene a three-judge panel even if a party\\ndoes not ask for it.\\n Recognizing these conflicting statutory signals, the leading federal\\nprocedure treatise is ambivalent about whether Section 2284 is jurisdictional.\\nSee 17A Charles Alan Wright et al., FED. PRAC. & PROC. § 4235, at 206–08 (3d\\ned. 2007). But apparently the courts that have considered the question—\\nincluding ours in a nonbinding decision—have treated Section 2284 as\\njurisdictional. See Kalson v. Patterson, 542 F.3d 281, 287 (2nd Cir. 2008);\\nArmour v. Ohio, 925 F.2d 987, 989 (6th Cir. 1991) (en banc); LULAC of Texas\\nv. Texas, 318 F. App’x 261, 264 (5th Cir. 2009). That consensus in the caselaw\\nmeans that forfeiture is an obstacle Defendants will likely be able to overcome\\non appeal.\\n Defendants’ delay in raising this issue does, however, say something\\nabout its merits. At the outset of this lawsuit, it was not obvious to Defendants\\n\\n\\n 8\\n\\n Case: 19-60133 Document: 00514887045 Page: 9 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\n(or Plaintiffs or the district judge for that matter) that its exclusively statutory\\nclaims required a three-judge court. Indeed, no reported case has ever used a\\nthree-judge panel for a case challenging district lines only under Section 2 of\\nthe Voting Rights Act. See Rural W. Tenn. African-American Affairs Council\\nv. Sundquist, 209 F.3d 835, 838 (6th Cir. 2000) (noting case reassigned to single\\njudge after dismissal of constitutional and Section 5 claims); Chestnut v.\\nMerrill, 2019 WL 338909 (N.D. Ala. 2019) (rejecting argument that a single\\njudge could not hear Section 2 challenge); Bone Shirt v. Hazeltine, 336 F. Supp.\\n2d 976, 980 (D. S.D. 2004) (same as Rural West); Old Person v. Brown, 182 F.\\nSupp. 2d 1002, 1003 (D. Mont. 2002) (single judge hearing Section 2 challenge);\\nsee also Armour, 925 F.2d at 989 (stating the jurisdictional test for Section\\n2284 as whether “there exists a non-frivolous constitutional challenge to the\\napportionment of a statewide legislative body” (emphasis added)). 4 That no\\ncourt has adopted Defendants’ reading of the three-judge statute in the more\\nthan four decades it has been on the books alone seems enough to prevent them\\nfrom showing a strong likelihood of succeeding on this issue. To be sure, only\\nthe Chestnut opinion from earlier this year addressed an argument like the one\\nDefendants make. But that is again telling: Before this year, it apparently had\\nnever dawned on a judge or party in a Section 2-only state redistricting case\\n\\n\\n\\n 4 Though uncited by Defendants or their amicus, the dissent finds Page v. Bartels, 248\\nF.3d 175 (3d Cir. 2001), “most significant[].” Dissenting Op. at 15. But unlike the cases cited\\nabove, Page does not involve a situation in which plaintiffs only brought Section 2 claims.\\nInstead, it involved both constitutional and statutory claims. Yet a single district court judge\\nattempted to spin off the statutory claims and deny an injunction based on them. Id. at 187.\\nThe Third Circuit said that when plaintiffs bring both claims, both must be sent to a three-\\njudge panel. Id. at 191. That is consistent with the common practice when both constitutional\\nand statutory challenges to reapportionment are brought—the constitutional hook for three-\\njudge jurisdiction sweeps in the statutory claims. While the dissent tries to find support for\\nits position in some of Page’s discussion of legislative history and policy, notably the Third\\nCircuit does not adopt the textual argument the dissent and amicus push.\\n\\n\\n 9\\n\\n Case: 19-60133 Document: 00514887045 Page: 10 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nthat a three-judge panel might be required. And that is because the most\\nstraightforward reading of the three-judge statute is that it applies only when\\nthe “constitutionality” of apportionment is being challenged.\\n So why does the dissent, adopting the argument of an amicus, think the\\nthree-judge statute applies to what is only a statutory challenge when no court\\nhas ever taken that view? One word—the “the” that precedes “apportionment\\nof any statewide legislative body.” 28 U.S.C. § 2284(a). Inclusion of that article\\nmeans, in their view, that “constitutionality” applies only to what immediately\\nfollows it: challenges to the “apportionment of congressional districts.” If\\n“constitutionality” does not also modify the “apportionment of any statewide\\nlegislative body,” id., then any challenges to those districts, including statutory\\nones, require a three-judge panel.\\n The textual argument is a dispute about application of the “series\\nmodifier” canon of construction. It normally means that a modifier\\n(“constitutionality” in Section 2284) applies to an entire series of parallel\\nterms. See Scalia & Garner, READING LAW: THE INTERPRETATION OF LEGAL\\nTEXTS 147 (2012). The district court concluded that principle supports reading\\nthe statute as applying to constitutional challenges to apportionment of both\\ncongressional and state legislative seats. But an amicus supporting the\\ndefendants argues the “the” coming before “apportionment of any statewide\\nlegislative body” breaks the series modifier. The amicus notes that a\\n“determiner” word, such as the “the” in Section 2284(a), is an indication that a\\nmodifier should not reach the second element. 5 See id. at 148–49.\\n\\n\\n\\n 5 Defendants make a different textual argument in support of their position that this\\ncase belongs with a three-judge court. They focus not just on the “the,” but on “the\\napportionment” that precedes “of any statewide legislative body.” They contend it is\\nsuperfluous if it does not break off the “constitutionality” modifier. But it may be\\n“appropriate to tolerate a degree of surplusage.” United States v. Atl. Research Corp., 551\\n 10\\n\\n Case: 19-60133 Document: 00514887045 Page: 11 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\n But inferring that “the” was meant to cut off the “constitutionality”\\nmodifier ignores what may be the most important teaching about the series\\nmodifier canon from the Scalia and Garner book on statutory interpretation:\\n“Perhaps more than most of the other canons, this one is highly sensitive to\\ncontext.” Id. at 150. That context supports the natural reading that courts have\\nlong given it: that “constitutionality” modifies both “the apportionment of\\ncongressional districts” and “the apportionment of any statewide legislative\\nbody.” That Congress wanted the two phrases to sound the same—“the\\napportionment of congressional districts” and “the apportionment of any\\nstatewide legislative body” are word-for-word identical, with the exception of\\nthe type of district that they reference—is consistent with how ordinary people\\nspeak and write. See Lockhart v. United States, 136 S. Ct. 958, 970 (2016)\\n(Kagan, J., dissenting). To illustrate this, consider what a reader would think\\nafter seeing the following in the newspaper: “The NCAA is investigating the\\nrecruiting practices of the football program and the basketball program.” As\\nwith the three-judge statute, the final “the” may not be necessary. But would\\nit make the reader think the investigation into the basketball program is not\\nlimited to recruiting violations, but also might include point shaving or ticket\\nscalping violations? Of course not. The dissent’s textual argument about the\\nthree-judge statute is just as detached from common usage.\\n What is more, giving so much significance to “the” runs counter to\\nanother point Justice Scalia made about statutory interpretation: that\\nCongress “does not . . . hide elephants in mouseholes.” Whitman v. Am.\\nTrucking Ass’n, 531 U.S. 457, 468 (2001). The historical development of the\\nthree-judge statute—that is, statutory history as opposed to the more\\n\\n\\n\\nU.S. 128, 137 (2007). Indeed, one could make the case that even the first “the,” the one before\\n“apportionment of congressional districts,” is unnecessary.\\n 11\\n\\n Case: 19-60133 Document: 00514887045 Page: 12 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\ncontroversial legislative history Defendants rely on—shows why it would have\\nbeen so significant and anomalous to require three-judge panels for statutory\\nclaims. The statute was first enacted in the aftermath of Ex parte Young to\\nrequire three judges to hear what Congress thought would be an increasing\\nnumber of suits challenging state laws “upon the ground of the\\nunconstitutionality of such statute.” 28 U.S.C. § 2281 (1970); see generally\\nDavid P. Currie, The Three-Judge District Court in Constitutional Litigation,\\n32 U. CHI. L. REV. 1, 5–8 (1964). When courts later struck down many New\\nDeal reforms, one of the only aspects of President Roosevelt’s court-packing\\nplan to become law was a measure also requiring three-judge panels for suits\\nseeking to enjoin “any Act of Congress for repugnance to the Constitution of\\nthe United States.” 28 U.S.C. § 2282 (1970); see Wright, FED. PRAC. & PROC.\\n§ 4234, at 194–95. Both laws’ focus on only constitutional challenges made\\nsense as striking down democratically enacted laws is “the gravest and most\\ndelicate duty” courts are “called on to perform.” Nw. Austin Mun. Util. Dist.\\nNo. One v. Holder, 557 U.S. 193, 204 (2009) (referring to striking down an Act\\nof Congress (quoting Blodgett v. Holden, 275 U.S. 142, 147–48 (1927) (Holmes,\\nJ., concurring))). The idea of requiring three judges for this “class of cases of\\nspecial importance” was to “assure more weight and greater deliberation by\\nnot leaving the fate of such litigation to a single judge.” Phillips v. United\\nStates, 312 U.S. 246, 249–50 (1941) (first quotation from Ex parte Collins, 277\\nU.S. 565, 567 (1928)). But in the mid-1970s, Congress decided to scrap just\\nabout all of the three-judge regime because it was burdening the Supreme\\nCourt and lower courts and had resulted in procedural complexities. See\\nWright, FED. PRAC. & PROC. § 4234, at 195–98; Kalson, 542 F.3d at 287 (noting\\nthat the 1976 Act “vastly reduced the category of cases for which a three-judge\\ncourt is mandated”). It nonetheless decided to retain the procedure for a small\\n\\n\\n 12\\n\\n Case: 19-60133 Document: 00514887045 Page: 13 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nset of important cases: constitutional challenges to redistricting for\\ncongressional and state legislative seats, then-recent phenomena in the\\naftermath of the revolutionary one person, one vote line of cases. See, e.g.,\\nReynolds v. Sims, 377 U.S. 533 (1964). If Congress had intended to expand the\\nstatute it was otherwise contracting by applying it for the first time to\\nstatutory challenges there were certainly better ways to do it than by stealthily\\ninserting an extra “the.”\\n Reading the statute in the way Defendants suggest does not make sense\\nfor another reason: Why would Congress require three judges to hear statutory\\nclaims challenging state legislative redistricting but not congressional\\nredistricting? The dissent posits, without citing any authority, that perhaps\\nfederalism concerns would explain such a difference. But there are also strong\\nfederalism concerns with how a state chooses to divvy up its citizens into\\ncongressional districts. In fact, contemporary critics of the initial judicial foray\\ninto review of legislative apportionment viewed courts’ redrawing of\\ncongressional district as even more intrusive on traditional state prerogatives\\nthan judicial redrawing of state legislative districts. That is because of the\\nview that Article I, Section II of the Constitution grants “States . . . plenary\\npower to select their allotted Representatives in accordance with any method\\nof popular election they please, subject only to the supervisory power of\\nCongress.” Wesberry v. Sanders, 376 U.S. 1, 23 (1964) (Harlan, J., dissenting).\\n The other problem with the dissent’s theory—that Congress in 1976 had\\na special concern with statutory challenges to the drawing of state legislative\\ndistricts—is that it fails to grapple with the rarity of Section 2 challenges to\\nredistricting at that time. It was then not even clear that Section 2 provided a\\nprivate right of action. City of Mobile v. Bolden, 446 U.S. 55, 60 & n.8 (1980)\\n(assuming without deciding such a suit could exist). A few years later the\\n\\n\\n 13\\n\\n Case: 19-60133 Document: 00514887045 Page: 14 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nSupreme Court held Section 2 did not prohibit discriminatory effects which\\nmeant it provided no guarantee beyond what the Constitution already did. See\\nid. And the typical pre-1982 Section 2 claim that courts did consider was a\\nchallenge to at-large electoral systems, not the line drawing of single member\\ndistricts. See, e.g., id. In other words, there was no practice of statutory\\nchallenges to state legislative apportionment that Congress needed to address\\nin 1976.\\n To sum up, the dissent would give this much weight to the “the” that\\ncomes before “reapportionment of any statewide legislative body”: Insertion of\\nthat article would require three-judge panels for exclusively statutory claims—\\nfollowed by direct appeal to the Supreme Court, 28 U.S.C. § 1253—when the\\nthree-judge regime Congress was contracting in 1976 never did. It would\\nrequire those three-judge panels only for statutory challenges to\\napportionment of state legislative seats, not congressional ones. And it would\\ndo all this to address statutory challenges to apportionment of state\\nlegislatures when those claims hardly existed in 1976. An elephant indeed.\\n The dissent contends that there might have been clearer ways to\\nemphasize that the statute is limited to constitutional challenges. Dissenting\\nOp. at 12. But if Congress intended to include statutory-only challenges within\\nthe reach of the general three-judge statute for the first time, there were many\\neasy ways to make that clear. This brings up a final point on the jurisdictional\\nquestion. To the extent there is ambiguity, the longstanding principle that\\n“congressional enactments providing for the convening of three-judge courts\\nmust be strictly construed” comes into play. Allen v. State Bd. of Elections, 393\\nU.S. 544, 561 (1969); Phillips, 312 U.S. at 250 (noting the three-judge statue\\nshould be read narrowly because of its impact on the Supreme Court docket\\nand the burdens of convening three-judge courts).\\n\\n\\n 14\\n\\n Case: 19-60133 Document: 00514887045 Page: 15 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\n That rule of construction, the text of the three-judge statute, its lineage,\\nand the caselaw applying it all favor the district court’s view that three judges\\nare not required for a claim raising only statutory challenges to state\\nlegislative redistricting. Defendants thus face a steep climb in convincing this\\ncourt to be the first to ever read the statute as applying to a case challenging\\na district’s lines only under Section Two of the Voting Rights Act.\\n IV.\\n A.\\n Defendants also seek a stay on the ground that we are likely to reverse\\nthe district court’s ruling that District 22 dilutes the voting power of African-\\nAmericans. The standard of review poses an obstacle to undoing the factual\\nfindings that led the court to conclude that the district violates Section 2. An\\nappellate court “will not set aside” Section 2 factual findings “unless [it is] left\\nwith the definite and firm conviction that a mistake has been committed.”\\nMagnolia Bar Ass’n, Inc. v. Lee, 994 F.2d 1143, 1147 (5th Cir. 1993) (quotation\\nomitted); see NAACP v. Fordice, 252 F.3d 361, 365 (5th Cir. 2001) (noting that\\nclear error review applies).\\n In an attempt to avoid the clear-error standard, Defendants frame their\\nprimary challenge to liability as a legal one. They contend that a court cannot\\nfind vote dilution of a racial group that makes up a majority of the challenged\\ndistrict (recall that here that is just barely the case for District 22). This per\\nse rule they advocate—a bar on vote dilution claims whenever the racial group\\ncrosses the 50% threshold—is at odds with the reason we give such deference\\nto factual findings in Section 2 cases: the question of vote dilution is “peculiarly\\ndependent upon the facts of each case,” Thornburg v. Gingles, 478 U.S. 30, 79\\n(1986) (quoting Nevett v. Sides, 571 F.2d 209, 224 (5th Cir. 1978)), and\\n“requires an ‘intensely local appraisal’ of the challenged district,” LULAC, 548\\n\\n\\n 15\\n\\n Case: 19-60133 Document: 00514887045 Page: 16 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nU.S. at 437 (quoting Gingles, 478 U.S. at 79). The numerous local factors courts\\nconsider—including the strength of bloc voting, demographics, and voter\\nturnout—may mean that a minority group has the equal electoral opportunity\\nthe Voting Rights Act guarantees when its members make up only 40% of a\\ndistrict, but not when they make up 51%. Applying Defendants’ absolute bar\\non Section 2 scrutiny of 50%-plus districts to this case shows how it would\\narbitrarily override the numerous local considerations that Congress and the\\nSupreme Court have said courts need to consider in this important area. If\\nthere were a few hundred fewer African-Americans out of the nearly 44,000\\nvoting-age citizens in District 22, Defendants would allow courts to engage in\\nthe regular multifaceted vote dilution inquiry. But, to Defendants, just over\\n300 additional African-Americans makes the difference between that ordinary\\ninquiry and removing Section 2’s protections for tens of thousands of\\nMississippi voters.\\n Given the statutory mandate to focus on the “totality of circumstances”\\nin Section 2 cases, 52 U.S.C. § 10301(b), it is not surprising that numerous\\ncourts have found dilution of the voting power of a racial group in districts\\nwhere they make up a majority of the voting population. Most importantly,\\nour court has long rejected the argument Defendants advance. In an early vote\\ndilution case—also out of the Mississippi Delta—we explained that the “mere\\nexistence of a black population majority does not preclude a finding of dilution.”\\nMoore v. Leflore Cty. Bd. of Election Comm’rs, 502 F.2d 621, 624 (5th Cir. 1974).\\nWe echoed that more recently, stating that “a protected class that is also a\\nregistered voter majority is not foreclosed, as a matter of law, from raising a\\nvote dilution claim.” Salas v. Sw. Tex. Jr. Coll. Dist., 964 F.2d 1542, 1550 (5th\\nCir. 1992). We have even gone so far so to describe the authority on this point\\nas “unimpeachable.” Monroe v. City of Woodville, 881 F.2d 1327, 1333 (5th\\n\\n\\n 16\\n\\n Case: 19-60133 Document: 00514887045 Page: 17 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nCir. 1989) (describing the caselaw from our circuit that “has rejected any per\\nse rule that a racial minority that is a majority in a political subdivision cannot\\nexperience vote dilution”). We are not alone. Many courts of appeals, including\\none last year, have rejected the argument that a “racial minority cannot prevail\\non a Section 2 claim when it constitutes a bare numerical majority within the\\ndistrict.” Mo. St. Conf. of the NAACP v. Ferguson-Florissant Sch. Dist., 894\\nF.3d 924, 933 (8th Cir. 2018) (collecting cases from the Second, Fifth, Eleventh,\\nand D.C. Circuits).\\n Defendants try to distinguish these cases and others by arguing that\\nthey addressed at-large elections rather than single-member districts. But\\nnothing in these cases turned on that feature. And one court of appeals case\\ndirectly confronting the question rejected a bar on vote dilution claims for\\ngroups that make up more than 50% of the challenged single-member district.\\nKingman Park Civic Ass’n v. Williams, 348 F.3d 1033, 1041 (D.C. Cir. 2003)\\n(agreeing with Salas and Moore in a single-member district vote dilution case).\\nSo did a recent three-judge panel in this circuit. See Perez v. Abbott, 253 F.\\nSupp. 3d 864, 879–90 (W.D. Tex. 2017) (rejecting Defendants’ position when\\nfinding vote dilution in a congressional district with a Hispanic voting-age\\npopulation of 58.5%).\\n Against all this authority of both old and recent vintage, all Defendants\\ncan point to is Justice Kennedy’s opinion in Bartlett v. Strickland, 556 U.S. 1\\n(2009) (opinion of Kennedy, J.). 6 Here is the statement they contend supports\\na categorical rule that there can be no Voting Rights Act violation when a racial\\ngroup exceeds 50% of the district’s population: “Where an election district could\\n\\n\\n 6The defendants also cite Jeffers v. Beebe, 895 F. Supp. 2d 920, 932 (E.D. Ark. 2012),\\nas an example of a court employing their 50%+ bar on Section 2 claims. Even if they read\\nthat case correctly, that holding is no longer good law in its circuit. See Mo. St. Conf. of the\\nNAACP, 894 F.3d at 933.\\n 17\\n\\n Case: 19-60133 Document: 00514887045 Page: 18 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nbe drawn in which minority voters form a majority but such a district is not\\ndrawn,” a Section 2 claim is possible. This is an “objective, numerical test.” Id.\\nat 18. Assuming this opinion is the controlling one under Marks 7 (Justice\\nKennedy wrote for only three judges), it is addressing a different question. He\\nwas rejecting the concept of crossover districts and instead would require that\\na vote-dilution plaintiff show that a district could be drawn in which the racial\\ngroup is a majority. Id. at 15-20. In fact, that is the first showing Gingles\\nrequires. LULAC, 548 U.S. at 425 (noting the first “condition[] for establishing\\na § 2 violation” is that “the racial group is sufficiently large and geographically\\ncompact to constitute a majority in a single-member district” (cleaned up)).\\nFrom that requirement it does not follow that vote dilution cannot occur when\\nthe protected group already makes up a majority in the contested district. It\\nis thus not surprising that no court has read Bartlett to override the widely\\naccepted view that the voting strength of a protected group can still be diluted\\nwhen that group is a majority of a challenged district. Indeed, if any opinion\\nfrom Justice Kennedy addresses the question before us, it is his recognition in\\nLULAC that “it may be possible for a citizen voting-age majority to lack real\\nelectoral opportunity.” Id. at 428.\\n Recognizing this robust caselaw rejecting Defendants’ per se rule\\n(including in single-member cases), the dissent relies on an argument the\\nDefendants have never made: that there needed to be a finding of cracking or\\npacking minority voters. We typically will not consider arguments not\\nadvanced by a party. State Indus. Prods. Corp. v. Beta Tech Inc., 575 F.3d 450,\\n456 (5th Cir. 2009). That principle makes even more sense in the stay context.\\n\\n\\n 7See Marks v. United States, 430 U.S. 188, 193 (1977) (“When a fragmented Court\\ndecides a case and no single rationale explaining the result enjoys the assent of five Justices,\\nthe holding of the Court may be viewed as that position taken by those Members who\\nconcurred in the judgments on the narrowest grounds.” (quotation omitted)).\\n 18\\n\\n Case: 19-60133 Document: 00514887045 Page: 19 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nIf a “party is not entitled to a stay as a matter of right” even based on objections\\nit raised before the district court and in requesting a stay, Campaign for\\nSouthern Equality v. Bryant, 773 F.3d 55 (5th Cir. 2014), it should not be\\nentitled to that extraordinary remedy based on arguments the district court\\nnever had the chance to consider.\\n Even if we could grant a stay based on a challenge to the judgment\\nDefendants do not raise, the dissent’s position misses the marks on the merits.\\nIt argues that vote dilution can occur in a 50%-plus district only if the dilution\\nis the result of cracking or packing minority voters. The terms cracking\\n(dividing minority voters among various districts to weaken their strength)\\nand packing (concentrating minority voters in one or a small number of\\ndistricts where they make up an excessive majority and thus reduce that\\ngroup’s influence in other districts) describe gerrymandering techniques. Gill\\nv. Whitford, 138 S. Ct. 1916, 1924 (2018) (describing the practice in challenge\\nalleging partisan gerrymander); Shaw v. Reno, 509 U.S. 630, 670 (1993)\\n(White, J., dissenting) (same in challenge alleging racial gerrymander). They\\nexplain why vote dilution is occurring. Gill, 138 S. Ct. at 1931. The terms can\\nthus be used to describe types of Section 2 vote dilution claims. See, e.g.,\\nVoinovich v. Quilter, 507 U.S. 146, 153 (1993). But the “cracking” or “packing”\\ndescription does not result in a different Section 2 test or finding. Whether the\\ntheory for dilution is cracking or packing or something else, Section 2 claims\\nare evaluated by first looking at the three Gingles factors to determine whether\\ndemographics, geography, and voting behavior would allow the creation of a\\ndistrict in which the minority group has electoral power. LULAC, 548 U.S. at\\n425. If the plaintiffs satisfy that threshold, then a court considers the “totality\\nof the circumstances” to determine if “members of a racial group have less\\n\\n\\n\\n 19\\n\\n Case: 19-60133 Document: 00514887045 Page: 20 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nopportunity than do other members of the electorate.” Id. at 425–26. The\\ndistrict court faithfully followed this path. 8\\n Although cracking and packing are not official parts of the Section 2\\nanalysis, as a matter of arithmetic vote dilution will often exist because of\\ncracking or packing. Put another way, minority voting strength is often\\nweaker than demographics would allow because those voters have been\\ncrammed into one district with a very high minority percentage and thus\\ndiluted in other districts (packing) or spread among various districts when they\\ncould have formed an electoral majority in at least one (cracking). Indeed, the\\ndistrict court’s findings demonstrate cracking occurred here. 9 District 22 has\\na BVAP of 50.77% and District 23 has a BVAP of 42.00% when, as the remedy\\nadopted by the district court demonstrates, African-Americans could easily\\nform sufficient electoral strength to elect their representative of choice in at\\nleast one of these two districts.\\n The district court correctly focused on the Section 2 factors as prescribed\\nby the Supreme Court and the Voting Rights Act. Part of the reason it found\\nthat the <51% majority of African-American voters in the district did not result\\nin an ability to elect a representative of that group’s choosing was because of\\nturnout in off-year elections. So the “50%-plus” issue is largely an attempt to\\npackage Defendants’ challenge to the factual finding in a more favorable\\nstandard of review. But as with any other factual finding, the clearly\\n\\n\\n 8 It is thus not true that the district court thought that “simply because a district can\\n\\nbe drawn in a way that will guarantee a minority an election win, the Voting Rights Act\\ncompels that such a district be drawn.” Dissenting Op. at 7–8. The district court considered\\nall of the statutorily prescribed factors in finding vote dilution. The dissent is also wrong in\\nsaying that the district court thought a 62% African-American district was required. See id.\\nThat is just the demographics of the remedy it adopted that changed only 28 precincts. To\\nsay that the court thought that percentage was a requirement is to say that any time a\\ndistrict court remedies a Section 2 violation it is creating a new minimum.\\n9 There was no need to use the cracking label because Defendants never made the argument\\n\\nthe dissent advances.\\n 20\\n\\n Case: 19-60133 Document: 00514887045 Page: 21 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nerroneous standard means it is unlikely to be disturbed on appeal. That is\\nparticularly true when the factfinder gives a sound reason for crediting one\\nside’s evidence over the other’s. The district court did that in explaining why\\nit relied on Plaintiffs’ expert for turnout data rather than Census Bureau\\nfigures. The Census Bureau’s election data is for even-year elections, while\\nMississippi conducts odd-year state senate elections.\\n Defendants have not shown a high likelihood of overturning the finding\\nof vote dilution because their legal argument is at odds with “unimpeachable\\nauthority” from our court and their factual challenges must overcome\\ndeferential standards of review.\\n B.\\n\\n Defendants also argue that the district court erred by not dismissing the\\nlawsuit on laches grounds, focusing entirely on Thomas’s delay in bringing this\\nlawsuit. Even if he were the only plaintiff, the standard of review would again\\npose a substantial obstacle for Defendants to overcome on appeal. A district\\ncourt’s equitable ruling on laches is reviewed for abuse of discretion, and the\\nfactual findings of delay, inexcusability, and prejudice that underlie it are\\nreviewed for clear error. See Retractable Tech., Inc. v. Becton Dickinson & Co.,\\n842 F.3d 883, 898 (5th Cir. 2016).\\n More problematic than that for Defendants, Thomas is not the only\\nperson who brought this suit. The stay motion makes no argument for why\\nlaches should bar the lawsuit as to Plaintiffs Ayers and Lawson. As with all\\naffirmative defenses, the party asserting a laches defense bears the burden of\\nproving it. See City of El Paso, Tex. v. El Paso Entm’t, Inc., 382 F. App’x 361,\\n366 (5th Cir. 2010). Defendants did not even attempt to meet this burden for\\nAyers and Lawson. Nor is there, despite the dissent’s attempt to salvage a\\nlaches defense, an exception for the “main plaintiff,” whatever that means. Cf.\\n\\n 21\\n\\n Case: 19-60133 Document: 00514887045 Page: 22 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nMassachusetts v. EPA, 549 U.S. 497, 518 (2007) (observing that only one\\npetitioner needed to have standing to bring suit). The Voting Rights Act\\nprotects the rights of voters, not politicians. As to voters Ayers and Lawson,\\nDefendants point to nothing showing that a laches defense is likely to succeed\\non appeal.\\n V.\\n A.\\n The final ground on which Defendants seek a stay is the remedy the\\ndistrict court ordered. The standard of review again poses a challenge: the\\ndistrict court’s remedy is reviewed for abuse of discretion. Rodriguez v. Bexar\\nCnty., Tex., 385 F.3d 853, 870 (5th Cir. 2004).\\n But “whenever practicable . . . a reasonable opportunity [should be\\nafforded] the legislature to meet constitutional requirements by adopting a\\nsubstituted measure rather than for the federal court to devise and order into\\neffect its own plan.” Veasey, 830 F.3d at 270 (quoting Wise v. Lipscomb, 437\\nU.S. 535, 540 (1978) (opinion of White, J.)) (emphasis original). As recounted\\nabove, the district court first honored this principle in noting it would allow\\ntime for a legislative fix before it would redraw the district. When the court\\nwas informed that the legislature would not act until it saw the outcome of the\\nstay requests, the district court went ahead and redrew the lines given\\nconcerns about the candidate qualifying deadline. It noted, however, that the\\nlegislature always has the ability to redraw districts. Plaintiffs also point this\\nout in their response to the stay motion.\\n The legislature’s desire to wait to see the outcome of the stay ruling is\\nunderstandable. It would have been inefficient for it to remedy a violation only\\nto have this court grant a stay of the district court’s entire judgment on the\\nground that Defendants were likely to overturn the finding of vote dilution.\\n\\n\\n 22\\n\\n Case: 19-60133 Document: 00514887045 Page: 23 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nBut now that we have concluded to the contrary, the legislature should have\\nthe initial opportunity to draw new lines for District 22 that comply with the\\nVoting Rights Act. The only reason not to give it that first shot at crafting a\\nremedy is the candidate filing deadline, but the Secretary of State is requesting\\nthe legislative fix and has not indicated that a further extension of that\\ndeadline for the affected districts is problematic. And while the legislature is\\nalways able to redraw lines, the remedial preference is for it to have the first\\nchance to remedy a Section 2 violation, not for it to act only after the court\\ndraws a new district, which would result in three different districts in a short\\ntime period. United States v. Brown, 561 F.3d 420, 435 (5th Cir. 2009).\\n We thus issued an order on March 15 granting a temporary stay to allow\\nthe legislature until April 3 to remedy the Section 2 violation. The order also\\nextended the candidate filing deadline for any affected districts until April 12.\\n B.\\n Defendants otherwise are not likely to surmount the abuse of discretion\\nstandard in challenging the court’s remedy. If the legislature does not act and\\nthe judicial remedy goes into effect, it must still respect the legislature’s policy\\nobjectives as much as possible. See Perry v. Perez, 565 U.S. 38, 393 (2012). The\\nremedy is a narrowly-tailored one that does that. While redistricting cases\\noften result in redrawing the entire state or at least several districts, this\\nremedy moves just 28 precincts, less than 2% of the precincts in the state. The\\nremedy affects only 2 of Mississippi’s 52 Senate districts. The court found that\\nthe new lines met traditional redistricting criteria: compactness, contiguity,\\npreservation of political subdivisions like counties and cities, and avoiding\\npairing incumbents. It adopted the proposed map of an expert it found credible\\nwho also determined that the new map honored traditional criteria of\\ncompactness and contiguity. In fact, the new district is more consistent with\\n\\n\\n 23\\n\\n Case: 19-60133 Document: 00514887045 Page: 24 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\ntraditional geographic divisions in one important respect: it removes the\\nsuburban Madison county precincts and thus limits the district to counties in\\nthe rural and agricultural Delta.\\n The slightly altered districts are, if anything, also more compact than\\nthey were before. The following map of the new and old districts show the\\nlimited impact of the court’s remedy. The orange and pink highlighting shows\\nthe new districts; the blue lines show the old ones.\\n\\n\\n\\n\\n 24\\n\\n Case: 19-60133 Document: 00514887045 Page: 25 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\n Defendants’ main critique is that the new lines split Vicksburg between\\nthe districts. But some splitting of counties or cities is inevitable given equal\\npopulation requirements. A look at the statewide senate districts reveals this.\\nThe lines the legislature drew split at least eight cities with populations\\nbetween 23,000 and 27,000 residents (Vicksburg had a population of 26,407\\nwhen the 2012 maps were drawn) into different senate districts, including\\nClinton, whose 25,216 citizens are split among 5 districts. Having to split\\nVicksburg thus does not lack fidelity to the legislature’s redistricting policy\\nwhich often results in the same situation. Defendants have not demonstrated\\na high likelihood of showing that that district court’s narrow redraw was an\\nabuse of discretion.\\n C.\\n The dissent also contends that the district court’s remedy interferes with\\nongoing election preparation, though the Defendants—including the Secretary\\nof State—do not cite this as a reason for a stay. In a recent case denying a stay\\nin a voting rights case, we did not consider this issue when government officials\\ndid not argue that the district court’s plan would substantially disturb the\\nelection process. Patino v. City of Pasadena, 677 F. App’x 950, 951–52 (5th Cir.\\n2017).\\n The election is even further away in this case than it was in Patino. Id.\\n(denying stay sought during the candidate registration period with election\\nthree months away); see also Patino v. City of Pasadena, 229 F. Supp. 3d 582,\\n585 (S.D. Tex. 2017) (providing the relevant dates). Primary voting is more\\nthan four months away; the general election is more than seven months away.\\nThat distance to the election means the potential for voter confusion that\\n\\n\\n\\n\\n 25\\n\\n Case: 19-60133 Document: 00514887045 Page: 26 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nanimates this concern, Purcell v. Gonzalez, 549 U.S. 1, 4 (2006), is absent. 10\\nMississippi voters in the 28 affected precincts will go to the same voting\\nlocation they always have, face the same voting requirements, and have\\nmonths to research the candidates in advance of the election. Indeed, the effect\\nof redrawing some of the lines for just two state senate districts with elections\\nmonths away pales in comparison to the impact of statewide redistricting that\\nhas been implemented in a similar timeframe. See, e.g., Covington v. North\\nCarolina, 2018 WL 604732 (M.D. N.C. 2018); Common Cause v. Rucho, 284 F.\\nSupp. 3d 780 (M.D. N.C. 2018); Larios v. Cox, 305 F. Supp. 2d 1335 (N.D. Ga.\\n2004).\\n With no risk of voter confusion, and no outcry from state officials that\\nimplementing the district court’s remedy substantially disturbs its election\\nprocess, this is not a basis for a stay.\\n D.\\n One final comment is necessary to set the record straight in response to\\nthe dissent’s attack on the remedy. It irresponsibly insinuates that the district\\njudge—whom it takes the unusual step of repeatedly naming—drew new lines\\nwith the aim of eliminating partisan opposition to Plaintiff Thomas. That is\\nnot true. Importantly, the incumbent state senator in District 22 had decided\\nnot to run for reelection before the district court ruled in this case. The\\ndissent’s conjecture also ignores that primary candidates file with the political\\nparty (not the state), with the parties notifying state officials of the candidates\\n\\n\\n 10 As most of the cases cited by the dissent show, the voter confusion concern is\\ntypically greatest when a court alters election procedures (as opposed to districts) with an\\nelection quickly approaching. See Veasey v. Perry, 769 F.3d 890, 892 (5th Cir. 2014) (staying\\ndistrict court injunction striking down voter ID laws); Purcell, 549 U.S. at 1 (same); North\\nCarolina v. League of Women Voters of N.C., 135 S. Ct. 6 (2014) (staying district court order\\nthat changed voter ID requirements, voting hours, voting locations, and voter registration);\\nHusted v. Ohio State Conference of NAACP, 135 S. Ct. 42 (2014) (staying district court order\\nthat changed voting hours).\\n 26\\n\\n Case: 19-60133 Document: 00514887045 Page: 27 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nonly after the filing deadline. That had not yet occurred when the court issued\\nfinal judgment.\\n In light of these circumstances, there is no basis for believing that the\\nPlaintiffs’ expert who drew the proposed remedy back in mid-January, or the\\ndistrict court that later adopted it, knew who the new candidates would be. No\\none brought the names or residences of the candidates to the court’s attention\\nprior to its remedy ruling. And the district court issued its remedy before the\\ninitial candidate qualifying deadline, so there may have been additional\\ncandidates. Not until after the court issued its remedy, in a motion for stay,\\ndid Defendants bring to the court’s attention the fact that two candidates\\nwould no longer reside in District 22. On learning this, the district court\\nlamented that it was not told prior to its ruling. As for the competition in the\\nnew district, we do not know who has filed nor who will file prior to the new\\nqualifying deadline.\\n ***\\n Per the order issued last week, the motion for stay is GRANTED IN\\nPART and DENIED IN PART. A majority of the panel concludes Defendants\\nhave satisfied the stay factors only based on the need to give the legislature\\nand Governor an opportunity to remedy the Section 2 violation. A stay is\\nentered for that purpose until April 3, 2019. The candidate filing deadline for\\nany districts whose lines are redrawn (whether by the legislature, or if it does\\nnot act, per the district court’s remedy) is extended to April 12, 2019. The\\ndistrict court has jurisdiction to consider any challenges to the adequacy of a\\nlegislative remedy.\\n\\n\\n\\n\\n 27\\n\\n Case: 19-60133 Document: 00514887045 Page: 28 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4380782/\", \"author_raw\": \"GREGG COSTA, Circuit Judge:\"}, {\"author\": \"EDITH BROWN CLEMENT, Circuit Judge, dissenting\", \"type\": \"dissent\", \"text\": \"EDITH BROWN CLEMENT, Circuit Judge, dissenting in part.\\n\\n Joseph Thomas is a black Democrat and resident of Yazoo County,\\nMississippi. A one-time State Senator who lost in 2007 and sat out the 2011\\nelection cycle, he is trying hard to get his seat back. Thomas ran in the 2015\\nState Senate election in District 22 and lost to the Republican incumbent by a\\nthin margin. Three years later, Thomas and two voters sued the Mississippi\\nGovernor, Secretary of State, and Attorney General, accusing them of\\ngerrymandering District 22 in violation of Section 2 of the Voting Rights Act.\\nThe plaintiffs argued that black voters in District 22 are politically cohesive,\\nbut that white bloc voting prevents them from electing their candidate of\\nchoice. Although black voters already comprised a majority of the voting age\\npopulation in District 22 at 51%, the plaintiffs argued that this majority was\\ntoo narrow for them to elect a candidate. They say they need at least a 62%\\nmajority to do that. The district court agreed that 62% was necessary. And\\nbecause achieving that percentage was possible by shifting black voters from a\\nneighboring district into District 22, Judge Reeves ordered it done. But he also\\nmanaged to move something important out of District 22 in the process.\\nNamely, the two Republican challengers to Thomas for the 2019 election.\\n\\n I feel confident that the district court’s decision will ultimately be\\nreversed. At least, it should be. Laches may well bar the challenge. There is a\\njurisdictional issue. The theory of liability is unheard-of. The evidence is\\nsuspect. And the remedy (as even the majority acknowledges) is faulty. A\\nlikelihood of success on any one of these cascading objections is enough to\\nentitle the defendants to a stay of the district court’s redistricting plan. After\\nall, as the majority explains, the stakes are high here. When the majority says\\nthere is a “meaningful possibility” that a full appeal could come too late, that\\nis quite the understatement. It is like saying there is a “meaningful possibility”\\n 28\\n\\n Case: 19-60133 Document: 00514887045 Page: 29 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nthat a Republican could win an election in the new District 22. Possible in\\ntheory, perhaps, but contrary to common understanding and experience.\\n\\n I dissent from the panel’s refusal to grant the stay in its entirety. Unless\\nwe act now, the November election in Senate District 22 is all but decided.\\nTrue, predictable election results are not uncommon. What is uncommon,\\nhowever, is for a federal district judge to be the one to decide them.\\n\\n I. The Remedy Problem\\n\\n I begin where the district court ended, because even the majority has\\ntrouble defending that. Even if Judge Reeves was permitted to decide this case\\nby himself and even if he was correct that District 22 violates Section 2, it\\nremains obvious that his remedy should be stayed and, ultimately, reversed.\\nIt is not even a close call.\\n\\n “Federal-court review of districting legislation represents a serious\\nintrusion on the most vital of local functions.” Miller v. Johnson, 515 U.S. 900,\\n915 (1995). It is well settled that “reapportionment is primarily the duty and\\nresponsibility of the State.” Id. Appropriately, therefore, our case law is clear\\nthat “whenever practicable, . . . a reasonable opportunity [should be afforded]\\nfor the legislature to meet constitutional requirements by adopting a substitute\\nmeasure rather than for the federal court to devise and order into effect its own\\nplan.” Veasey v. Abbott, 830 F.3d 216, 270 (5th Cir. 2016) (en banc) (quotation\\nomitted).\\n\\n That standard undoubtedly leaves room for a district court to act before\\nthe legislature when necessary. Given that the original candidate qualifying\\ndeadline has come and gone, that the ballots must be sent to overseas troops\\nby the end of June, and that the primary is scheduled for early August, I can\\n\\n 29\\n\\n Case: 19-60133 Document: 00514887045 Page: 30 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nappreciate that we are operating on an abbreviated timetable. But that is all\\nthe more reason to preserve the status quo. Federal courts rarely have the right\\nto issue orders the effect of which is to dramatically interfere with ongoing\\nelection preparation. See Veasey v. Perry, 769 F.3d 890, 892 (5th Cir. 2014)\\n(“The Supreme Court has repeatedly instructed courts to carefully consider the\\nimportance of preserving the status quo on the eve of an election.”). “[U]nder\\ncertain circumstances, such as where an impending election is imminent and\\na State’s election machinery is already in progress, equitable considerations\\nmight justify a court in withholding the granting of immediately effective relief\\nin a legislative apportionment case, even though the existing apportionment\\nscheme was found invalid.” Reynolds v. Sims, 377 U.S. 533, 585 (1964).\\n\\n When issues are hotly contested or when the district court’s reasoning or\\nremedy are flawed, when time to act is short, and when elections hang in the\\nbalance, it is almost always better to wait than to interfere. Our court has\\nstayed district court orders in such situations in the past. See, e.g., Veasey, 769\\nF.3d 890. And when we or other appellate courts have been unwilling to do so,\\nthe Supreme Court has stepped in to preserve the status quo. See, e.g., North\\nCarolina v. League of Women Voters of N.C., 135 S. Ct. 6 (2014) (overturning\\nFourth Circuit injunction which barred implementation of the state’s voting\\nreform laws); Husted v. Ohio State Conference of NAACP, 135 S. Ct. 42 (2014)\\n(staying district court’s injunction); Perry v. Perez, 565 U.S. 1090 (2011) (same);\\nPurcell v. Gonzalez, 549 U.S. 1, 4–5 (2006) (per curiam) (vacating Ninth Circuit\\ninjunction, and observing that “[c]ourt orders affecting elections, especially\\nconflicting orders, can themselves result in voter confusion and consequent\\nincentive to remain away from the polls”).\\n\\n\\n\\n\\n 30\\n\\n Case: 19-60133 Document: 00514887045 Page: 31 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\n Curiously, the majority believes that because the Supreme Court has\\nmostly done so in cases involving “election procedures,” not redistricting, the\\nCourt’s admonitions carry less weight here. But they have it backwards.\\nAltering which candidates appear on a voter’s ballot is a much greater\\nimposition on him than changing the location of his poll or the form of ID he\\nmust have in his pocket. Indeed, I have not found a case in which a court\\naltered district boundaries during or after a candidate qualification period. We\\nshould maintain the status quo here, or else expect the country’s highest court\\nto once again do it for us.\\n\\n But even if Judge Reeves had little choice but to implement a remedy\\nhimself, I am deeply concerned with the remedy he chose and the way that he\\nchose it. As the majority explains, Judge Reeves adopted the first of three plans\\nsubmitted by the plaintiffs. He adopted it without making factual findings and\\nwithout a hearing. In his single-page order adopting the plan, Judge Reeves\\ndid not explain why “Plan 1” was the narrowest remedy or clarify why he had\\nrejected “Plan 2” and “Plan 3.” The only time Judge Reeves discussed the\\ndetails of the plans was in his liability opinion, where he devoted three pages\\nto describing them.\\n\\n The three plans are similar. All require moving several thousand\\nindividuals (27,000 for Plan 1) either into or out of District 22 from one or two\\nadjacent districts. Plans 1 and 2 only affect only Districts 22 and 23, whereas\\nPlan 3 also changes the boundary of District 13. All three plans split the city\\nof Vicksburg in half, though only Plan 2 and Plan 3 offset that splitting by\\nreuniting other cities that are currently split. Under Plan 1, the black voting\\nage population of District 22 would increase to 62%. Under Plan 2, the\\npopulation would increase to 61%. And under Plan 3, it would increase to 66%.\\nApart from stating generically that none of the plans “dilute minority voting\\n 31\\n\\n Case: 19-60133 Document: 00514887045 Page: 32 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nstrength,” Judge Reeves did not discuss the effect each of the plans would have\\non the black voting age population of District 23 or District 13. He simply noted\\nthat Plan 1 would decrease the black voting age population in neighboring\\nDistrict 23 from 42% to 31%.\\n\\n Looking at the record, I have no idea why Judge Reeves preferred one\\nplan over another. I do not understand why he selected the one plan in which\\nthe splitting of Vicksburg was not offset in some other way. I do not understand\\nhow Judge Reeves could endorse increasing the black voting age population of\\none district without discussing the effect that the change would have on the\\nblack voting age population of adjacent districts. And I do not understand why\\nJudge Reeves did not hold a hearing before making his decision. The fact\\nremains that his order—perhaps, inadvertently—eliminated meaningful\\ncompetition for Thomas in the upcoming election. The majority says that Judge\\nReeves’s plan is “narrowly tailored.” Agreed—it is “narrowly tailored” to win\\nThomas the election. 1 In my view, our circuit’s strong preference for the\\nlegislature to have the first say on redistricting, combined with the obvious\\ndefects in Judge Reeves’s remedy, make it likely that his redistricting plan will\\nultimately be reversed.\\n\\n II. The Merits Problem\\n\\n Another problem with the remedy is that there shouldn’t be one. Indeed,\\nI also think the district court erred in finding a Voting Rights Act violation. I\\nagree with the majority that, at least as a matter of theory, it may be possible\\n\\n 1 The majority thinks this observation “irresponsibl[e].” But even though the slate of\\ncandidates had not and could not have been finalized at the time of the district court’s order,\\nit does not require a crystal ball to foresee the result of Judge Reeves’s remedy. He eliminated\\nthe Republican base in District 22, essentially making the primary election dispositive. As\\nfar as we know, Thomas is the only previously-elected State Senator running in that primary\\nand as far as we know, his only two Republican challengers are now in another district.\\n 32\\n\\n Case: 19-60133 Document: 00514887045 Page: 33 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nfor a state to violate Section 2 of the Act even when a protected group forms a\\nmajority of the voting population. That option is left open by our precedent. See\\nSalas v. Southwest Texas Jr. College Dist., 964 F.2d 1542, 1550 (5th Cir. 1992);\\nMoore v. Leflore County Bd. of Election Com’rs, 502 F.2d 621, 624 (5th Cir.\\n1974). But even accepting that possibility, there is a strong likelihood that\\nJudge Reeves committed clear error by finding a Section 2 violation here.\\nWhere “the ultimate finding of dilution” is based on “a misreading of the\\ngoverning law,” there is reversible error. Johnson v. De Grandy, 512 U.S. 997,\\n1022 (1994).\\n\\n As the Supreme Court has explained, “a plaintiff may allege a § 2\\nviolation in a single-member district if the manipulation of districting lines\\nfragments politically cohesive minority voters among several districts or packs\\nthem into one district or a small number of districts, and thereby dilutes the\\nvoting strength of members of the minority population.” Shaw v. Hunt, 517\\nU.S. 899, 914 (1996). In other words, a state can violate Section 2 by “cracking”\\nthe minority vote into separate districts so that the minority is unable to elect\\nits chosen representatives, or by “packing” the minority vote into\\nsupermajority-minority districts—thereby reducing the overall number of\\nrepresentatives that the minority receives. See, e.g., Pope v. Cty. of Albany, 687\\nF.3d 565, 567 (2d Cir. 2012) (minority alleging that their population size and\\ngeographical distribution warranted five majority-minority districts, not four);\\nKingman Park Civic Ass’n v. Williams, 348 F.3d 1033, 1038 (D.C. Cir. 2003)\\n(minority alleging that redistricting diluted the minority vote overall by\\npacking it into some districts and cracking it in others).\\n\\n It is crucial to understand this context. No court has ever found that a\\nmajority-minority single-member district violates Section 2 by itself. The idea\\nthat a majority-minority district violates Section 2 only makes sense if the\\n 33\\n\\n Case: 19-60133 Document: 00514887045 Page: 34 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nallegation is that packing or cracking has occurred. See Thornburg v. Gingles,\\n478 U.S. 30, 46 n.11 (1986) (“Dilution of racial minority group voting strength\\nmay be caused by the dispersal of blacks into districts in which they constitute\\nan ineffective minority of voters or from the concentration of blacks into\\ndistricts where they constitute an excessive majority.”). Both kinds of\\nviolations span district lines. A plaintiff cannot prove packing or cracking\\nwithout analyzing minority population and voter statistics for multiple\\ndistricts. See, e.g., Perez v. Abbott, 253 F. Supp. 3d 864, 879 (W.D. Tex. 2017)\\n(analyzing statistics for numerous districts and concluding that “while\\nPlaintiffs may not have submitted sufficient proof that they are entitled to\\neight [Hispanic citizen voting age population]-majority districts in South/West\\nTexas, they have shown that they are entitled to seven such districts, and they\\nmay assert claims under . . . § 2 against the districts in [the current plan]”).\\n\\n There was no such evidence in this case. Indeed, the complaint nowhere\\nmentions “packing” or “cracking,” and the evidence focused on District 22\\nalone. I do not understand how a majority-minority district could violate\\nSection 2 unless the district is the result of packing or cracking the minority\\nvote among a geographical area that is larger than the district itself. The\\nallegation that the minority’s majority is not large enough to overcome white\\nbloc voting would only become actionable if the minority’s majority is being\\nartificially lowered to dilute the minority vote.\\n\\n The majority opinion suggests that Section 2 vote dilution requires that\\na minority group be deprived of a district in which it has electoral strength to\\nelect a representative of its choice when such a district is possible. But nothing\\nin Section 2 “establishes a right to have members of a protected class elected\\nin numbers equal to their proportion in the population.” 52 U.S.C. § 10301(b).\\n“[T]he ultimate right of § 2 is equality of opportunity, not a guarantee of\\n 34\\n\\n Case: 19-60133 Document: 00514887045 Page: 35 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nelectoral success for minority-preferred candidates of whatever race.” De\\nGrandy, 512 U.S. at 1014 n.11; see also Gingles, 478 U.S. at96 (O’Connor, J.,\\nconcurring in the judgment).\\n\\n The district court and the majority seem to think that simply because a\\ndistrict can be drawn in a way that will guarantee a minority an election win,\\nthe Voting Rights Act compels that such a district be drawn. Not so. Section 2\\ndoes not grant the plaintiffs a right to a 62% majority to overcome low black\\nturnout or white bloc voting in the abstract. It is only when the drawing of\\ndistrict lines along traditional methods should have resulted in a different\\nelectoral scheme that Section 2 is violated. There must be evidence that\\npacking or cracking has taken place (whether or not it is expressly referred to\\nas such). 2 That is the difference between guaranteeing equal opportunity and\\nguaranteeing electoral success.\\n\\n The majority would avoid this reality by saying the defendants do not\\nraise the issue. But challenging the viability of Voting Rights Act claims in\\nmajority-minority single-member districts and also challenging the plaintiffs’\\nevidence in this case—both of which defendants do—places the district court’s\\nmerits ruling in contention. It is telling that the majority, apparently\\nrecognizing the conceptual difficulty of finding vote dilution in the absence of\\npacking or cracking, ultimately attempts to recast the district court’s finding\\nin that vein. But because there was no such evidence—indeed, neither packing\\n\\n\\n\\n\\n 2 Putting these fundamental concerns to the side, I also believe the plaintiffs did not\\noffer sufficient evidence to support their claim. I am particularly troubled by Judge Reeves’s\\ndecision to disregard Census Bureau statistics concluding that black voter turnout generally\\nexceeds white voter turnout. Even the cases relied on by the plaintiffs acknowledge that\\nCensus Bureau statistics are usually dispositive. See Mo. St. Conf. of the NAACP v. Ferguson-\\nFlorissant Sch. Dist., 894 F.3d 924, 932–33 (8th Cir. 2018).\\n 35\\n\\n Case: 19-60133 Document: 00514887045 Page: 36 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nnor cracking was even alleged—the plaintiffs have not shown a Section 2\\nviolation.\\n\\n III. The Laches Problem\\n\\n The plaintiffs are entirely to blame for the haste with which we must\\nresolve this case. The challenged redistricting occurred seven years ago.\\nDisliking what he saw from the start, Thomas contacted the Department of\\nJustice in 2012 and asked them to “look hard” at newly drawn Senate Districts\\n21, 22, and 34. He questioned whether the new redistricting plan as a whole\\nreduced black voting strength in Mississippi. Rejecting Thomas’s concerns, the\\nDOJ precleared the plan in September 2012.\\n\\n Thomas waited. He did not file a Voting Rights Act challenge in 2012,\\n2013, or 2014. He chose instead to run in the 2015 election, losing 54% to 46%\\nto the incumbent chairman of the State Senate Appropriations Committee.\\nThomas was “real disappointed” that despite his efforts to appeal to white\\nvoters in the 2015 election, he garnered little of the white vote. See Thomas v.\\nBryant, 2019 WL 654314, at *1 (S.D. Miss. Feb. 16, 2019).\\n\\n Still, Thomas did nothing. He did not file a Voting Rights Act challenge\\nin 2015, 2016, or 2017. Thomas has explained that he was unaware that an\\nindividual could file a Voting Rights Act challenge until his lawyer told him in\\n2018. But “laches does not depend on subjective awareness of the legal basis\\non which a claim can be made.” Envtl. Def. Fund, Inc. v. Alexander, 614 F.2d\\n474, 479 (5th Cir. 1980). The letter to the DOJ shows that Thomas had\\nconcerns about District 22 as early as 2012, yet he waited until halfway\\nthrough 2018 to act.\\n\\n\\n\\n\\n 36\\n\\n Case: 19-60133 Document: 00514887045 Page: 37 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\n That delay prejudiced the defendants and the public. Laches is an\\ninexcusable delay on the part of the plaintiff that results in prejudice to the\\ndefendant. Conan Props., Inc. v. Conans Pizza, Inc., 752 F.2d 145, 153 (5th Cir.\\n1985). It has been applied by the Supreme Court to bar untimely Voting Rights\\nAct challenges. Lopez v. Hale Cty., Tex., 506 U.S. 1042 (1993) (affirming Lopez\\nv. Hale Cty., Tex., 797 F. Supp. 547, 550 (N.D. Tex. 1992)); Cf. White v. Daniel,\\n909 F.2d 99, 102 (4th Cir. 1990). By waiting until now to challenge the district,\\nThomas has injected needless uncertainty into the November 2019 election.\\nMere months before Election Day, Mississippi voters went to bed in one district\\nand woke up in another. Candidates suddenly find themselves running for\\noffice in a district they do not know, appealing to a public that does not know\\nthem. And the Republican Party finds itself without a horse in the race,\\nmoments before the starting gun is fired.\\n\\n The delay has inured to the benefit only of Thomas, whose prospects have\\nbrightened noticeably since the district court redrew the political landscape.\\nHis postponement of legal action has—unless the stay is granted—all but\\nensured that there will be no time for reconsideration of the district court’s\\nopinion before the election. Judge Reeves’s decision, made on an accelerated\\ntimeline following expedited discovery, is likely to be the end of the matter.\\nThe balance of the equities, in my view, is not on Thomas’s side. 3\\n\\n\\n\\n\\n 3 The other plaintiffs, Vernon Ayers and Melvin Lawson, do not undermine this view.\\nLawson is a District 22 voter who worked on Thomas’s Senate campaign and then joined\\nThomas’s lawsuit. No one seems to know anything about Ayers besides the fact that he is a\\nregistered voter in District 22. Thomas is the main plaintiff (even the district court’s opinion\\nfocused almost exclusively on Thomas). In any event, all the plaintiffs are challenging district\\nlines which were implemented seven years ago. It is that unnecessary delay, common to all\\nthe plaintiffs, which should bar the suit.\\n 37\\n\\n Case: 19-60133 Document: 00514887045 Page: 38 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\n IV. The Jurisdiction Problem\\n\\n Assuming Thomas did not unduly delay, however, was it permissible for\\nthe district court to decide this Voting Rights Act case without convening a\\nthree-judge panel? As the majority notes, there is no need to get into this unless\\n28 U.S.C. § 2284(a) is jurisdictional. That statute provides: “A district court of\\nthree judges shall be convened when otherwise required by Act of Congress, or\\nwhen an action is filed challenging the constitutionality of the apportionment\\nof congressional districts or the apportionment of any statewide legislative\\nbody.”\\n\\n The majority is right that the statute certainly “sounds jurisdictional.”\\nMaybe that is why every court to consider the question has said that it is. See\\nKalson v. Patterson, 542 F.3d 281, 287 (2nd Cir. 2008); Armour v. State of Ohio,\\n925 F.2d 987, 988–89 (6th Cir. 1991) (en banc); LULAC of Texas v. Texas, 318\\nF. App’x 261, 264 (5th Cir. 2009) (per curiam). I think so too. And since the\\nmajority ultimately concedes that forfeiture is an obstacle the defendants “will\\nlikely be able to overcome on appeal,” I will get straight to the heart of the\\nquestion.\\n\\n This lawsuit is indisputably an action challenging the apportionment of\\na statewide legislative body. The only question is whether the “constitutional”\\nmodifier in § 2284(a) applies to the second phrase in the sentence. The district\\ncourt ruled that it does, giving three reasons. Thomas v. Bryant, No. 0190219C,\\n2019 WL 454598, at *2–3 (S.D. Miss. Feb. 5, 2019). First, that there was no\\nreason to treat Voting Rights Act claims and constitutional claims as identical\\nin the statewide context. Second, that the plain language of the text and\\nstatutory canons of construction compelled the court’s interpretation. Third,\\n\\n\\n\\n 38\\n\\n Case: 19-60133 Document: 00514887045 Page: 39 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nthat the court’s decision was buttressed by other persuasive decisions. The first\\ntwo reasons are totally incorrect, and the third is weak.\\n\\n “The task of statutory interpretation begins and, if possible, ends with\\nthe language of the statute.” United States v. Lauderdale Cty., Mississippi, 914\\nF.3d 960, 964 (5th Cir. 2019). The district court said that the “series-qualifier”\\ncanon compelled its conclusion that the constitutionality modifier applied to\\nboth phrases. Thomas, 2019 WL 454598 at *2–3. The book “Reading Law”\\nexplains the canon as follows: “When there is a straightforward, parallel\\nconstruction that involves all nouns or verbs in a series, a prepositive or\\npostpositive modifier normally applies to the entire series.” ANTONIN SCALIA &\\nBRYAN A. GARNER, READING LAW: THE INTERPRETATION OF LEGAL TEXTS 147\\n(2012). A typical example is the phrase “Forcibly assaults, resists, opposes,\\nimpedes, intimidates, or interferes with,” in which the modifier “forcibly\\nmodifies each verb in the list.” Id. at 148. Crucially for our purposes, however,\\nthe authors also explain when the modifier does not apply:\\n\\n The typical way in which syntax would suggest no carryover\\n modification is that a determiner (a, the, some, etc.) will be\\n repeated before the second element: [for example,] The charitable\\n institutions or the societies (the presence of the second the suggests\\n that the societies need not be charitable).\\n\\n\\nId.\\n\\n That is exactly the situation we have here. The statute provides for a\\nthree-judge court “when an action is filed challenging the constitutionality of\\nthe apportionment of congressional districts or the apportionment of any\\nstatewide legislative body.” 28 U.S.C. § 2284(a) (emphasis added). The\\ndeterminer “the” (or the determining phrase “the apportionment”) cuts off the\\n\\n 39\\n\\n Case: 19-60133 Document: 00514887045 Page: 40 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\ncontinued application of the word “constitutionality” to the second phrase. That\\nthe sentence has a parallel structure, as the majority harps on, is not\\ndispositive. After all, if the statute did not have a parallel structure, we would\\nnot be discussing the series-qualifier canon in the first place. The whole point\\nof the canon is to describe when a modifier applies to a parallel series, and\\nwhen it does not. The canon and the context both answer that question in the\\nnegative.\\n\\n If Congress intended the majority’s interpretation, there would have\\nbeen much clearer ways to say so. Here are just three examples:\\n\\n • A district court of three judges shall be convened . . . when an\\n action is filed challenging the constitutionality of the\\n apportionment of congressional districts or [the\\n apportionment] of any statewide legislative body.\\n\\n\\n • A district court of three judges shall be convened . . . when an\\n action is filed challenging the constitutionality of [either] the\\n apportionment of congressional districts or the apportionment\\n of any statewide legislative body.\\n\\n\\n • A district court of three judges shall be convened . . . when an\\n action is filed challenging the constitutionality of the\\n apportionment of congressional districts or [of] the\\n apportionment of any statewide legislative body.\\n\\n\\nNotably, Congress said none of those things. At the risk of quoting someone\\nother than the late Justice Scalia, the Supreme Court has observed time and\\nagain that we “must presume that a legislature says in a statute what it means\\nand means in a statute what it says.” Connecticut Nat. Bank v. Germain, 503\\nU.S. 249, 253–54 (1992); see also, e.g., Arlington Cent. Sch. Dist. Bd. of Educ.\\n\\n\\n\\n 40\\n\\n Case: 19-60133 Document: 00514887045 Page: 41 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nv. Murphy, 548 U.S. 291, 296 (2006); In re Camp, 631 F.3d 757, 759 (5th Cir.\\n2011).\\n\\n This may seem overly technical. But the district court explicitly noted\\nthat “[d]espite its ‘fancy name,’ the series-qualifier canon ‘reflects the\\ncompletely ordinary way that people speak and listen, write and read.’”\\nThomas, 2019 WL 454598 at *2 n.5 (quoting Lockhart v. United States, 136 S.\\nCt. 958, 970 (2016) (Kagan, J., dissenting)). And the canon supports the\\nopposite interpretation from the one adopted by the district court. It is this\\nreading, and not the majority’s reading, which reflects the plain meaning of\\nthe statute. Further, the district court admitted the defendants had a “fair\\npoint” that the court’s interpretation resulted in the statute containing\\nneedless words. Id. at *2. “If ‘the constitutionality of’ is indeed carried over to\\nall following phrases, the second use of ‘the apportionment of’ is rendered\\nunnecessary.” Id. The correct application of the series-qualifier canon has the\\nadded benefit of avoiding that contradiction and giving meaning to every word\\nin the statute. This is consistent with yet another canon: the surplusage canon.\\nSee SCALIA & GARNER, at 174–79.\\n\\n The district court could not understand why Congress would treat Voting\\nRights Act and constitutional claims as identical, focusing on the fact that they\\nhave different evidentiary requirements and that a plaintiff is master of his\\ncomplaint. Thomas, 2019 WL 454598 at *2. But the differing burdens of proof\\nand the plaintiff’s undenied ability to select the claims he wishes to bring do\\nnot undermine the rationale for treating all challenges to statewide legislative\\napportionment the same. Both constitutional and statutory attacks on\\nlegislative redistricting implicate the same fundamental concern: balancing\\njudicial respect for a state’s decision regarding the best manner of selecting its\\nrepresentatives with the need to ensure equal opportunity within the\\n 41\\n\\n Case: 19-60133 Document: 00514887045 Page: 42 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nelectorate. Whether court-ordered redistricting is based on the Constitution or\\nthe Voting Rights Act makes little difference to the state whose actions have\\nbeen curtailed.\\n\\n Indeed, a more relevant question than the one asked by the district court\\nis why the statute would treat challenges to congressional redistricting\\ndifferently from challenges to statewide legislative redistricting. The answer\\nto that challenge may well lie in federalism. It is entirely plausible that\\nCongress wanted federal courts to show more deference to state\\nreapportionment plans that only affect state interests than to state\\nreapportionment plans which affect national interests. The majority suggests\\nthat federalism would actually support the opposite inference, considering that\\na state’s power to select its congressional representatives stems directly from\\nArticle I, Section II of the Constitution. But that line of reasoning is\\nundermined by Supreme Court precedent, which has allowed the states greater\\nlatitude in creating state legislative districts than in creating congressional\\ndistricts. See Gaffney v. Cummings, 412 U.S. 735, 742–44 (1973).\\n\\n In any event, I am not arguing that federalism compels the statutory\\ninterpretation for which I advocate. I simply offer a plausible explanation for\\nwhy the plain text says what it does. The truth is that most of the time, the\\nopposing interpretations of § 2284(a) will not matter, as Voting Rights Act\\nclaims and constitutional claims are usually asserted together. That is why—\\nfar from hiding an elephant in a mousehole—the correct interpretation merely\\nensures equal treatment for stand-alone Voting Rights Act claims whose\\nimplications can be quite as severe as constitutional ones. My view has the\\nadditional benefit of avoiding the forum-shopping concerns implicit in the\\nmajority’s reading.\\n\\n\\n 42\\n\\n Case: 19-60133 Document: 00514887045 Page: 43 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\n Finally, the district court’s conclusion that non-binding cases “buttress[]”\\nits decision is weak. See Thomas, 2019 WL 454598 at *3. The district court\\ncited a Sixth Circuit decision, a Third Circuit decision, and a decision from the\\nNorthern District of Georgia. Id. The majority adds a citation from the\\nNorthern District of Alabama, the District of South Dakota, and the District of\\nMontana. The sum of persuasive authority on this point is two circuit court\\nopinions and four district court opinions. And as the majority admits, these\\ncases really aren’t on point to begin with. The Sixth Circuit opinion does not\\nmention § 2284(a)—it simply affirmed a single-judge decision. Rural West\\nTennessee African-American Affairs Council v. Sundquist, 209 F.3d 835 (6th\\nCir. 2000). Of the district court opinions, only the Northern District of Alabama\\naddresses the question head-on, and it fails to mention the series-qualifier\\ncanon or the superfluous language that all parties admit results from the\\ndistrict court’s reading. See Chestnut v. Merrill, 2019 WL 338909 (N.D. Ala.\\n2019).\\n\\n Most significantly, the Third Circuit decision supports the opposite\\nconclusion from that reached by the district court. In Page, the court was\\nconsidering whether a single judge may decide a Voting Rights Act claim when\\nstatutory and constitutional claims are brought together. See Page v. Bartels,\\n248 F.3d 175, 186–94 (3d Cir. 2001). While the opinion says that § 2284(a) “only\\nrequires a three-judge district court for certain constitutionally-based\\napportionment challenges,” the court further stated that Congress likely did\\nnot make a “deliberate choice to distinguish between constitutional\\napportionment challenges and apportionment challenges brought under § 2 of\\nthe Voting Rights Act.” Id. at 189.\\n\\n Indeed, most redistricting challenges at the time of the 1976 amendment\\nwere constitutional, meaning the distinction carried less importance in 1976\\n 43\\n\\n Case: 19-60133 Document: 00514887045 Page: 44 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nthan it does today. And “the legislative history of the 1976 revisions to 28\\nU.S.C. § 2284 clearly demonstrates that Congress was concerned less with the\\nsource of the law on which an apportionment challenge was based than on the\\nunique importance of apportionment cases generally.” Id. at 190. Because all\\ncases attacking “the legitimacy of the state legislative apportionment” are\\n“highly sensitive matters,” the Third Circuit concluded that practical and\\npolicy considerations weighed in favor of three-judge review irrespective of the\\nnature of the claims asserted. Id. So in its survey of the caselaw, the majority\\nseems to have missed that the only circuit court opinion to address the issue\\nin any depth goes the other way. 4\\n\\n Of course, none of these opinions (and there are not very many of them)\\nare binding on this court. As noted earlier, the issue does not come up often\\nsince plaintiffs normally bring suit using all the potential weapons in their\\narsenal. To the extent that the opinions that have considered this question cut\\nin any direction, however, I’d submit they cut in favor of the three-judge panel\\nfor Voting Rights Act claims. The district court was wrong to read § 2284(a) in\\nthe manner it did. A three-judge panel should have decided this case.\\n\\n * * *\\n\\n This case presents several extraordinary issues. Unfortunately, this\\ncourt’s usual procedures do not appear to permit en banc review of this denial\\nof a stay even if a majority of the active judges would otherwise grant it. I am\\nafraid defendants have simply had the poor luck of drawing a majority-\\nminority panel. I trust that in light of this, the State will pursue a stay in the\\n\\n\\n 4 The majority acknowledges Page in a footnote, noting that it “does not adopt the\\ntextual argument” I am advocating here. That is unsurprising, considering that no one\\nadvocated for such an interpretation in Page. It is the reasoning from the opinion which\\nsupports my view—not the opinion’s different answer to a different question.\\n 44\\n\\n Case: 19-60133 Document: 00514887045 Page: 45 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nSupreme Court because of the injustice that results from the joint efforts of the\\ndistrict judge and the motions panel majority. I also encourage the State to\\nmove for an expedited appellate process before this court, preferably seeking\\nan April or May sitting—it might yet be possible for this court to undo its own\\nmistake.\\n\\n\\n\\n\\n 45\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4380782/\", \"author_raw\": \"EDITH BROWN CLEMENT, Circuit Judge, dissenting\"}]}"},"judge1":{"kind":"string","value":"DENNIS"},"judge2":{"kind":"string","value":"CLEMENT"},"judge3":{"kind":"string","value":"COSTA"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"DENNIS\": \", Circuit\", \"CLEMENT\": \", Circuit\", \"COSTA\": \", Circuit\"}"},"opinions_count":{"kind":"number","value":2,"string":"2"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":1,"string":"1"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4603529/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Joseph Thomas v. Phil Bryant\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-25\nOpinion type: majority\nHas dissenting opinion: Yes\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 19-60133 Document: 00514887045 Page: 1 Date Filed: 03/25/2019\n\n\n\n\n REVISED March 25, 2019\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT United States Court of Appeals\n Fifth Circuit\n\n ___________________ FILED\n March 22, 2019\n No. 19-60133 Lyle W. Cayce\n ___________________ Clerk\n\nJOSEPH THOMAS; VERNON AYERS; MELVIN LAWSON,\n\n Plaintiffs - Appellees\n\nv.\n\nPHIL BRYANT, Governor of the State of Mississippi,; DELBERT\nHOSEMANN, Secretary of State of the State of Mississippi, both in the\nofficial capacities of their own offices and in their official capacities as\nmembers of the State Board of Election Commissioners,\n\n Defendants - Appellants\n\n _______________________\n\n Appeal from the United States District Court\n for the Southern District of Mississippi\n _______________________\n\nBefore DENNIS, CLEMENT, and COSTA, Circuit Judges.\nGREGG COSTA, Circuit Judge:\n A district court found that the boundaries for Mississippi State Senate\nDistrict 22 dilute African-American voting strength and prevent those citizens\nfrom having the equal opportunity “to participate in the political process and\nto elect representatives of their choice” that the Voting Rights Act guarantees.\n52 U.S.C. § 10301(b). To remedy the violation, the district court switched 28\n\n Case: 19-60133 Document: 00514887045 Page: 2 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\nprecincts between District 22 and a bordering district. The Governor and\nSecretary of State seek a stay of the final judgment.\n I.\n Most of District 22 lies in the heart of the Mississippi Delta. Those\nunfamiliar with the state’s geography might think that the Mississippi Delta\nis in the southern portion of the state that is closer to the mouth of the\nMississippi River. But the “Delta” refers not to the outlet of that mighty river\ninto the Gulf of Mexico, but to the alluvial plain between the Mississippi River\nand the Yazoo River. John M. Barry, RISING TIDE: THE GREAT MISSISSIPPI\nFLOOD OF 1927 AND HOW IT CHANGED AMERICA 96 (1997). It is located in the\nnorthwest section of Mississippi and looks like an “elongated diamond.” Id.\nThe district court recited this colorful description of its boundaries: “The\nMississippi Delta begins in the lobby of the Peabody Hotel [in Memphis] and\nends on Catfish Row in Vicksburg.” David L. Cohn, GOD SHAKES CREATION\n(1935).\n The sediment that the Mississippi River deposited in this region over the\nmillennia made Delta soil some of the richest in the world. Barry, supra, at\n97. And that soil made the Delta one of the leading cotton-producing areas in\nthe world. One historian compared the influence the Delta once held over\nglobal cotton prices to the modern influence of Saudi Arabia over oil prices.\nSven Beckert, EMPIRE OF COTTON: A GLOBAL HISTORY 113 (2014).\n But before agriculture could prosper in the Delta its forests of hardwood\ntrees had to be cleared. Slaves were forced to begin that process, and\nemancipated slaves finished it in the latter part of the nineteenth century.\nSince that time, African-Americans have been a majority in the Delta. In the\nearly twentieth century, they made up almost 90% of the region’s population.\nBarry, supra, at 125 (noting that in 1908 the Delta had “a black population of\n\n\n 2\n\n Case: 19-60133 Document: 00514887045 Page: 3 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\nat least 171,209” and “a white population of 24,137”). The Great Migration to\nthe north reduced the African-American percentage, but they remain a\nsizeable majority in the region.\n Of course, for most of their time laboring in the Delta, African-Americans\ncould not vote. The Voting Rights Act changed that. It has resulted in\nnumerous African-Americans being elected to office in the Delta. Indeed, the\nState of Mississippi has more African-American elected officials than any other\nstate. U.S. Census Bureau, STATISTICAL ABSTRACT OF THE UNITED STATES:\n2011, 258 (130th ed.).\n But in places like the state legislature, African-Americans have still not\nachieved political power in Mississippi that comes close to their share of the\npopulation. This case involves a claim that one state senate district\ncontributed to that underrepresentation by diluting the voting strength of\nAfrican-Americans that Delta demographics and geography should otherwise\nsupport.\n District 22 includes all or part of five Delta counties: Bolivar,\nHumphreys, Sharkey, Washington, and Yazoo. It also includes parts of one\nnon-Delta county: Madison. The addition of the white-majority Madison\nCounty precincts in the last redistricting reduced the African-American\npercentage in District 22. Overall the district still has an African-American\nmajority, but just barely at 50.7%. 1 Without the non-Delta precincts from\n\n\n\n 1 Plaintiff Thomas told the Department of Justice that the 50.7% figure includes the\npopulation of the Yazoo City federal prison, the majority of whose inmates he says are\nAfrican-American. He contended that without including that prison, African-Americans\nwould not be a majority in the district. It is questionable whether disenfranchised people\nshould be included in the BVAP (black voting age population) calculation for purposes of the\nVoting Rights Act. The focus is usually on those eligible to vote, thus the typical requirement\nin our circuit that the percentage focus on those of voting age who are citizens. See Reyes v.\nCity of Farmers Branch, Tex., 586 F.3d 1019, 1023 (5th Cir. 2009) (noting that only citizens\nare included in population calculations).\n 3\n\n Case: 19-60133 Document: 00514887045 Page: 4 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\nMadison County, that percentage would be much higher.\n The candidate preferred by the black majority did not prevail in the 2015\nelection. The losing candidate those voters did prefer (Joseph Thomas), along\nwith two voters (Vernon Ayers and Melvin Lawson), brought this lawsuit in\n2018 alleging that the district violated of Section 2 of the Voting Rights Act.\n Last month, the district court held a bench trial and agreed. It concluded\nthat the threshold Gingles factors for establishing vote dilution existed. The\nAfrican-American population is “sufficiently large and geographically compact”\nto constitute a majority with electoral power in the district; that racial group\nis politically cohesive; but the white population voted as a bloc to prevent\nAfrican-Americans from electing their chosen candidate. LULAC v. Perry, 548\nU.S. 399, 425 (2006). The bloc voting by both racial groups was stark: in 10\nelections within district 22, the candidate favored by African-Americans\nreceived between 82% and 93% of their vote but only between 8% and 19% of\nthe white vote.\n The district court then followed the statutory directive to consider the\n“totality of circumstances” in determining whether African-Americans “have\nless opportunity than other members of the electorate to participate in the\npolitical process and to elect representatives of their choice.” 52 U.S.C.\n§ 10301(b); LULAC, 548 U.S. at 425–26. It credited Plaintiffs’ expert’s analysis\nof voter participation as more rigorous and concluded that African-American\nturnout was depressed in off-year elections—that is, odd-year elections without\nfederal races—which is when Mississippi elects its legislature. The district\ncourt also highlighted the persistent representation gap in the Mississippi\nSenate, as well as substantial socioeconomic differences between black voters\nand white voters in the district.\n After finding a Voting Rights Act violation, the court initially declined to\n\n\n 4\n\n Case: 19-60133 Document: 00514887045 Page: 5 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\norder a remedy so “the Mississippi Legislature [could] consider[] whether to\nredraw the District and extend the candidate qualification deadline.”\nAlthough the primary and general elections were months away, the deadline\nfor candidate filing was March 1.\n A flurry of procedural moves followed at warp speed. Three days after\nthe court made its trial findings, the Governor and Secretary of State\n(Defendants) 2 filed a motion a motion to stay with the district court and also\nfiled an appeal, arguing that the ruling was an appealable interlocutory\ninjunction. Less than a week later, they asked this court to stay the district\ncourt’s ruling. That same day, Plaintiffs asked the court to extend the\nqualification deadline in District 22 and bordering District 23 (the other\ndistrict affected by the proposed remedy) by two weeks. Later that day, the\ndistrict court ordered Defendants to update it on any progress, if any, in\nlegislative redrawing of District 22.\n The next day, Defendants filed a brief opposing Plaintiffs’ motion to\nextend the qualification deadline, in which they stated that they had contacted\nthe leadership of the legislative chambers. The Senate leaders had said that\n“should the stay motions pending before [the district court] and the Fifth\nCircuit be denied, the Senate desire[d] the opportunity to enact a new\nredistricting plan redrawing Senate District 22.” Late that same day, the\ndistrict court ruled that, because the legislature was unwilling to act, the first\nmap drawn by one of Plaintiffs’ experts would be adopted as the boundaries of\nDistricts 22 and 23. The court also moved the qualification deadline to March\n\n\n\n\n 2 The third defendant, Attorney General Jim Hood, did not join these motions or this\nappeal.\n 5\n\n Case: 19-60133 Document: 00514887045 Page: 6 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\n15 for the two affected senate districts. The court also declined to enter a stay\nand entered final judgment.\n The final judgment caused our court to dismiss the appeal of the\npreliminary ruling. Thomas v. Bryant, 2019 WL 994034 (5th Cir. Feb. 28,\n2019). But by that time the Defendants had already appealed from the final\njudgment, and not long after that they sought a stay pending the new appeal,\nwhich is the motion before this panel. 3\n This is the effect of the final judgment: It switches some precincts\nbetween Districts 22 and 23. It extends the candidate filing deadline to March\n15. In terms of other upcoming deadlines, the primary election is August 6,\nwith a June 22 deadline to send ballots to troops overseas. The general election\nis November 5.\n II.\n The stay Defendants seek is an extraordinary remedy. Nken v. Holder,\n556 U.S. 418, 437 (2009) (Kennedy, J., concurring). It is also an equitable one\ncommitted to this court’s discretion. Id. at 433; Ruiz v. Estelle, 666 F.2d 854,\n856 & n.4 (5th Cir. 1982). Four factors guide the exercise of our discretion:\n1) whether the applicant has made a strong showing of likelihood to succeed\non the merits; 2) whether the movant will be irreparably harmed absent a stay;\n3) whether issuance of a stay will substantially injure other interested parties;\nand 4) where the public interest lies. Nken, 556 U.S. at 434. The first two\nfactors are usually the most important. Id.; ODonnell v. Goodhart, 900 F.3d\n220, 223 (5th Cir. 2018).\n In this case, the likelihood of success ends up being dispositive. That is\nbecause Defendants can establish irreparable harm. A court order preventing\n\n\n 3 Before seeking the stay pending appeal for the second time in our court after entry\nof final judgment, Defendants also sought a stay in the district court for the second time. The\ndistrict court denied that motion.\n 6\n\n Case: 19-60133 Document: 00514887045 Page: 7 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\nenforcement of a state law, including the drawing of legislative lines,\nconstitutes that harm. Abbott v. Perez, 138 S. Ct. 2305, 2324 n.17 (2018). And\nthat injury may be irreparable in light of the meaningful possibility (but not\ncertainty) that a full appeal cannot be decided in time to provide Defendants\nrelief before this year’s senate elections. But Plaintiffs face the same risk that\nthe appellate ruling will prove futile should this court grant a stay. And the\ninjury they seek to prevent—holding an election under an unlawful plan with\ndiscriminatory effects—is also, it should go without saying, a serious one.\nVeasey v. Abbott, 830 F.3d 216, 270 (5th Cir. 2016) (en banc) (“It would be\nuntenable to permit a law with a discriminatory effect to remain in operation\nfor that election.”); cf. Reynolds v. Sims, 377 U.S. 533, 585 (1964) (“[I]t would\nbe the unusual case in which a court would be justified in not taking\nappropriate action to insure that no further elections are conducted under the\ninvalid plan.”). So Defendants’ entitlement to a stay turns on whether they\nhave a strong likelihood of success.\n III.\n We will first address Defendants’ attempt to make that showing with a\njurisdictional argument. They contend that a three-judge court should have\ndecided this case. The statute says that a “district court of three judges shall\nbe convened when otherwise required by Act of Congress, or when an action is\nfiled challenging the constitutionality of the apportionment of congressional\ndistricts or the apportionment of any statewide legislative body.” 28 U.S.C.\n§ 2284(a). The Voting Rights Act does not require three-judge courts for\nSection 2 cases (notably it does for Section 5 cases, 52 U.S.C. § 10304(a)), so\nDefendants focus on the latter part of the statute. They contend that\n“constitutionality” modifies only challenges to apportionment of congressional\ndistricts, not challenges to apportionment of state legislatures. On their\n\n\n 7\n\n Case: 19-60133 Document: 00514887045 Page: 8 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\nreading, any challenge to state legislative redistricting—including the\nstatutory Voting Rights Act one asserted here—requires a three-judge panel.\n Defendants requested a three-judge panel late in the litigation, a week\nbefore trial. Failing to request such a panel in their answer may have forfeited\nthe issue unless it is a jurisdictional requirement. The three-judge statute has\nconflicting language on whether it is one. It begins by saying “a district court\nof three judges shall be convened” for specified cases. 28 U.S.C. § 2284(a). That\nmandatory language sounds jurisdictional. So does the statute’s prohibition\non a single judge taking certain actions, including granting injunctive relief.\nId. § 2284(b)(3). But the statute also says that the procedure for convening a\nthree-judge court kicks in “[u]pon the filing of a request for three judges.” Id.\n§ 2284(b)(1). That does not sound jurisdictional. If the requirement is\njurisdictional, then the single district judge first assigned the case would\nseemingly have an obligation to convene a three-judge panel even if a party\ndoes not ask for it.\n Recognizing these conflicting statutory signals, the leading federal\nprocedure treatise is ambivalent about whether Section 2284 is jurisdictional.\nSee 17A Charles Alan Wright et al., FED. PRAC. & PROC. § 4235, at 206–08 (3d\ned. 2007). But apparently the courts that have considered the question—\nincluding ours in a nonbinding decision—have treated Section 2284 as\njurisdictional. See Kalson v. Patterson, 542 F.3d 281, 287 (2nd Cir. 2008);\nArmour v. Ohio, 925 F.2d 987, 989 (6th Cir. 1991) (en banc); LULAC of Texas\nv. Texas, 318 F. App’x 261, 264 (5th Cir. 2009). That consensus in the caselaw\nmeans that forfeiture is an obstacle Defendants will likely be able to overcome\non appeal.\n Defendants’ delay in raising this issue does, however, say something\nabout its merits. At the outset of this lawsuit, it was not obvious to Defendants\n\n\n 8\n\n Case: 19-60133 Document: 00514887045 Page: 9 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\n(or Plaintiffs or the district judge for that matter) that its exclusively statutory\nclaims required a three-judge court. Indeed, no reported case has ever used a\nthree-judge panel for a case challenging district lines only under Section 2 of\nthe Voting Rights Act. See Rural W. Tenn. African-American Affairs Council\nv. Sundquist, 209 F.3d 835, 838 (6th Cir. 2000) (noting case reassigned to single\njudge after dismissal of constitutional and Section 5 claims); Chestnut v.\nMerrill, 2019 WL 338909 (N.D. Ala. 2019) (rejecting argument that a single\njudge could not hear Section 2 challenge); Bone Shirt v. Hazeltine, 336 F. Supp.\n2d 976, 980 (D. S.D. 2004) (same as Rural West); Old Person v. Brown, 182 F.\nSupp. 2d 1002, 1003 (D. Mont. 2002) (single judge hearing Section 2 challenge);\nsee also Armour, 925 F.2d at 989 (stating the jurisdictional test for Section\n2284 as whether “there exists a non-frivolous constitutional challenge to the\napportionment of a statewide legislative body” (emphasis added)). 4 That no\ncourt has adopted Defendants’ reading of the three-judge statute in the more\nthan four decades it has been on the books alone seems enough to prevent them\nfrom showing a strong likelihood of succeeding on this issue. To be sure, only\nthe Chestnut opinion from earlier this year addressed an argument like the one\nDefendants make. But that is again telling: Before this year, it apparently had\nnever dawned on a judge or party in a Section 2-only state redistricting case\n\n\n\n 4 Though uncited by Defendants or their amicus, the dissent finds Page v. Bartels, 248\nF.3d 175 (3d Cir. 2001), “most significant[].” Dissenting Op. at 15. But unlike the cases cited\nabove, Page does not involve a situation in which plaintiffs only brought Section 2 claims.\nInstead, it involved both constitutional and statutory claims. Yet a single district court judge\nattempted to spin off the statutory claims and deny an injunction based on them. Id. at 187.\nThe Third Circuit said that when plaintiffs bring both claims, both must be sent to a three-\njudge panel. Id. at 191. That is consistent with the common practice when both constitutional\nand statutory challenges to reapportionment are brought—the constitutional hook for three-\njudge jurisdiction sweeps in the statutory claims. While the dissent tries to find support for\nits position in some of Page’s discussion of legislative history and policy, notably the Third\nCircuit does not adopt the textual argument the dissent and amicus push.\n\n\n 9\n\n Case: 19-60133 Document: 00514887045 Page: 10 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\nthat a three-judge panel might be required. And that is because the most\nstraightforward reading of the three-judge statute is that it applies only when\nthe “constitutionality” of apportionment is being challenged.\n So why does the dissent, adopting the argument of an amicus, think the\nthree-judge statute applies to what is only a statutory challenge when no court\nhas ever taken that view? One word—the “the” that precedes “apportionment\nof any statewide legislative body.” 28 U.S.C. § 2284(a). Inclusion of that article\nmeans, in their view, that “constitutionality” applies only to what immediately\nfollows it: challenges to the “apportionment of congressional districts.” If\n“constitutionality” does not also modify the “apportionment of any statewide\nlegislative body,” id., then any challenges to those districts, including statutory\nones, require a three-judge panel.\n The textual argument is a dispute about application of the “series\nmodifier” canon of construction. It normally means that a modifier\n(“constitutionality” in Section 2284) applies to an entire series of parallel\nterms. See Scalia & Garner, READING LAW: THE INTERPRETATION OF LEGAL\nTEXTS 147 (2012). The district court concluded that principle supports reading\nthe statute as applying to constitutional challenges to apportionment of both\ncongressional and state legislative seats. But an amicus supporting the\ndefendants argues the “the” coming before “apportionment of any statewide\nlegislative body” breaks the series modifier. The amicus notes that a\n“determiner” word, such as the “the” in Section 2284(a), is an indication that a\nmodifier should not reach the second element. 5 See id. at 148–49.\n\n\n\n 5 Defendants make a different textual argument in support of their position that this\ncase belongs with a three-judge court. They focus not just on the “the,” but on “the\napportionment” that precedes “of any statewide legislative body.” They contend it is\nsuperfluous if it does not break off the “constitutionality” modifier. But it may be\n“appropriate to tolerate a degree of surplusage.” United States v. Atl. Research Corp., 551\n 10\n\n Case: 19-60133 Document: 00514887045 Page: 11 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\n But inferring that “the” was meant to cut off the “constitutionality”\nmodifier ignores what may be the most important teaching about the series\nmodifier canon from the Scalia and Garner book on statutory interpretation:\n“Perhaps more than most of the other canons, this one is highly sensitive to\ncontext.” Id. at 150. That context supports the natural reading that courts have\nlong given it: that “constitutionality” modifies both “the apportionment of\ncongressional districts” and “the apportionment of any statewide legislative\nbody.” That Congress wanted the two phrases to sound the same—“the\napportionment of congressional districts” and “the apportionment of any\nstatewide legislative body” are word-for-word identical, with the exception of\nthe type of district that they reference—is consistent with how ordinary people\nspeak and write. See Lockhart v. United States, 136 S. Ct. 958, 970 (2016)\n(Kagan, J., dissenting). To illustrate this, consider what a reader would think\nafter seeing the following in the newspaper: “The NCAA is investigating the\nrecruiting practices of the football program and the basketball program.” As\nwith the three-judge statute, the final “the” may not be necessary. But would\nit make the reader think the investigation into the basketball program is not\nlimited to recruiting violations, but also might include point shaving or ticket\nscalping violations? Of course not. The dissent’s textual argument about the\nthree-judge statute is just as detached from common usage.\n What is more, giving so much significance to “the” runs counter to\nanother point Justice Scalia made about statutory interpretation: that\nCongress “does not . . . hide elephants in mouseholes.” Whitman v. Am.\nTrucking Ass’n, 531 U.S. 457, 468 (2001). The historical development of the\nthree-judge statute—that is, statutory history as opposed to the more\n\n\n\nU.S. 128, 137 (2007). Indeed, one could make the case that even the first “the,” the one before\n“apportionment of congressional districts,” is unnecessary.\n 11\n\n Case: 19-60133 Document: 00514887045 Page: 12 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\ncontroversial legislative history Defendants rely on—shows why it would have\nbeen so significant and anomalous to require three-judge panels for statutory\nclaims. The statute was first enacted in the aftermath of Ex parte Young to\nrequire three judges to hear what Congress thought would be an increasing\nnumber of suits challenging state laws “upon the ground of the\nunconstitutionality of such statute.” 28 U.S.C. § 2281 (1970); see generally\nDavid P. Currie, The Three-Judge District Court in Constitutional Litigation,\n32 U. CHI. L. REV. 1, 5–8 (1964). When courts later struck down many New\nDeal reforms, one of the only aspects of President Roosevelt’s court-packing\nplan to become law was a measure also requiring three-judge panels for suits\nseeking to enjoin “any Act of Congress for repugnance to the Constitution of\nthe United States.” 28 U.S.C. § 2282 (1970); see Wright, FED. PRAC. & PROC.\n§ 4234, at 194–95. Both laws’ focus on only constitutional challenges made\nsense as striking down democratically enacted laws is “the gravest and most\ndelicate duty” courts are “called on to perform.” Nw. Austin Mun. Util. Dist.\nNo. One v. Holder, 557 U.S. 193, 204 (2009) (referring to striking down an Act\nof Congress (quoting Blodgett v. Holden, 275 U.S. 142, 147–48 (1927) (Holmes,\nJ., concurring))). The idea of requiring three judges for this “class of cases of\nspecial importance” was to “assure more weight and greater deliberation by\nnot leaving the fate of such litigation to a single judge.” Phillips v. United\nStates, 312 U.S. 246, 249–50 (1941) (first quotation from Ex parte Collins, 277\nU.S. 565, 567 (1928)). But in the mid-1970s, Congress decided to scrap just\nabout all of the three-judge regime because it was burdening the Supreme\nCourt and lower courts and had resulted in procedural complexities. See\nWright, FED. PRAC. & PROC. § 4234, at 195–98; Kalson, 542 F.3d at 287 (noting\nthat the 1976 Act “vastly reduced the category of cases for which a three-judge\ncourt is mandated”). It nonetheless decided to retain the procedure for a small\n\n\n 12\n\n Case: 19-60133 Document: 00514887045 Page: 13 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\nset of important cases: constitutional challenges to redistricting for\ncongressional and state legislative seats, then-recent phenomena in the\naftermath of the revolutionary one person, one vote line of cases. See, e.g.,\nReynolds v. Sims, 377 U.S. 533 (1964). If Congress had intended to expand the\nstatute it was otherwise contracting by applying it for the first time to\nstatutory challenges there were certainly better ways to do it than by stealthily\ninserting an extra “the.”\n Reading the statute in the way Defendants suggest does not make sense\nfor another reason: Why would Congress require three judges to hear statutory\nclaims challenging state legislative redistricting but not congressional\nredistricting? The dissent posits, without citing any authority, that perhaps\nfederalism concerns would explain such a difference. But there are also strong\nfederalism concerns with how a state chooses to divvy up its citizens into\ncongressional districts. In fact, contemporary critics of the initial judicial foray\ninto review of legislative apportionment viewed courts’ redrawing of\ncongressional district as even more intrusive on traditional state prerogatives\nthan judicial redrawing of state legislative districts. That is because of the\nview that Article I, Section II of the Constitution grants “States . . . plenary\npower to select their allotted Representatives in accordance with any method\nof popular election they please, subject only to the supervisory power of\nCongress.” Wesberry v. Sanders, 376 U.S. 1, 23 (1964) (Harlan, J., dissenting).\n The other problem with the dissent’s theory—that Congress in 1976 had\na special concern with statutory challenges to the drawing of state legislative\ndistricts—is that it fails to grapple with the rarity of Section 2 challenges to\nredistricting at that time. It was then not even clear that Section 2 provided a\nprivate right of action. City of Mobile v. Bolden, 446 U.S. 55, 60 & n.8 (1980)\n(assuming without deciding such a suit could exist). A few years later the\n\n\n 13\n\n Case: 19-60133 Document: 00514887045 Page: 14 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\nSupreme Court held Section 2 did not prohibit discriminatory effects which\nmeant it provided no guarantee beyond what the Constitution already did. See\nid. And the typical pre-1982 Section 2 claim that courts did consider was a\nchallenge to at-large electoral systems, not the line drawing of single member\ndistricts. See, e.g., id. In other words, there was no practice of statutory\nchallenges to state legislative apportionment that Congress needed to address\nin 1976.\n To sum up, the dissent would give this much weight to the “the” that\ncomes before “reapportionment of any statewide legislative body”: Insertion of\nthat article would require three-judge panels for exclusively statutory claims—\nfollowed by direct appeal to the Supreme Court, 28 U.S.C. § 1253—when the\nthree-judge regime Congress was contracting in 1976 never did. It would\nrequire those three-judge panels only for statutory challenges to\napportionment of state legislative seats, not congressional ones. And it would\ndo all this to address statutory challenges to apportionment of state\nlegislatures when those claims hardly existed in 1976. An elephant indeed.\n The dissent contends that there might have been clearer ways to\nemphasize that the statute is limited to constitutional challenges. Dissenting\nOp. at 12. But if Congress intended to include statutory-only challenges within\nthe reach of the general three-judge statute for the first time, there were many\neasy ways to make that clear. This brings up a final point on the jurisdictional\nquestion. To the extent there is ambiguity, the longstanding principle that\n“congressional enactments providing for the convening of three-judge courts\nmust be strictly construed” comes into play. Allen v. State Bd. of Elections, 393\nU.S. 544, 561 (1969); Phillips, 312 U.S. at 250 (noting the three-judge statue\nshould be read narrowly because of its impact on the Supreme Court docket\nand the burdens of convening three-judge courts).\n\n\n 14\n\n Case: 19-60133 Document: 00514887045 Page: 15 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\n That rule of construction, the text of the three-judge statute, its lineage,\nand the caselaw applying it all favor the district court’s view that three judges\nare not required for a claim raising only statutory challenges to state\nlegislative redistricting. Defendants thus face a steep climb in convincing this\ncourt to be the first to ever read the statute as applying to a case challenging\na district’s lines only under Section Two of the Voting Rights Act.\n IV.\n A.\n Defendants also seek a stay on the ground that we are likely to reverse\nthe district court’s ruling that District 22 dilutes the voting power of African-\nAmericans. The standard of review poses an obstacle to undoing the factual\nfindings that led the court to conclude that the district violates Section 2. An\nappellate court “will not set aside” Section 2 factual findings “unless [it is] left\nwith the definite and firm conviction that a mistake has been committed.”\nMagnolia Bar Ass’n, Inc. v. Lee, 994 F.2d 1143, 1147 (5th Cir. 1993) (quotation\nomitted); see NAACP v. Fordice, 252 F.3d 361, 365 (5th Cir. 2001) (noting that\nclear error review applies).\n In an attempt to avoid the clear-error standard, Defendants frame their\nprimary challenge to liability as a legal one. They contend that a court cannot\nfind vote dilution of a racial group that makes up a majority of the challenged\ndistrict (recall that here that is just barely the case for District 22). This per\nse rule they advocate—a bar on vote dilution claims whenever the racial group\ncrosses the 50% threshold—is at odds with the reason we give such deference\nto factual findings in Section 2 cases: the question of vote dilution is “peculiarly\ndependent upon the facts of each case,” Thornburg v. Gingles, 478 U.S. 30, 79\n(1986) (quoting Nevett v. Sides, 571 F.2d 209, 224 (5th Cir. 1978)), and\n“requires an ‘intensely local appraisal’ of the challenged district,” LULAC, 548\n\n\n 15\n\n Case: 19-60133 Document: 00514887045 Page: 16 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\nU.S. at 437 (quoting Gingles, 478 U.S. at 79). The numerous local factors courts\nconsider—including the strength of bloc voting, demographics, and voter\nturnout—may mean that a minority group has the equal electoral opportunity\nthe Voting Rights Act guarantees when its members make up only 40% of a\ndistrict, but not when they make up 51%. Applying Defendants’ absolute bar\non Section 2 scrutiny of 50%-plus districts to this case shows how it would\narbitrarily override the numerous local considerations that Congress and the\nSupreme Court have said courts need to consider in this important area. If\nthere were a few hundred fewer African-Americans out of the nearly 44,000\nvoting-age citizens in District 22, Defendants would allow courts to engage in\nthe regular multifaceted vote dilution inquiry. But, to Defendants, just over\n300 additional African-Americans makes the difference between that ordinary\ninquiry and removing Section 2’s protections for tens of thousands of\nMississippi voters.\n Given the statutory mandate to focus on the “totality of circumstances”\nin Section 2 cases, 52 U.S.C. § 10301(b), it is not surprising that numerous\ncourts have found dilution of the voting power of a racial group in districts\nwhere they make up a majority of the voting population. Most importantly,\nour court has long rejected the argument Defendants advance. In an early vote\ndilution case—also out of the Mississippi Delta—we explained that the “mere\nexistence of a black population majority does not preclude a finding of dilution.”\nMoore v. Leflore Cty. Bd. of Election Comm’rs, 502 F.2d 621, 624 (5th Cir. 1974).\nWe echoed that more recently, stating that “a protected class that is also a\nregistered voter majority is not foreclosed, as a matter of law, from raising a\nvote dilution claim.” Salas v. Sw. Tex. Jr. Coll. Dist., 964 F.2d 1542, 1550 (5th\nCir. 1992). We have even gone so far so to describe the authority on this point\nas “unimpeachable.” Monroe v. City of Woodville, 881 F.2d 1327, 1333 (5th\n\n\n 16\n\n Case: 19-60133 Document: 00514887045 Page: 17 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\nCir. 1989) (describing the caselaw from our circuit that “has rejected any per\nse rule that a racial minority that is a majority in a political subdivision cannot\nexperience vote dilution”). We are not alone. Many courts of appeals, including\none last year, have rejected the argument that a “racial minority cannot prevail\non a Section 2 claim when it constitutes a bare numerical majority within the\ndistrict.” Mo. St. Conf. of the NAACP v. Ferguson-Florissant Sch. Dist., 894\nF.3d 924, 933 (8th Cir. 2018) (collecting cases from the Second, Fifth, Eleventh,\nand D.C. Circuits).\n Defendants try to distinguish these cases and others by arguing that\nthey addressed at-large elections rather than single-member districts. But\nnothing in these cases turned on that feature. And one court of appeals case\ndirectly confronting the question rejected a bar on vote dilution claims for\ngroups that make up more than 50% of the challenged single-member district.\nKingman Park Civic Ass’n v. Williams, 348 F.3d 1033, 1041 (D.C. Cir. 2003)\n(agreeing with Salas and Moore in a single-member district vote dilution case).\nSo did a recent three-judge panel in this circuit. See Perez v. Abbott, 253 F.\nSupp. 3d 864, 879–90 (W.D. Tex. 2017) (rejecting Defendants’ position when\nfinding vote dilution in a congressional district with a Hispanic voting-age\npopulation of 58.5%).\n Against all this authority of both old and recent vintage, all Defendants\ncan point to is Justice Kennedy’s opinion in Bartlett v. Strickland, 556 U.S. 1\n(2009) (opinion of Kennedy, J.). 6 Here is the statement they contend supports\na categorical rule that there can be no Voting Rights Act violation when a racial\ngroup exceeds 50% of the district’s population: “Where an election district could\n\n\n 6The defendants also cite Jeffers v. Beebe, 895 F. Supp. 2d 920, 932 (E.D. Ark. 2012),\nas an example of a court employing their 50%+ bar on Section 2 claims. Even if they read\nthat case correctly, that holding is no longer good law in its circuit. See Mo. St. Conf. of the\nNAACP, 894 F.3d at 933.\n 17\n\n Case: 19-60133 Document: 00514887045 Page: 18 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\nbe drawn in which minority voters form a majority but such a district is not\ndrawn,” a Section 2 claim is possible. This is an “objective, numerical test.” Id.\nat 18. Assuming this opinion is the controlling one under Marks 7 (Justice\nKennedy wrote for only three judges), it is addressing a different question. He\nwas rejecting the concept of crossover districts and instead would require that\na vote-dilution plaintiff show that a district could be drawn in which the racial\ngroup is a majority. Id. at 15-20. In fact, that is the first showing Gingles\nrequires. LULAC, 548 U.S. at 425 (noting the first “condition[] for establishing\na § 2 violation” is that “the racial group is sufficiently large and geographically\ncompact to constitute a majority in a single-member district” (cleaned up)).\nFrom that requirement it does not follow that vote dilution cannot occur when\nthe protected group already makes up a majority in the contested district. It\nis thus not surprising that no court has read Bartlett to override the widely\naccepted view that the voting strength of a protected group can still be diluted\nwhen that group is a majority of a challenged district. Indeed, if any opinion\nfrom Justice Kennedy addresses the question before us, it is his recognition in\nLULAC that “it may be possible for a citizen voting-age majority to lack real\nelectoral opportunity.” Id. at 428.\n Recognizing this robust caselaw rejecting Defendants’ per se rule\n(including in single-member cases), the dissent relies on an argument the\nDefendants have never made: that there needed to be a finding of cracking or\npacking minority voters. We typically will not consider arguments not\nadvanced by a party. State Indus. Prods. Corp. v. Beta Tech Inc., 575 F.3d 450,\n456 (5th Cir. 2009). That principle makes even more sense in the stay context.\n\n\n 7See Marks v. United States, 430 U.S. 188, 193 (1977) (“When a fragmented Court\ndecides a case and no single rationale explaining the result enjoys the assent of five Justices,\nthe holding of the Court may be viewed as that position taken by those Members who\nconcurred in the judgments on the narrowest grounds.” (quotation omitted)).\n 18\n\n Case: 19-60133 Document: 00514887045 Page: 19 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\nIf a “party is not entitled to a stay as a matter of right” even based on objections\nit raised before the district court and in requesting a stay, Campaign for\nSouthern Equality v. Bryant, 773 F.3d 55 (5th Cir. 2014), it should not be\nentitled to that extraordinary remedy based on arguments the district court\nnever had the chance to consider.\n Even if we could grant a stay based on a challenge to the judgment\nDefendants do not raise, the dissent’s position misses the marks on the merits.\nIt argues that vote dilution can occur in a 50%-plus district only if the dilution\nis the result of cracking or packing minority voters. The terms cracking\n(dividing minority voters among various districts to weaken their strength)\nand packing (concentrating minority voters in one or a small number of\ndistricts where they make up an excessive majority and thus reduce that\ngroup’s influence in other districts) describe gerrymandering techniques. Gill\nv. Whitford, 138 S. Ct. 1916, 1924 (2018) (describing the practice in challenge\nalleging partisan gerrymander); Shaw v. Reno, 509 U.S. 630, 670 (1993)\n(White, J., dissenting) (same in challenge alleging racial gerrymander). They\nexplain why vote dilution is occurring. Gill, 138 S. Ct. at 1931. The terms can\nthus be used to describe types of Section 2 vote dilution claims. See, e.g.,\nVoinovich v. Quilter, 507 U.S. 146, 153 (1993). But the “cracking” or “packing”\ndescription does not result in a different Section 2 test or finding. Whether the\ntheory for dilution is cracking or packing or something else, Section 2 claims\nare evaluated by first looking at the three Gingles factors to determine whether\ndemographics, geography, and voting behavior would allow the creation of a\ndistrict in which the minority group has electoral power. LULAC, 548 U.S. at\n425. If the plaintiffs satisfy that threshold, then a court considers the “totality\nof the circumstances” to determine if “members of a racial group have less\n\n\n\n 19\n\n Case: 19-60133 Document: 00514887045 Page: 20 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\nopportunity than do other members of the electorate.” Id. at 425–26. The\ndistrict court faithfully followed this path. 8\n Although cracking and packing are not official parts of the Section 2\nanalysis, as a matter of arithmetic vote dilution will often exist because of\ncracking or packing. Put another way, minority voting strength is often\nweaker than demographics would allow because those voters have been\ncrammed into one district with a very high minority percentage and thus\ndiluted in other districts (packing) or spread among various districts when they\ncould have formed an electoral majority in at least one (cracking). Indeed, the\ndistrict court’s findings demonstrate cracking occurred here. 9 District 22 has\na BVAP of 50.77% and District 23 has a BVAP of 42.00% when, as the remedy\nadopted by the district court demonstrates, African-Americans could easily\nform sufficient electoral strength to elect their representative of choice in at\nleast one of these two districts.\n The district court correctly focused on the Section 2 factors as prescribed\nby the Supreme Court and the Voting Rights Act. Part of the reason it found\nthat the <51% majority of African-American voters in the district did not result\nin an ability to elect a representative of that group’s choosing was because of\nturnout in off-year elections. So the “50%-plus” issue is largely an attempt to\npackage Defendants’ challenge to the factual finding in a more favorable\nstandard of review. But as with any other factual finding, the clearly\n\n\n 8 It is thus not true that the district court thought that “simply because a district can\n\nbe drawn in a way that will guarantee a minority an election win, the Voting Rights Act\ncompels that such a district be drawn.” Dissenting Op. at 7–8. The district court considered\nall of the statutorily prescribed factors in finding vote dilution. The dissent is also wrong in\nsaying that the district court thought a 62% African-American district was required. See id.\nThat is just the demographics of the remedy it adopted that changed only 28 precincts. To\nsay that the court thought that percentage was a requirement is to say that any time a\ndistrict court remedies a Section 2 violation it is creating a new minimum.\n9 There was no need to use the cracking label because Defendants never made the argument\n\nthe dissent advances.\n 20\n\n Case: 19-60133 Document: 00514887045 Page: 21 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\nerroneous standard means it is unlikely to be disturbed on appeal. That is\nparticularly true when the factfinder gives a sound reason for crediting one\nside’s evidence over the other’s. The district court did that in explaining why\nit relied on Plaintiffs’ expert for turnout data rather than Census Bureau\nfigures. The Census Bureau’s election data is for even-year elections, while\nMississippi conducts odd-year state senate elections.\n Defendants have not shown a high likelihood of overturning the finding\nof vote dilution because their legal argument is at odds with “unimpeachable\nauthority” from our court and their factual challenges must overcome\ndeferential standards of review.\n B.\n\n Defendants also argue that the district court erred by not dismissing the\nlawsuit on laches grounds, focusing entirely on Thomas’s delay in bringing this\nlawsuit. Even if he were the only plaintiff, the standard of review would again\npose a substantial obstacle for Defendants to overcome on appeal. A district\ncourt’s equitable ruling on laches is reviewed for abuse of discretion, and the\nfactual findings of delay, inexcusability, and prejudice that underlie it are\nreviewed for clear error. See Retractable Tech., Inc. v. Becton Dickinson & Co.,\n842 F.3d 883, 898 (5th Cir. 2016).\n More problematic than that for Defendants, Thomas is not the only\nperson who brought this suit. The stay motion makes no argument for why\nlaches should bar the lawsuit as to Plaintiffs Ayers and Lawson. As with all\naffirmative defenses, the party asserting a laches defense bears the burden of\nproving it. See City of El Paso, Tex. v. El Paso Entm’t, Inc., 382 F. App’x 361,\n366 (5th Cir. 2010). Defendants did not even attempt to meet this burden for\nAyers and Lawson. Nor is there, despite the dissent’s attempt to salvage a\nlaches defense, an exception for the “main plaintiff,” whatever that means. Cf.\n\n 21\n\n Case: 19-60133 Document: 00514887045 Page: 22 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\nMassachusetts v. EPA, 549 U.S. 497, 518 (2007) (observing that only one\npetitioner needed to have standing to bring suit). The Voting Rights Act\nprotects the rights of voters, not politicians. As to voters Ayers and Lawson,\nDefendants point to nothing showing that a laches defense is likely to succeed\non appeal.\n V.\n A.\n The final ground on which Defendants seek a stay is the remedy the\ndistrict court ordered. The standard of review again poses a challenge: the\ndistrict court’s remedy is reviewed for abuse of discretion. Rodriguez v. Bexar\nCnty., Tex., 385 F.3d 853, 870 (5th Cir. 2004).\n But “whenever practicable . . . a reasonable opportunity [should be\nafforded] the legislature to meet constitutional requirements by adopting a\nsubstituted measure rather than for the federal court to devise and order into\neffect its own plan.” Veasey, 830 F.3d at 270 (quoting Wise v. Lipscomb, 437\nU.S. 535, 540 (1978) (opinion of White, J.)) (emphasis original). As recounted\nabove, the district court first honored this principle in noting it would allow\ntime for a legislative fix before it would redraw the district. When the court\nwas informed that the legislature would not act until it saw the outcome of the\nstay requests, the district court went ahead and redrew the lines given\nconcerns about the candidate qualifying deadline. It noted, however, that the\nlegislature always has the ability to redraw districts. Plaintiffs also point this\nout in their response to the stay motion.\n The legislature’s desire to wait to see the outcome of the stay ruling is\nunderstandable. It would have been inefficient for it to remedy a violation only\nto have this court grant a stay of the district court’s entire judgment on the\nground that Defendants were likely to overturn the finding of vote dilution.\n\n\n 22\n\n Case: 19-60133 Document: 00514887045 Page: 23 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\nBut now that we have concluded to the contrary, the legislature should have\nthe initial opportunity to draw new lines for District 22 that comply with the\nVoting Rights Act. The only reason not to give it that first shot at crafting a\nremedy is the candidate filing deadline, but the Secretary of State is requesting\nthe legislative fix and has not indicated that a further extension of that\ndeadline for the affected districts is problematic. And while the legislature is\nalways able to redraw lines, the remedial preference is for it to have the first\nchance to remedy a Section 2 violation, not for it to act only after the court\ndraws a new district, which would result in three different districts in a short\ntime period. United States v. Brown, 561 F.3d 420, 435 (5th Cir. 2009).\n We thus issued an order on March 15 granting a temporary stay to allow\nthe legislature until April 3 to remedy the Section 2 violation. The order also\nextended the candidate filing deadline for any affected districts until April 12.\n B.\n Defendants otherwise are not likely to surmount the abuse of discretion\nstandard in challenging the court’s remedy. If the legislature does not act and\nthe judicial remedy goes into effect, it must still respect the legislature’s policy\nobjectives as much as possible. See Perry v. Perez, 565 U.S. 38, 393 (2012). The\nremedy is a narrowly-tailored one that does that. While redistricting cases\noften result in redrawing the entire state or at least several districts, this\nremedy moves just 28 precincts, less than 2% of the precincts in the state. The\nremedy affects only 2 of Mississippi’s 52 Senate districts. The court found that\nthe new lines met traditional redistricting criteria: compactness, contiguity,\npreservation of political subdivisions like counties and cities, and avoiding\npairing incumbents. It adopted the proposed map of an expert it found credible\nwho also determined that the new map honored traditional criteria of\ncompactness and contiguity. In fact, the new district is more consistent with\n\n\n 23\n\n Case: 19-60133 Document: 00514887045 Page: 24 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\ntraditional geographic divisions in one important respect: it removes the\nsuburban Madison county precincts and thus limits the district to counties in\nthe rural and agricultural Delta.\n The slightly altered districts are, if anything, also more compact than\nthey were before. The following map of the new and old districts show the\nlimited impact of the court’s remedy. The orange and pink highlighting shows\nthe new districts; the blue lines show the old ones.\n\n\n\n\n 24\n\n Case: 19-60133 Document: 00514887045 Page: 25 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\n Defendants’ main critique is that the new lines split Vicksburg between\nthe districts. But some splitting of counties or cities is inevitable given equal\npopulation requirements. A look at the statewide senate districts reveals this.\nThe lines the legislature drew split at least eight cities with populations\nbetween 23,000 and 27,000 residents (Vicksburg had a population of 26,407\nwhen the 2012 maps were drawn) into different senate districts, including\nClinton, whose 25,216 citizens are split among 5 districts. Having to split\nVicksburg thus does not lack fidelity to the legislature’s redistricting policy\nwhich often results in the same situation. Defendants have not demonstrated\na high likelihood of showing that that district court’s narrow redraw was an\nabuse of discretion.\n C.\n The dissent also contends that the district court’s remedy interferes with\nongoing election preparation, though the Defendants—including the Secretary\nof State—do not cite this as a reason for a stay. In a recent case denying a stay\nin a voting rights case, we did not consider this issue when government officials\ndid not argue that the district court’s plan would substantially disturb the\nelection process. Patino v. City of Pasadena, 677 F. App’x 950, 951–52 (5th Cir.\n2017).\n The election is even further away in this case than it was in Patino. Id.\n(denying stay sought during the candidate registration period with election\nthree months away); see also Patino v. City of Pasadena, 229 F. Supp. 3d 582,\n585 (S.D. Tex. 2017) (providing the relevant dates). Primary voting is more\nthan four months away; the general election is more than seven months away.\nThat distance to the election means the potential for voter confusion that\n\n\n\n\n 25\n\n Case: 19-60133 Document: 00514887045 Page: 26 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\nanimates this concern, Purcell v. Gonzalez, 549 U.S. 1, 4 (2006), is absent. 10\nMississippi voters in the 28 affected precincts will go to the same voting\nlocation they always have, face the same voting requirements, and have\nmonths to research the candidates in advance of the election. Indeed, the effect\nof redrawing some of the lines for just two state senate districts with elections\nmonths away pales in comparison to the impact of statewide redistricting that\nhas been implemented in a similar timeframe. See, e.g., Covington v. North\nCarolina, 2018 WL 604732 (M.D. N.C. 2018); Common Cause v. Rucho, 284 F.\nSupp. 3d 780 (M.D. N.C. 2018); Larios v. Cox, 305 F. Supp. 2d 1335 (N.D. Ga.\n2004).\n With no risk of voter confusion, and no outcry from state officials that\nimplementing the district court’s remedy substantially disturbs its election\nprocess, this is not a basis for a stay.\n D.\n One final comment is necessary to set the record straight in response to\nthe dissent’s attack on the remedy. It irresponsibly insinuates that the district\njudge—whom it takes the unusual step of repeatedly naming—drew new lines\nwith the aim of eliminating partisan opposition to Plaintiff Thomas. That is\nnot true. Importantly, the incumbent state senator in District 22 had decided\nnot to run for reelection before the district court ruled in this case. The\ndissent’s conjecture also ignores that primary candidates file with the political\nparty (not the state), with the parties notifying state officials of the candidates\n\n\n 10 As most of the cases cited by the dissent show, the voter confusion concern is\ntypically greatest when a court alters election procedures (as opposed to districts) with an\nelection quickly approaching. See Veasey v. Perry, 769 F.3d 890, 892 (5th Cir. 2014) (staying\ndistrict court injunction striking down voter ID laws); Purcell, 549 U.S. at 1 (same); North\nCarolina v. League of Women Voters of N.C., 135 S. Ct. 6 (2014) (staying district court order\nthat changed voter ID requirements, voting hours, voting locations, and voter registration);\nHusted v. Ohio State Conference of NAACP, 135 S. Ct. 42 (2014) (staying district court order\nthat changed voting hours).\n 26\n\n Case: 19-60133 Document: 00514887045 Page: 27 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\nonly after the filing deadline. That had not yet occurred when the court issued\nfinal judgment.\n In light of these circumstances, there is no basis for believing that the\nPlaintiffs’ expert who drew the proposed remedy back in mid-January, or the\ndistrict court that later adopted it, knew who the new candidates would be. No\none brought the names or residences of the candidates to the court’s attention\nprior to its remedy ruling. And the district court issued its remedy before the\ninitial candidate qualifying deadline, so there may have been additional\ncandidates. Not until after the court issued its remedy, in a motion for stay,\ndid Defendants bring to the court’s attention the fact that two candidates\nwould no longer reside in District 22. On learning this, the district court\nlamented that it was not told prior to its ruling. As for the competition in the\nnew district, we do not know who has filed nor who will file prior to the new\nqualifying deadline.\n ***\n Per the order issued last week, the motion for stay is GRANTED IN\nPART and DENIED IN PART. A majority of the panel concludes Defendants\nhave satisfied the stay factors only based on the need to give the legislature\nand Governor an opportunity to remedy the Section 2 violation. A stay is\nentered for that purpose until April 3, 2019. The candidate filing deadline for\nany districts whose lines are redrawn (whether by the legislature, or if it does\nnot act, per the district court’s remedy) is extended to April 12, 2019. The\ndistrict court has jurisdiction to consider any challenges to the adequacy of a\nlegislative remedy.\n\n\n\n\n 27\n\n Case: 19-60133 Document: 00514887045 Page: 28 Date Filed: 03/25/2019\n\n\n\n No. 19-60133\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Joseph Thomas v. Phil Bryant\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-25\\nOpinion type: majority\\nHas dissenting opinion: Yes\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 19-60133 Document: 00514887045 Page: 1 Date Filed: 03/25/2019\\n\\n\\n\\n\\n REVISED March 25, 2019\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT United States Court of Appeals\\n Fifth Circuit\\n\\n ___________________ FILED\\n March 22, 2019\\n No. 19-60133 Lyle W. Cayce\\n ___________________ Clerk\\n\\nJOSEPH THOMAS; VERNON AYERS; MELVIN LAWSON,\\n\\n Plaintiffs - Appellees\\n\\nv.\\n\\nPHIL BRYANT, Governor of the State of Mississippi,; DELBERT\\nHOSEMANN, Secretary of State of the State of Mississippi, both in the\\nofficial capacities of their own offices and in their official capacities as\\nmembers of the State Board of Election Commissioners,\\n\\n Defendants - Appellants\\n\\n _______________________\\n\\n Appeal from the United States District Court\\n for the Southern District of Mississippi\\n _______________________\\n\\nBefore DENNIS, CLEMENT, and COSTA, Circuit Judges.\\nGREGG COSTA, Circuit Judge:\\n A district court found that the boundaries for Mississippi State Senate\\nDistrict 22 dilute African-American voting strength and prevent those citizens\\nfrom having the equal opportunity “to participate in the political process and\\nto elect representatives of their choice” that the Voting Rights Act guarantees.\\n52 U.S.C. § 10301(b). To remedy the violation, the district court switched 28\\n\\n Case: 19-60133 Document: 00514887045 Page: 2 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nprecincts between District 22 and a bordering district. The Governor and\\nSecretary of State seek a stay of the final judgment.\\n I.\\n Most of District 22 lies in the heart of the Mississippi Delta. Those\\nunfamiliar with the state’s geography might think that the Mississippi Delta\\nis in the southern portion of the state that is closer to the mouth of the\\nMississippi River. But the “Delta” refers not to the outlet of that mighty river\\ninto the Gulf of Mexico, but to the alluvial plain between the Mississippi River\\nand the Yazoo River. John M. Barry, RISING TIDE: THE GREAT MISSISSIPPI\\nFLOOD OF 1927 AND HOW IT CHANGED AMERICA 96 (1997). It is located in the\\nnorthwest section of Mississippi and looks like an “elongated diamond.” Id.\\nThe district court recited this colorful description of its boundaries: “The\\nMississippi Delta begins in the lobby of the Peabody Hotel [in Memphis] and\\nends on Catfish Row in Vicksburg.” David L. Cohn, GOD SHAKES CREATION\\n(1935).\\n The sediment that the Mississippi River deposited in this region over the\\nmillennia made Delta soil some of the richest in the world. Barry, supra, at\\n97. And that soil made the Delta one of the leading cotton-producing areas in\\nthe world. One historian compared the influence the Delta once held over\\nglobal cotton prices to the modern influence of Saudi Arabia over oil prices.\\nSven Beckert, EMPIRE OF COTTON: A GLOBAL HISTORY 113 (2014).\\n But before agriculture could prosper in the Delta its forests of hardwood\\ntrees had to be cleared. Slaves were forced to begin that process, and\\nemancipated slaves finished it in the latter part of the nineteenth century.\\nSince that time, African-Americans have been a majority in the Delta. In the\\nearly twentieth century, they made up almost 90% of the region’s population.\\nBarry, supra, at 125 (noting that in 1908 the Delta had “a black population of\\n\\n\\n 2\\n\\n Case: 19-60133 Document: 00514887045 Page: 3 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nat least 171,209” and “a white population of 24,137”). The Great Migration to\\nthe north reduced the African-American percentage, but they remain a\\nsizeable majority in the region.\\n Of course, for most of their time laboring in the Delta, African-Americans\\ncould not vote. The Voting Rights Act changed that. It has resulted in\\nnumerous African-Americans being elected to office in the Delta. Indeed, the\\nState of Mississippi has more African-American elected officials than any other\\nstate. U.S. Census Bureau, STATISTICAL ABSTRACT OF THE UNITED STATES:\\n2011, 258 (130th ed.).\\n But in places like the state legislature, African-Americans have still not\\nachieved political power in Mississippi that comes close to their share of the\\npopulation. This case involves a claim that one state senate district\\ncontributed to that underrepresentation by diluting the voting strength of\\nAfrican-Americans that Delta demographics and geography should otherwise\\nsupport.\\n District 22 includes all or part of five Delta counties: Bolivar,\\nHumphreys, Sharkey, Washington, and Yazoo. It also includes parts of one\\nnon-Delta county: Madison. The addition of the white-majority Madison\\nCounty precincts in the last redistricting reduced the African-American\\npercentage in District 22. Overall the district still has an African-American\\nmajority, but just barely at 50.7%. 1 Without the non-Delta precincts from\\n\\n\\n\\n 1 Plaintiff Thomas told the Department of Justice that the 50.7% figure includes the\\npopulation of the Yazoo City federal prison, the majority of whose inmates he says are\\nAfrican-American. He contended that without including that prison, African-Americans\\nwould not be a majority in the district. It is questionable whether disenfranchised people\\nshould be included in the BVAP (black voting age population) calculation for purposes of the\\nVoting Rights Act. The focus is usually on those eligible to vote, thus the typical requirement\\nin our circuit that the percentage focus on those of voting age who are citizens. See Reyes v.\\nCity of Farmers Branch, Tex., 586 F.3d 1019, 1023 (5th Cir. 2009) (noting that only citizens\\nare included in population calculations).\\n 3\\n\\n Case: 19-60133 Document: 00514887045 Page: 4 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nMadison County, that percentage would be much higher.\\n The candidate preferred by the black majority did not prevail in the 2015\\nelection. The losing candidate those voters did prefer (Joseph Thomas), along\\nwith two voters (Vernon Ayers and Melvin Lawson), brought this lawsuit in\\n2018 alleging that the district violated of Section 2 of the Voting Rights Act.\\n Last month, the district court held a bench trial and agreed. It concluded\\nthat the threshold Gingles factors for establishing vote dilution existed. The\\nAfrican-American population is “sufficiently large and geographically compact”\\nto constitute a majority with electoral power in the district; that racial group\\nis politically cohesive; but the white population voted as a bloc to prevent\\nAfrican-Americans from electing their chosen candidate. LULAC v. Perry, 548\\nU.S. 399, 425 (2006). The bloc voting by both racial groups was stark: in 10\\nelections within district 22, the candidate favored by African-Americans\\nreceived between 82% and 93% of their vote but only between 8% and 19% of\\nthe white vote.\\n The district court then followed the statutory directive to consider the\\n“totality of circumstances” in determining whether African-Americans “have\\nless opportunity than other members of the electorate to participate in the\\npolitical process and to elect representatives of their choice.” 52 U.S.C.\\n§ 10301(b); LULAC, 548 U.S. at 425–26. It credited Plaintiffs’ expert’s analysis\\nof voter participation as more rigorous and concluded that African-American\\nturnout was depressed in off-year elections—that is, odd-year elections without\\nfederal races—which is when Mississippi elects its legislature. The district\\ncourt also highlighted the persistent representation gap in the Mississippi\\nSenate, as well as substantial socioeconomic differences between black voters\\nand white voters in the district.\\n After finding a Voting Rights Act violation, the court initially declined to\\n\\n\\n 4\\n\\n Case: 19-60133 Document: 00514887045 Page: 5 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\norder a remedy so “the Mississippi Legislature [could] consider[] whether to\\nredraw the District and extend the candidate qualification deadline.”\\nAlthough the primary and general elections were months away, the deadline\\nfor candidate filing was March 1.\\n A flurry of procedural moves followed at warp speed. Three days after\\nthe court made its trial findings, the Governor and Secretary of State\\n(Defendants) 2 filed a motion a motion to stay with the district court and also\\nfiled an appeal, arguing that the ruling was an appealable interlocutory\\ninjunction. Less than a week later, they asked this court to stay the district\\ncourt’s ruling. That same day, Plaintiffs asked the court to extend the\\nqualification deadline in District 22 and bordering District 23 (the other\\ndistrict affected by the proposed remedy) by two weeks. Later that day, the\\ndistrict court ordered Defendants to update it on any progress, if any, in\\nlegislative redrawing of District 22.\\n The next day, Defendants filed a brief opposing Plaintiffs’ motion to\\nextend the qualification deadline, in which they stated that they had contacted\\nthe leadership of the legislative chambers. The Senate leaders had said that\\n“should the stay motions pending before [the district court] and the Fifth\\nCircuit be denied, the Senate desire[d] the opportunity to enact a new\\nredistricting plan redrawing Senate District 22.” Late that same day, the\\ndistrict court ruled that, because the legislature was unwilling to act, the first\\nmap drawn by one of Plaintiffs’ experts would be adopted as the boundaries of\\nDistricts 22 and 23. The court also moved the qualification deadline to March\\n\\n\\n\\n\\n 2 The third defendant, Attorney General Jim Hood, did not join these motions or this\\nappeal.\\n 5\\n\\n Case: 19-60133 Document: 00514887045 Page: 6 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\n15 for the two affected senate districts. The court also declined to enter a stay\\nand entered final judgment.\\n The final judgment caused our court to dismiss the appeal of the\\npreliminary ruling. Thomas v. Bryant, 2019 WL 994034 (5th Cir. Feb. 28,\\n2019). But by that time the Defendants had already appealed from the final\\njudgment, and not long after that they sought a stay pending the new appeal,\\nwhich is the motion before this panel. 3\\n This is the effect of the final judgment: It switches some precincts\\nbetween Districts 22 and 23. It extends the candidate filing deadline to March\\n15. In terms of other upcoming deadlines, the primary election is August 6,\\nwith a June 22 deadline to send ballots to troops overseas. The general election\\nis November 5.\\n II.\\n The stay Defendants seek is an extraordinary remedy. Nken v. Holder,\\n556 U.S. 418, 437 (2009) (Kennedy, J., concurring). It is also an equitable one\\ncommitted to this court’s discretion. Id. at 433; Ruiz v. Estelle, 666 F.2d 854,\\n856 & n.4 (5th Cir. 1982). Four factors guide the exercise of our discretion:\\n1) whether the applicant has made a strong showing of likelihood to succeed\\non the merits; 2) whether the movant will be irreparably harmed absent a stay;\\n3) whether issuance of a stay will substantially injure other interested parties;\\nand 4) where the public interest lies. Nken, 556 U.S. at 434. The first two\\nfactors are usually the most important. Id.; ODonnell v. Goodhart, 900 F.3d\\n220, 223 (5th Cir. 2018).\\n In this case, the likelihood of success ends up being dispositive. That is\\nbecause Defendants can establish irreparable harm. A court order preventing\\n\\n\\n 3 Before seeking the stay pending appeal for the second time in our court after entry\\nof final judgment, Defendants also sought a stay in the district court for the second time. The\\ndistrict court denied that motion.\\n 6\\n\\n Case: 19-60133 Document: 00514887045 Page: 7 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nenforcement of a state law, including the drawing of legislative lines,\\nconstitutes that harm. Abbott v. Perez, 138 S. Ct. 2305, 2324 n.17 (2018). And\\nthat injury may be irreparable in light of the meaningful possibility (but not\\ncertainty) that a full appeal cannot be decided in time to provide Defendants\\nrelief before this year’s senate elections. But Plaintiffs face the same risk that\\nthe appellate ruling will prove futile should this court grant a stay. And the\\ninjury they seek to prevent—holding an election under an unlawful plan with\\ndiscriminatory effects—is also, it should go without saying, a serious one.\\nVeasey v. Abbott, 830 F.3d 216, 270 (5th Cir. 2016) (en banc) (“It would be\\nuntenable to permit a law with a discriminatory effect to remain in operation\\nfor that election.”); cf. Reynolds v. Sims, 377 U.S. 533, 585 (1964) (“[I]t would\\nbe the unusual case in which a court would be justified in not taking\\nappropriate action to insure that no further elections are conducted under the\\ninvalid plan.”). So Defendants’ entitlement to a stay turns on whether they\\nhave a strong likelihood of success.\\n III.\\n We will first address Defendants’ attempt to make that showing with a\\njurisdictional argument. They contend that a three-judge court should have\\ndecided this case. The statute says that a “district court of three judges shall\\nbe convened when otherwise required by Act of Congress, or when an action is\\nfiled challenging the constitutionality of the apportionment of congressional\\ndistricts or the apportionment of any statewide legislative body.” 28 U.S.C.\\n§ 2284(a). The Voting Rights Act does not require three-judge courts for\\nSection 2 cases (notably it does for Section 5 cases, 52 U.S.C. § 10304(a)), so\\nDefendants focus on the latter part of the statute. They contend that\\n“constitutionality” modifies only challenges to apportionment of congressional\\ndistricts, not challenges to apportionment of state legislatures. On their\\n\\n\\n 7\\n\\n Case: 19-60133 Document: 00514887045 Page: 8 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nreading, any challenge to state legislative redistricting—including the\\nstatutory Voting Rights Act one asserted here—requires a three-judge panel.\\n Defendants requested a three-judge panel late in the litigation, a week\\nbefore trial. Failing to request such a panel in their answer may have forfeited\\nthe issue unless it is a jurisdictional requirement. The three-judge statute has\\nconflicting language on whether it is one. It begins by saying “a district court\\nof three judges shall be convened” for specified cases. 28 U.S.C. § 2284(a). That\\nmandatory language sounds jurisdictional. So does the statute’s prohibition\\non a single judge taking certain actions, including granting injunctive relief.\\nId. § 2284(b)(3). But the statute also says that the procedure for convening a\\nthree-judge court kicks in “[u]pon the filing of a request for three judges.” Id.\\n§ 2284(b)(1). That does not sound jurisdictional. If the requirement is\\njurisdictional, then the single district judge first assigned the case would\\nseemingly have an obligation to convene a three-judge panel even if a party\\ndoes not ask for it.\\n Recognizing these conflicting statutory signals, the leading federal\\nprocedure treatise is ambivalent about whether Section 2284 is jurisdictional.\\nSee 17A Charles Alan Wright et al., FED. PRAC. & PROC. § 4235, at 206–08 (3d\\ned. 2007). But apparently the courts that have considered the question—\\nincluding ours in a nonbinding decision—have treated Section 2284 as\\njurisdictional. See Kalson v. Patterson, 542 F.3d 281, 287 (2nd Cir. 2008);\\nArmour v. Ohio, 925 F.2d 987, 989 (6th Cir. 1991) (en banc); LULAC of Texas\\nv. Texas, 318 F. App’x 261, 264 (5th Cir. 2009). That consensus in the caselaw\\nmeans that forfeiture is an obstacle Defendants will likely be able to overcome\\non appeal.\\n Defendants’ delay in raising this issue does, however, say something\\nabout its merits. At the outset of this lawsuit, it was not obvious to Defendants\\n\\n\\n 8\\n\\n Case: 19-60133 Document: 00514887045 Page: 9 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\n(or Plaintiffs or the district judge for that matter) that its exclusively statutory\\nclaims required a three-judge court. Indeed, no reported case has ever used a\\nthree-judge panel for a case challenging district lines only under Section 2 of\\nthe Voting Rights Act. See Rural W. Tenn. African-American Affairs Council\\nv. Sundquist, 209 F.3d 835, 838 (6th Cir. 2000) (noting case reassigned to single\\njudge after dismissal of constitutional and Section 5 claims); Chestnut v.\\nMerrill, 2019 WL 338909 (N.D. Ala. 2019) (rejecting argument that a single\\njudge could not hear Section 2 challenge); Bone Shirt v. Hazeltine, 336 F. Supp.\\n2d 976, 980 (D. S.D. 2004) (same as Rural West); Old Person v. Brown, 182 F.\\nSupp. 2d 1002, 1003 (D. Mont. 2002) (single judge hearing Section 2 challenge);\\nsee also Armour, 925 F.2d at 989 (stating the jurisdictional test for Section\\n2284 as whether “there exists a non-frivolous constitutional challenge to the\\napportionment of a statewide legislative body” (emphasis added)). 4 That no\\ncourt has adopted Defendants’ reading of the three-judge statute in the more\\nthan four decades it has been on the books alone seems enough to prevent them\\nfrom showing a strong likelihood of succeeding on this issue. To be sure, only\\nthe Chestnut opinion from earlier this year addressed an argument like the one\\nDefendants make. But that is again telling: Before this year, it apparently had\\nnever dawned on a judge or party in a Section 2-only state redistricting case\\n\\n\\n\\n 4 Though uncited by Defendants or their amicus, the dissent finds Page v. Bartels, 248\\nF.3d 175 (3d Cir. 2001), “most significant[].” Dissenting Op. at 15. But unlike the cases cited\\nabove, Page does not involve a situation in which plaintiffs only brought Section 2 claims.\\nInstead, it involved both constitutional and statutory claims. Yet a single district court judge\\nattempted to spin off the statutory claims and deny an injunction based on them. Id. at 187.\\nThe Third Circuit said that when plaintiffs bring both claims, both must be sent to a three-\\njudge panel. Id. at 191. That is consistent with the common practice when both constitutional\\nand statutory challenges to reapportionment are brought—the constitutional hook for three-\\njudge jurisdiction sweeps in the statutory claims. While the dissent tries to find support for\\nits position in some of Page’s discussion of legislative history and policy, notably the Third\\nCircuit does not adopt the textual argument the dissent and amicus push.\\n\\n\\n 9\\n\\n Case: 19-60133 Document: 00514887045 Page: 10 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nthat a three-judge panel might be required. And that is because the most\\nstraightforward reading of the three-judge statute is that it applies only when\\nthe “constitutionality” of apportionment is being challenged.\\n So why does the dissent, adopting the argument of an amicus, think the\\nthree-judge statute applies to what is only a statutory challenge when no court\\nhas ever taken that view? One word—the “the” that precedes “apportionment\\nof any statewide legislative body.” 28 U.S.C. § 2284(a). Inclusion of that article\\nmeans, in their view, that “constitutionality” applies only to what immediately\\nfollows it: challenges to the “apportionment of congressional districts.” If\\n“constitutionality” does not also modify the “apportionment of any statewide\\nlegislative body,” id., then any challenges to those districts, including statutory\\nones, require a three-judge panel.\\n The textual argument is a dispute about application of the “series\\nmodifier” canon of construction. It normally means that a modifier\\n(“constitutionality” in Section 2284) applies to an entire series of parallel\\nterms. See Scalia & Garner, READING LAW: THE INTERPRETATION OF LEGAL\\nTEXTS 147 (2012). The district court concluded that principle supports reading\\nthe statute as applying to constitutional challenges to apportionment of both\\ncongressional and state legislative seats. But an amicus supporting the\\ndefendants argues the “the” coming before “apportionment of any statewide\\nlegislative body” breaks the series modifier. The amicus notes that a\\n“determiner” word, such as the “the” in Section 2284(a), is an indication that a\\nmodifier should not reach the second element. 5 See id. at 148–49.\\n\\n\\n\\n 5 Defendants make a different textual argument in support of their position that this\\ncase belongs with a three-judge court. They focus not just on the “the,” but on “the\\napportionment” that precedes “of any statewide legislative body.” They contend it is\\nsuperfluous if it does not break off the “constitutionality” modifier. But it may be\\n“appropriate to tolerate a degree of surplusage.” United States v. Atl. Research Corp., 551\\n 10\\n\\n Case: 19-60133 Document: 00514887045 Page: 11 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\n But inferring that “the” was meant to cut off the “constitutionality”\\nmodifier ignores what may be the most important teaching about the series\\nmodifier canon from the Scalia and Garner book on statutory interpretation:\\n“Perhaps more than most of the other canons, this one is highly sensitive to\\ncontext.” Id. at 150. That context supports the natural reading that courts have\\nlong given it: that “constitutionality” modifies both “the apportionment of\\ncongressional districts” and “the apportionment of any statewide legislative\\nbody.” That Congress wanted the two phrases to sound the same—“the\\napportionment of congressional districts” and “the apportionment of any\\nstatewide legislative body” are word-for-word identical, with the exception of\\nthe type of district that they reference—is consistent with how ordinary people\\nspeak and write. See Lockhart v. United States, 136 S. Ct. 958, 970 (2016)\\n(Kagan, J., dissenting). To illustrate this, consider what a reader would think\\nafter seeing the following in the newspaper: “The NCAA is investigating the\\nrecruiting practices of the football program and the basketball program.” As\\nwith the three-judge statute, the final “the” may not be necessary. But would\\nit make the reader think the investigation into the basketball program is not\\nlimited to recruiting violations, but also might include point shaving or ticket\\nscalping violations? Of course not. The dissent’s textual argument about the\\nthree-judge statute is just as detached from common usage.\\n What is more, giving so much significance to “the” runs counter to\\nanother point Justice Scalia made about statutory interpretation: that\\nCongress “does not . . . hide elephants in mouseholes.” Whitman v. Am.\\nTrucking Ass’n, 531 U.S. 457, 468 (2001). The historical development of the\\nthree-judge statute—that is, statutory history as opposed to the more\\n\\n\\n\\nU.S. 128, 137 (2007). Indeed, one could make the case that even the first “the,” the one before\\n“apportionment of congressional districts,” is unnecessary.\\n 11\\n\\n Case: 19-60133 Document: 00514887045 Page: 12 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\ncontroversial legislative history Defendants rely on—shows why it would have\\nbeen so significant and anomalous to require three-judge panels for statutory\\nclaims. The statute was first enacted in the aftermath of Ex parte Young to\\nrequire three judges to hear what Congress thought would be an increasing\\nnumber of suits challenging state laws “upon the ground of the\\nunconstitutionality of such statute.” 28 U.S.C. § 2281 (1970); see generally\\nDavid P. Currie, The Three-Judge District Court in Constitutional Litigation,\\n32 U. CHI. L. REV. 1, 5–8 (1964). When courts later struck down many New\\nDeal reforms, one of the only aspects of President Roosevelt’s court-packing\\nplan to become law was a measure also requiring three-judge panels for suits\\nseeking to enjoin “any Act of Congress for repugnance to the Constitution of\\nthe United States.” 28 U.S.C. § 2282 (1970); see Wright, FED. PRAC. & PROC.\\n§ 4234, at 194–95. Both laws’ focus on only constitutional challenges made\\nsense as striking down democratically enacted laws is “the gravest and most\\ndelicate duty” courts are “called on to perform.” Nw. Austin Mun. Util. Dist.\\nNo. One v. Holder, 557 U.S. 193, 204 (2009) (referring to striking down an Act\\nof Congress (quoting Blodgett v. Holden, 275 U.S. 142, 147–48 (1927) (Holmes,\\nJ., concurring))). The idea of requiring three judges for this “class of cases of\\nspecial importance” was to “assure more weight and greater deliberation by\\nnot leaving the fate of such litigation to a single judge.” Phillips v. United\\nStates, 312 U.S. 246, 249–50 (1941) (first quotation from Ex parte Collins, 277\\nU.S. 565, 567 (1928)). But in the mid-1970s, Congress decided to scrap just\\nabout all of the three-judge regime because it was burdening the Supreme\\nCourt and lower courts and had resulted in procedural complexities. See\\nWright, FED. PRAC. & PROC. § 4234, at 195–98; Kalson, 542 F.3d at 287 (noting\\nthat the 1976 Act “vastly reduced the category of cases for which a three-judge\\ncourt is mandated”). It nonetheless decided to retain the procedure for a small\\n\\n\\n 12\\n\\n Case: 19-60133 Document: 00514887045 Page: 13 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nset of important cases: constitutional challenges to redistricting for\\ncongressional and state legislative seats, then-recent phenomena in the\\naftermath of the revolutionary one person, one vote line of cases. See, e.g.,\\nReynolds v. Sims, 377 U.S. 533 (1964). If Congress had intended to expand the\\nstatute it was otherwise contracting by applying it for the first time to\\nstatutory challenges there were certainly better ways to do it than by stealthily\\ninserting an extra “the.”\\n Reading the statute in the way Defendants suggest does not make sense\\nfor another reason: Why would Congress require three judges to hear statutory\\nclaims challenging state legislative redistricting but not congressional\\nredistricting? The dissent posits, without citing any authority, that perhaps\\nfederalism concerns would explain such a difference. But there are also strong\\nfederalism concerns with how a state chooses to divvy up its citizens into\\ncongressional districts. In fact, contemporary critics of the initial judicial foray\\ninto review of legislative apportionment viewed courts’ redrawing of\\ncongressional district as even more intrusive on traditional state prerogatives\\nthan judicial redrawing of state legislative districts. That is because of the\\nview that Article I, Section II of the Constitution grants “States . . . plenary\\npower to select their allotted Representatives in accordance with any method\\nof popular election they please, subject only to the supervisory power of\\nCongress.” Wesberry v. Sanders, 376 U.S. 1, 23 (1964) (Harlan, J., dissenting).\\n The other problem with the dissent’s theory—that Congress in 1976 had\\na special concern with statutory challenges to the drawing of state legislative\\ndistricts—is that it fails to grapple with the rarity of Section 2 challenges to\\nredistricting at that time. It was then not even clear that Section 2 provided a\\nprivate right of action. City of Mobile v. Bolden, 446 U.S. 55, 60 & n.8 (1980)\\n(assuming without deciding such a suit could exist). A few years later the\\n\\n\\n 13\\n\\n Case: 19-60133 Document: 00514887045 Page: 14 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nSupreme Court held Section 2 did not prohibit discriminatory effects which\\nmeant it provided no guarantee beyond what the Constitution already did. See\\nid. And the typical pre-1982 Section 2 claim that courts did consider was a\\nchallenge to at-large electoral systems, not the line drawing of single member\\ndistricts. See, e.g., id. In other words, there was no practice of statutory\\nchallenges to state legislative apportionment that Congress needed to address\\nin 1976.\\n To sum up, the dissent would give this much weight to the “the” that\\ncomes before “reapportionment of any statewide legislative body”: Insertion of\\nthat article would require three-judge panels for exclusively statutory claims—\\nfollowed by direct appeal to the Supreme Court, 28 U.S.C. § 1253—when the\\nthree-judge regime Congress was contracting in 1976 never did. It would\\nrequire those three-judge panels only for statutory challenges to\\napportionment of state legislative seats, not congressional ones. And it would\\ndo all this to address statutory challenges to apportionment of state\\nlegislatures when those claims hardly existed in 1976. An elephant indeed.\\n The dissent contends that there might have been clearer ways to\\nemphasize that the statute is limited to constitutional challenges. Dissenting\\nOp. at 12. But if Congress intended to include statutory-only challenges within\\nthe reach of the general three-judge statute for the first time, there were many\\neasy ways to make that clear. This brings up a final point on the jurisdictional\\nquestion. To the extent there is ambiguity, the longstanding principle that\\n“congressional enactments providing for the convening of three-judge courts\\nmust be strictly construed” comes into play. Allen v. State Bd. of Elections, 393\\nU.S. 544, 561 (1969); Phillips, 312 U.S. at 250 (noting the three-judge statue\\nshould be read narrowly because of its impact on the Supreme Court docket\\nand the burdens of convening three-judge courts).\\n\\n\\n 14\\n\\n Case: 19-60133 Document: 00514887045 Page: 15 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\n That rule of construction, the text of the three-judge statute, its lineage,\\nand the caselaw applying it all favor the district court’s view that three judges\\nare not required for a claim raising only statutory challenges to state\\nlegislative redistricting. Defendants thus face a steep climb in convincing this\\ncourt to be the first to ever read the statute as applying to a case challenging\\na district’s lines only under Section Two of the Voting Rights Act.\\n IV.\\n A.\\n Defendants also seek a stay on the ground that we are likely to reverse\\nthe district court’s ruling that District 22 dilutes the voting power of African-\\nAmericans. The standard of review poses an obstacle to undoing the factual\\nfindings that led the court to conclude that the district violates Section 2. An\\nappellate court “will not set aside” Section 2 factual findings “unless [it is] left\\nwith the definite and firm conviction that a mistake has been committed.”\\nMagnolia Bar Ass’n, Inc. v. Lee, 994 F.2d 1143, 1147 (5th Cir. 1993) (quotation\\nomitted); see NAACP v. Fordice, 252 F.3d 361, 365 (5th Cir. 2001) (noting that\\nclear error review applies).\\n In an attempt to avoid the clear-error standard, Defendants frame their\\nprimary challenge to liability as a legal one. They contend that a court cannot\\nfind vote dilution of a racial group that makes up a majority of the challenged\\ndistrict (recall that here that is just barely the case for District 22). This per\\nse rule they advocate—a bar on vote dilution claims whenever the racial group\\ncrosses the 50% threshold—is at odds with the reason we give such deference\\nto factual findings in Section 2 cases: the question of vote dilution is “peculiarly\\ndependent upon the facts of each case,” Thornburg v. Gingles, 478 U.S. 30, 79\\n(1986) (quoting Nevett v. Sides, 571 F.2d 209, 224 (5th Cir. 1978)), and\\n“requires an ‘intensely local appraisal’ of the challenged district,” LULAC, 548\\n\\n\\n 15\\n\\n Case: 19-60133 Document: 00514887045 Page: 16 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nU.S. at 437 (quoting Gingles, 478 U.S. at 79). The numerous local factors courts\\nconsider—including the strength of bloc voting, demographics, and voter\\nturnout—may mean that a minority group has the equal electoral opportunity\\nthe Voting Rights Act guarantees when its members make up only 40% of a\\ndistrict, but not when they make up 51%. Applying Defendants’ absolute bar\\non Section 2 scrutiny of 50%-plus districts to this case shows how it would\\narbitrarily override the numerous local considerations that Congress and the\\nSupreme Court have said courts need to consider in this important area. If\\nthere were a few hundred fewer African-Americans out of the nearly 44,000\\nvoting-age citizens in District 22, Defendants would allow courts to engage in\\nthe regular multifaceted vote dilution inquiry. But, to Defendants, just over\\n300 additional African-Americans makes the difference between that ordinary\\ninquiry and removing Section 2’s protections for tens of thousands of\\nMississippi voters.\\n Given the statutory mandate to focus on the “totality of circumstances”\\nin Section 2 cases, 52 U.S.C. § 10301(b), it is not surprising that numerous\\ncourts have found dilution of the voting power of a racial group in districts\\nwhere they make up a majority of the voting population. Most importantly,\\nour court has long rejected the argument Defendants advance. In an early vote\\ndilution case—also out of the Mississippi Delta—we explained that the “mere\\nexistence of a black population majority does not preclude a finding of dilution.”\\nMoore v. Leflore Cty. Bd. of Election Comm’rs, 502 F.2d 621, 624 (5th Cir. 1974).\\nWe echoed that more recently, stating that “a protected class that is also a\\nregistered voter majority is not foreclosed, as a matter of law, from raising a\\nvote dilution claim.” Salas v. Sw. Tex. Jr. Coll. Dist., 964 F.2d 1542, 1550 (5th\\nCir. 1992). We have even gone so far so to describe the authority on this point\\nas “unimpeachable.” Monroe v. City of Woodville, 881 F.2d 1327, 1333 (5th\\n\\n\\n 16\\n\\n Case: 19-60133 Document: 00514887045 Page: 17 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nCir. 1989) (describing the caselaw from our circuit that “has rejected any per\\nse rule that a racial minority that is a majority in a political subdivision cannot\\nexperience vote dilution”). We are not alone. Many courts of appeals, including\\none last year, have rejected the argument that a “racial minority cannot prevail\\non a Section 2 claim when it constitutes a bare numerical majority within the\\ndistrict.” Mo. St. Conf. of the NAACP v. Ferguson-Florissant Sch. Dist., 894\\nF.3d 924, 933 (8th Cir. 2018) (collecting cases from the Second, Fifth, Eleventh,\\nand D.C. Circuits).\\n Defendants try to distinguish these cases and others by arguing that\\nthey addressed at-large elections rather than single-member districts. But\\nnothing in these cases turned on that feature. And one court of appeals case\\ndirectly confronting the question rejected a bar on vote dilution claims for\\ngroups that make up more than 50% of the challenged single-member district.\\nKingman Park Civic Ass’n v. Williams, 348 F.3d 1033, 1041 (D.C. Cir. 2003)\\n(agreeing with Salas and Moore in a single-member district vote dilution case).\\nSo did a recent three-judge panel in this circuit. See Perez v. Abbott, 253 F.\\nSupp. 3d 864, 879–90 (W.D. Tex. 2017) (rejecting Defendants’ position when\\nfinding vote dilution in a congressional district with a Hispanic voting-age\\npopulation of 58.5%).\\n Against all this authority of both old and recent vintage, all Defendants\\ncan point to is Justice Kennedy’s opinion in Bartlett v. Strickland, 556 U.S. 1\\n(2009) (opinion of Kennedy, J.). 6 Here is the statement they contend supports\\na categorical rule that there can be no Voting Rights Act violation when a racial\\ngroup exceeds 50% of the district’s population: “Where an election district could\\n\\n\\n 6The defendants also cite Jeffers v. Beebe, 895 F. Supp. 2d 920, 932 (E.D. Ark. 2012),\\nas an example of a court employing their 50%+ bar on Section 2 claims. Even if they read\\nthat case correctly, that holding is no longer good law in its circuit. See Mo. St. Conf. of the\\nNAACP, 894 F.3d at 933.\\n 17\\n\\n Case: 19-60133 Document: 00514887045 Page: 18 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nbe drawn in which minority voters form a majority but such a district is not\\ndrawn,” a Section 2 claim is possible. This is an “objective, numerical test.” Id.\\nat 18. Assuming this opinion is the controlling one under Marks 7 (Justice\\nKennedy wrote for only three judges), it is addressing a different question. He\\nwas rejecting the concept of crossover districts and instead would require that\\na vote-dilution plaintiff show that a district could be drawn in which the racial\\ngroup is a majority. Id. at 15-20. In fact, that is the first showing Gingles\\nrequires. LULAC, 548 U.S. at 425 (noting the first “condition[] for establishing\\na § 2 violation” is that “the racial group is sufficiently large and geographically\\ncompact to constitute a majority in a single-member district” (cleaned up)).\\nFrom that requirement it does not follow that vote dilution cannot occur when\\nthe protected group already makes up a majority in the contested district. It\\nis thus not surprising that no court has read Bartlett to override the widely\\naccepted view that the voting strength of a protected group can still be diluted\\nwhen that group is a majority of a challenged district. Indeed, if any opinion\\nfrom Justice Kennedy addresses the question before us, it is his recognition in\\nLULAC that “it may be possible for a citizen voting-age majority to lack real\\nelectoral opportunity.” Id. at 428.\\n Recognizing this robust caselaw rejecting Defendants’ per se rule\\n(including in single-member cases), the dissent relies on an argument the\\nDefendants have never made: that there needed to be a finding of cracking or\\npacking minority voters. We typically will not consider arguments not\\nadvanced by a party. State Indus. Prods. Corp. v. Beta Tech Inc., 575 F.3d 450,\\n456 (5th Cir. 2009). That principle makes even more sense in the stay context.\\n\\n\\n 7See Marks v. United States, 430 U.S. 188, 193 (1977) (“When a fragmented Court\\ndecides a case and no single rationale explaining the result enjoys the assent of five Justices,\\nthe holding of the Court may be viewed as that position taken by those Members who\\nconcurred in the judgments on the narrowest grounds.” (quotation omitted)).\\n 18\\n\\n Case: 19-60133 Document: 00514887045 Page: 19 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nIf a “party is not entitled to a stay as a matter of right” even based on objections\\nit raised before the district court and in requesting a stay, Campaign for\\nSouthern Equality v. Bryant, 773 F.3d 55 (5th Cir. 2014), it should not be\\nentitled to that extraordinary remedy based on arguments the district court\\nnever had the chance to consider.\\n Even if we could grant a stay based on a challenge to the judgment\\nDefendants do not raise, the dissent’s position misses the marks on the merits.\\nIt argues that vote dilution can occur in a 50%-plus district only if the dilution\\nis the result of cracking or packing minority voters. The terms cracking\\n(dividing minority voters among various districts to weaken their strength)\\nand packing (concentrating minority voters in one or a small number of\\ndistricts where they make up an excessive majority and thus reduce that\\ngroup’s influence in other districts) describe gerrymandering techniques. Gill\\nv. Whitford, 138 S. Ct. 1916, 1924 (2018) (describing the practice in challenge\\nalleging partisan gerrymander); Shaw v. Reno, 509 U.S. 630, 670 (1993)\\n(White, J., dissenting) (same in challenge alleging racial gerrymander). They\\nexplain why vote dilution is occurring. Gill, 138 S. Ct. at 1931. The terms can\\nthus be used to describe types of Section 2 vote dilution claims. See, e.g.,\\nVoinovich v. Quilter, 507 U.S. 146, 153 (1993). But the “cracking” or “packing”\\ndescription does not result in a different Section 2 test or finding. Whether the\\ntheory for dilution is cracking or packing or something else, Section 2 claims\\nare evaluated by first looking at the three Gingles factors to determine whether\\ndemographics, geography, and voting behavior would allow the creation of a\\ndistrict in which the minority group has electoral power. LULAC, 548 U.S. at\\n425. If the plaintiffs satisfy that threshold, then a court considers the “totality\\nof the circumstances” to determine if “members of a racial group have less\\n\\n\\n\\n 19\\n\\n Case: 19-60133 Document: 00514887045 Page: 20 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nopportunity than do other members of the electorate.” Id. at 425–26. The\\ndistrict court faithfully followed this path. 8\\n Although cracking and packing are not official parts of the Section 2\\nanalysis, as a matter of arithmetic vote dilution will often exist because of\\ncracking or packing. Put another way, minority voting strength is often\\nweaker than demographics would allow because those voters have been\\ncrammed into one district with a very high minority percentage and thus\\ndiluted in other districts (packing) or spread among various districts when they\\ncould have formed an electoral majority in at least one (cracking). Indeed, the\\ndistrict court’s findings demonstrate cracking occurred here. 9 District 22 has\\na BVAP of 50.77% and District 23 has a BVAP of 42.00% when, as the remedy\\nadopted by the district court demonstrates, African-Americans could easily\\nform sufficient electoral strength to elect their representative of choice in at\\nleast one of these two districts.\\n The district court correctly focused on the Section 2 factors as prescribed\\nby the Supreme Court and the Voting Rights Act. Part of the reason it found\\nthat the <51% majority of African-American voters in the district did not result\\nin an ability to elect a representative of that group’s choosing was because of\\nturnout in off-year elections. So the “50%-plus” issue is largely an attempt to\\npackage Defendants’ challenge to the factual finding in a more favorable\\nstandard of review. But as with any other factual finding, the clearly\\n\\n\\n 8 It is thus not true that the district court thought that “simply because a district can\\n\\nbe drawn in a way that will guarantee a minority an election win, the Voting Rights Act\\ncompels that such a district be drawn.” Dissenting Op. at 7–8. The district court considered\\nall of the statutorily prescribed factors in finding vote dilution. The dissent is also wrong in\\nsaying that the district court thought a 62% African-American district was required. See id.\\nThat is just the demographics of the remedy it adopted that changed only 28 precincts. To\\nsay that the court thought that percentage was a requirement is to say that any time a\\ndistrict court remedies a Section 2 violation it is creating a new minimum.\\n9 There was no need to use the cracking label because Defendants never made the argument\\n\\nthe dissent advances.\\n 20\\n\\n Case: 19-60133 Document: 00514887045 Page: 21 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nerroneous standard means it is unlikely to be disturbed on appeal. That is\\nparticularly true when the factfinder gives a sound reason for crediting one\\nside’s evidence over the other’s. The district court did that in explaining why\\nit relied on Plaintiffs’ expert for turnout data rather than Census Bureau\\nfigures. The Census Bureau’s election data is for even-year elections, while\\nMississippi conducts odd-year state senate elections.\\n Defendants have not shown a high likelihood of overturning the finding\\nof vote dilution because their legal argument is at odds with “unimpeachable\\nauthority” from our court and their factual challenges must overcome\\ndeferential standards of review.\\n B.\\n\\n Defendants also argue that the district court erred by not dismissing the\\nlawsuit on laches grounds, focusing entirely on Thomas’s delay in bringing this\\nlawsuit. Even if he were the only plaintiff, the standard of review would again\\npose a substantial obstacle for Defendants to overcome on appeal. A district\\ncourt’s equitable ruling on laches is reviewed for abuse of discretion, and the\\nfactual findings of delay, inexcusability, and prejudice that underlie it are\\nreviewed for clear error. See Retractable Tech., Inc. v. Becton Dickinson & Co.,\\n842 F.3d 883, 898 (5th Cir. 2016).\\n More problematic than that for Defendants, Thomas is not the only\\nperson who brought this suit. The stay motion makes no argument for why\\nlaches should bar the lawsuit as to Plaintiffs Ayers and Lawson. As with all\\naffirmative defenses, the party asserting a laches defense bears the burden of\\nproving it. See City of El Paso, Tex. v. El Paso Entm’t, Inc., 382 F. App’x 361,\\n366 (5th Cir. 2010). Defendants did not even attempt to meet this burden for\\nAyers and Lawson. Nor is there, despite the dissent’s attempt to salvage a\\nlaches defense, an exception for the “main plaintiff,” whatever that means. Cf.\\n\\n 21\\n\\n Case: 19-60133 Document: 00514887045 Page: 22 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nMassachusetts v. EPA, 549 U.S. 497, 518 (2007) (observing that only one\\npetitioner needed to have standing to bring suit). The Voting Rights Act\\nprotects the rights of voters, not politicians. As to voters Ayers and Lawson,\\nDefendants point to nothing showing that a laches defense is likely to succeed\\non appeal.\\n V.\\n A.\\n The final ground on which Defendants seek a stay is the remedy the\\ndistrict court ordered. The standard of review again poses a challenge: the\\ndistrict court’s remedy is reviewed for abuse of discretion. Rodriguez v. Bexar\\nCnty., Tex., 385 F.3d 853, 870 (5th Cir. 2004).\\n But “whenever practicable . . . a reasonable opportunity [should be\\nafforded] the legislature to meet constitutional requirements by adopting a\\nsubstituted measure rather than for the federal court to devise and order into\\neffect its own plan.” Veasey, 830 F.3d at 270 (quoting Wise v. Lipscomb, 437\\nU.S. 535, 540 (1978) (opinion of White, J.)) (emphasis original). As recounted\\nabove, the district court first honored this principle in noting it would allow\\ntime for a legislative fix before it would redraw the district. When the court\\nwas informed that the legislature would not act until it saw the outcome of the\\nstay requests, the district court went ahead and redrew the lines given\\nconcerns about the candidate qualifying deadline. It noted, however, that the\\nlegislature always has the ability to redraw districts. Plaintiffs also point this\\nout in their response to the stay motion.\\n The legislature’s desire to wait to see the outcome of the stay ruling is\\nunderstandable. It would have been inefficient for it to remedy a violation only\\nto have this court grant a stay of the district court’s entire judgment on the\\nground that Defendants were likely to overturn the finding of vote dilution.\\n\\n\\n 22\\n\\n Case: 19-60133 Document: 00514887045 Page: 23 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nBut now that we have concluded to the contrary, the legislature should have\\nthe initial opportunity to draw new lines for District 22 that comply with the\\nVoting Rights Act. The only reason not to give it that first shot at crafting a\\nremedy is the candidate filing deadline, but the Secretary of State is requesting\\nthe legislative fix and has not indicated that a further extension of that\\ndeadline for the affected districts is problematic. And while the legislature is\\nalways able to redraw lines, the remedial preference is for it to have the first\\nchance to remedy a Section 2 violation, not for it to act only after the court\\ndraws a new district, which would result in three different districts in a short\\ntime period. United States v. Brown, 561 F.3d 420, 435 (5th Cir. 2009).\\n We thus issued an order on March 15 granting a temporary stay to allow\\nthe legislature until April 3 to remedy the Section 2 violation. The order also\\nextended the candidate filing deadline for any affected districts until April 12.\\n B.\\n Defendants otherwise are not likely to surmount the abuse of discretion\\nstandard in challenging the court’s remedy. If the legislature does not act and\\nthe judicial remedy goes into effect, it must still respect the legislature’s policy\\nobjectives as much as possible. See Perry v. Perez, 565 U.S. 38, 393 (2012). The\\nremedy is a narrowly-tailored one that does that. While redistricting cases\\noften result in redrawing the entire state or at least several districts, this\\nremedy moves just 28 precincts, less than 2% of the precincts in the state. The\\nremedy affects only 2 of Mississippi’s 52 Senate districts. The court found that\\nthe new lines met traditional redistricting criteria: compactness, contiguity,\\npreservation of political subdivisions like counties and cities, and avoiding\\npairing incumbents. It adopted the proposed map of an expert it found credible\\nwho also determined that the new map honored traditional criteria of\\ncompactness and contiguity. In fact, the new district is more consistent with\\n\\n\\n 23\\n\\n Case: 19-60133 Document: 00514887045 Page: 24 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\ntraditional geographic divisions in one important respect: it removes the\\nsuburban Madison county precincts and thus limits the district to counties in\\nthe rural and agricultural Delta.\\n The slightly altered districts are, if anything, also more compact than\\nthey were before. The following map of the new and old districts show the\\nlimited impact of the court’s remedy. The orange and pink highlighting shows\\nthe new districts; the blue lines show the old ones.\\n\\n\\n\\n\\n 24\\n\\n Case: 19-60133 Document: 00514887045 Page: 25 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\n Defendants’ main critique is that the new lines split Vicksburg between\\nthe districts. But some splitting of counties or cities is inevitable given equal\\npopulation requirements. A look at the statewide senate districts reveals this.\\nThe lines the legislature drew split at least eight cities with populations\\nbetween 23,000 and 27,000 residents (Vicksburg had a population of 26,407\\nwhen the 2012 maps were drawn) into different senate districts, including\\nClinton, whose 25,216 citizens are split among 5 districts. Having to split\\nVicksburg thus does not lack fidelity to the legislature’s redistricting policy\\nwhich often results in the same situation. Defendants have not demonstrated\\na high likelihood of showing that that district court’s narrow redraw was an\\nabuse of discretion.\\n C.\\n The dissent also contends that the district court’s remedy interferes with\\nongoing election preparation, though the Defendants—including the Secretary\\nof State—do not cite this as a reason for a stay. In a recent case denying a stay\\nin a voting rights case, we did not consider this issue when government officials\\ndid not argue that the district court’s plan would substantially disturb the\\nelection process. Patino v. City of Pasadena, 677 F. App’x 950, 951–52 (5th Cir.\\n2017).\\n The election is even further away in this case than it was in Patino. Id.\\n(denying stay sought during the candidate registration period with election\\nthree months away); see also Patino v. City of Pasadena, 229 F. Supp. 3d 582,\\n585 (S.D. Tex. 2017) (providing the relevant dates). Primary voting is more\\nthan four months away; the general election is more than seven months away.\\nThat distance to the election means the potential for voter confusion that\\n\\n\\n\\n\\n 25\\n\\n Case: 19-60133 Document: 00514887045 Page: 26 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nanimates this concern, Purcell v. Gonzalez, 549 U.S. 1, 4 (2006), is absent. 10\\nMississippi voters in the 28 affected precincts will go to the same voting\\nlocation they always have, face the same voting requirements, and have\\nmonths to research the candidates in advance of the election. Indeed, the effect\\nof redrawing some of the lines for just two state senate districts with elections\\nmonths away pales in comparison to the impact of statewide redistricting that\\nhas been implemented in a similar timeframe. See, e.g., Covington v. North\\nCarolina, 2018 WL 604732 (M.D. N.C. 2018); Common Cause v. Rucho, 284 F.\\nSupp. 3d 780 (M.D. N.C. 2018); Larios v. Cox, 305 F. Supp. 2d 1335 (N.D. Ga.\\n2004).\\n With no risk of voter confusion, and no outcry from state officials that\\nimplementing the district court’s remedy substantially disturbs its election\\nprocess, this is not a basis for a stay.\\n D.\\n One final comment is necessary to set the record straight in response to\\nthe dissent’s attack on the remedy. It irresponsibly insinuates that the district\\njudge—whom it takes the unusual step of repeatedly naming—drew new lines\\nwith the aim of eliminating partisan opposition to Plaintiff Thomas. That is\\nnot true. Importantly, the incumbent state senator in District 22 had decided\\nnot to run for reelection before the district court ruled in this case. The\\ndissent’s conjecture also ignores that primary candidates file with the political\\nparty (not the state), with the parties notifying state officials of the candidates\\n\\n\\n 10 As most of the cases cited by the dissent show, the voter confusion concern is\\ntypically greatest when a court alters election procedures (as opposed to districts) with an\\nelection quickly approaching. See Veasey v. Perry, 769 F.3d 890, 892 (5th Cir. 2014) (staying\\ndistrict court injunction striking down voter ID laws); Purcell, 549 U.S. at 1 (same); North\\nCarolina v. League of Women Voters of N.C., 135 S. Ct. 6 (2014) (staying district court order\\nthat changed voter ID requirements, voting hours, voting locations, and voter registration);\\nHusted v. Ohio State Conference of NAACP, 135 S. Ct. 42 (2014) (staying district court order\\nthat changed voting hours).\\n 26\\n\\n Case: 19-60133 Document: 00514887045 Page: 27 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\nonly after the filing deadline. That had not yet occurred when the court issued\\nfinal judgment.\\n In light of these circumstances, there is no basis for believing that the\\nPlaintiffs’ expert who drew the proposed remedy back in mid-January, or the\\ndistrict court that later adopted it, knew who the new candidates would be. No\\none brought the names or residences of the candidates to the court’s attention\\nprior to its remedy ruling. And the district court issued its remedy before the\\ninitial candidate qualifying deadline, so there may have been additional\\ncandidates. Not until after the court issued its remedy, in a motion for stay,\\ndid Defendants bring to the court’s attention the fact that two candidates\\nwould no longer reside in District 22. On learning this, the district court\\nlamented that it was not told prior to its ruling. As for the competition in the\\nnew district, we do not know who has filed nor who will file prior to the new\\nqualifying deadline.\\n ***\\n Per the order issued last week, the motion for stay is GRANTED IN\\nPART and DENIED IN PART. A majority of the panel concludes Defendants\\nhave satisfied the stay factors only based on the need to give the legislature\\nand Governor an opportunity to remedy the Section 2 violation. A stay is\\nentered for that purpose until April 3, 2019. The candidate filing deadline for\\nany districts whose lines are redrawn (whether by the legislature, or if it does\\nnot act, per the district court’s remedy) is extended to April 12, 2019. The\\ndistrict court has jurisdiction to consider any challenges to the adequacy of a\\nlegislative remedy.\\n\\n\\n\\n\\n 27\\n\\n Case: 19-60133 Document: 00514887045 Page: 28 Date Filed: 03/25/2019\\n\\n\\n\\n No. 19-60133\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":1099,"cells":{"id":{"kind":"number","value":4603849,"string":"4,603,849"},"name":{"kind":"string","value":"Sheaneter J. BOGAN, Plaintiff-Appellant v. MTD CONSUMER GROUP, INCORPORATED, Defendant-Appellee"},"name_abbreviation":{"kind":"string","value":"Sheaneter Bogan v. MTD Consumer Group, Inc."},"decision_date":{"kind":"string","value":"2019-03-26"},"docket_number":{"kind":"string","value":"17-60697"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fifth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Wiener, Southwick, Costa\", \"parties\": \"\", \"opinions\": [{\"author\": \"GREGG COSTA, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 17-60697 Document: 00514888165 Page: 1 Date Filed: 03/26/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n\\n No. 17-60697 FILED\\n March 26, 2019\\n Lyle W. Cayce\\nSHEANETER J. BOGAN., Clerk\\n\\n Plaintiff - Appellant\\n\\nv.\\n\\nMTD CONSUMER GROUP, INCORPORATED,\\n\\n Defendant - Appellee\\n\\n\\n\\n\\n Appeal from the United States District Court\\n for the Northern District of Mississippi\\n\\n\\nBefore WIENER, SOUTHWICK, and COSTA, Circuit Judges.\\nGREGG COSTA, Circuit Judge:\\n Sheaneter Bogan filed suit alleging that she was fired because of her race\\nand sex. A jury found in her favor but awarded her just $1. The district court\\nthen denied Bogan both reinstatement and front pay, leaving her with no\\nremedy. We review the district court’s decision not to award prospective relief.\\nBecause two of the reasons the district court relied on in denying reinstatement\\ndo not support that result, we remand for reconsideration.\\n I.\\n A.\\n Bogan worked at MTD Consumer Group, a manufacturer of outdoor\\npower equipment, for about 20 years. She started with the company in\\n\\f Case: 17-60697 Document: 00514888165 Page: 2 Date Filed: 03/26/2019\\n\\n\\n\\n 17-60697\\nunskilled positions, but while working took full-time classes at a community\\ncollege so she could obtain a skilled position. After she completed that\\ncoursework, MTD eventually promoted Bogan to be a machinist in the Tool and\\nDie department. She remained in that job for about two years until her\\ntermination in April 2013.\\n While pursuing the Tool and Die position, Bogan also began going to\\nschool for a degree in social work. Her supervisors initially accommodated her\\nclass schedule with flexible work hours. But in fall 2012, human resources\\nnotified Bogan that, based on company policy only allowing flexible hours for\\nwork-related schooling, she had to work a normal shift.\\n Despite this decision, Bogan still worked some irregular hours. So\\nBogan’s supervisors reminded her that she had to work the regular 5:00 a.m.\\nto 3:30 p.m shift and could not attend classes during work hours. But on\\noccasion Bogan would squeeze class time into her lunch break. When a\\nsupervisor learned about this, he suspended Bogan. MTD then terminated\\nher, ostensibly because she came back from lunch late. Bogan unsuccessfully\\nappealed her termination to an employee review board.\\n B.\\n After receiving a right-to-sue letter from the EEOC, Bogan filed this suit\\nalleging race and sex discrimination. MTD sought summary judgment. The\\ndistrict court denied that motion, concluding that the evidence could support a\\nfinding that MTD’s reason for the termination was pretextual. For example,\\nother employees “routinely” took lunch breaks that lasted longer than thirty\\nminutes, but Bogan was the only one punished for doing so. The court also\\npointed to doubts about the accuracy of information in Bogan’s personnel file.\\n A four-day trial followed that resulted in the jury finding that MTD\\n“discriminated against [Bogan] on the basis of her race and/or gender.” The\\n\\n\\n 2\\n\\f Case: 17-60697 Document: 00514888165 Page: 3 Date Filed: 03/26/2019\\n\\n\\n\\n 17-60697\\njury awarded her $1, perhaps because of a jury instruction on the consequences\\nof a failure to mitigate, an argument that MTD pushed.\\n Bogan then asked the court for reinstatement or front pay. The district\\ncourt held a hearing after which it denied both requests. It cited four factors\\nthat it believed counseled against reinstatement and refused to order that\\nremedy. For front pay, the court held that MTD established that Bogan did\\nnot mitigate her damages.\\n II.\\n Reinstatement and front pay are equitable remedies. The ultimate\\nexercise of a court’s equitable power is reviewed for abuse of discretion.\\nDeloach v. Delchamps, Inc., 897 F.2d 815, 822 (5th Cir. 1990). An error of law\\nor application of an incorrect legal standard rises to that level. Klier v. Elf\\nAtochem N. Am., Inc., 658 F.3d 468, 474 (5th Cir. 2011). But the factual\\nfindings that underlie the decision to grant or deny relief are reviewed only for\\nclear error. Sellers v. Delgado Cmty. Coll., 839 F.2d 1132, 1138 (5th Cir. 1988).\\n A.\\n That deferential standard for review of factual determinations disposes\\nof Bogan’s appeal of the front pay ruling. Bogan argues she did make\\nreasonable efforts to obtain work and tried to keep up with her training. She\\nmakes some good points, but there was also evidence to support the district\\ncourt’s contrary conclusions. We thus see no clear error in the court’s finding\\nthat Bogan did not use reasonable diligence to obtain “substantially equivalent\\nemployment.” Id.\\n B.\\n That leaves her challenge to the ruling on reinstatement. Reinstatement\\nis the preferred equitable remedy under Title VII. Hansard v. Pepsi-Cola\\nMetro. Bottling Co., 865 F.2d 1461, 1469 (5th Cir. 1989). Reinstatement more\\ntightly fits the termination injury. It does not require answering the front pay\\n 3\\n\\f Case: 17-60697 Document: 00514888165 Page: 4 Date Filed: 03/26/2019\\n\\n\\n\\n 17-60697\\nquestion of “whether and for how long a plaintiff will work in the future,” for\\nwhich a bad guess means either that plaintiff is “left without a remedy” or\\n“end[s] up with a windfall.” Duke v. Uniroyal Inc., 928 F.2d 1413, 1423 (4th\\nCir. 1991); see also Reneau v. Wayne Griffin & Sons, Inc., 945 F.2d 869, 870\\n(5th Cir. 1991) (noting that front pay is “necessarily speculative in nature” and\\nrequires the court to engage in “intelligent guesswork”). And reinstatement\\nrestores not just the financial benefits of a job but also the “psychological\\nbenefits” of work. Allen v. Autauga Cty. Bd. of Educ., 685 F.2d 1302, 1306\\n(11th Cir. 1982). Ergo, reinstatement is most consistent with Title VII’s\\n“‘make-whole’ philosophy.” Hansard, 865 F.2d at 1469.\\n This case presents an unusual situation in which no prospective (or\\nmeaningful retrospective) relief was awarded after a finding of discrimination.\\nOur caselaw contemplates that one form of prospective relief will ordinarily be\\nappropriate when it is requested. We have often said that the trial court’s\\nremedial discretion in this area involves the “selection between reinstatement\\nand front pay.” Brunnemann v. Terra Int'l, Inc., 975 F.2d 175, 180 (5th Cir.\\n1992) (emphasis added); see also Palasota v. Haggar Clothing Co., 499 F.3d\\n474, 489 (5th Cir. 2007) (quoting Brunnemann); Weaver v. Amoco Prod. Co., 66\\nF.3d 85, 88 (5th Cir. 1995) (same). The typical “either/or” nature of this\\nremedial choice is also seen in our statement that “if reinstatement is not\\nfeasible, front pay is the appropriate award.” Weaver, 66 F.3d at 88;\\nBrunnemann, 975 F.2d at 180 (“Generally, if reinstatement is not feasible,\\nfront pay will be awarded.”); see also Weaver v. Casa Gallardo, Inc., 922 F.2d\\n1515, 1528 (11th Cir. 1991) (“[P]revailing Title VII plaintiffs are presumptively\\nentitled to either reinstatement or front pay.”). In discussing another federal\\nemployment statute (the retaliation provision of the Fair Labor Standards\\nAct), Judge Wisdom went so far as to say that “it is impossible for us to imagine\\n\\n\\n 4\\n\\f Case: 17-60697 Document: 00514888165 Page: 5 Date Filed: 03/26/2019\\n\\n\\n\\n 17-60697\\ncases when a denial of both reinstatement and reimbursement would be\\njustified.” 1 Goldberg v. Bama Mfg. Corp., 302 F.2d 152, 156 (5th Cir. 1962).\\n Yet given the equitable nature of these remedies and the limits of our\\nimagining the full variety of situations that arise in the workplace, there may\\nbe outlier situations in which no prospective relief is appropriate for a victim\\nof discrimination. Indeed, although the parties could point to no case from our\\ncourt in which a plaintiff sought either form of prospective relief but received\\nneither, 2 we found one such case involving an award of punitive damages that\\nthe district court concluded was enough to make the victim whole. Hadley v.\\nVAM P T S, 44 F.3d 372, 376 (5th Cir. 1995). The Supreme Court has also\\nidentified one scenario: when after termination the employer obtains evidence\\nof serious employee misconduct. McKennon v. Nashville Banner Publ’g Co.,\\n513 U.S. 352, 361–62 (1995). 3 But our consistent signaling is that the usual\\ncase involves a district court’s choosing which of the two options better serves\\n\\n\\n\\n 1 When Judge Wisdom made that observation, the FLSA did not allow damages for\\nretaliation. 29 U.S.C. § 216(b); Pub. L. 95-151 (1977) (adding provision that allows for both\\nlegal and equitable remedies). It now does, as does Title VII since the Civil Rights Act of\\n1991. 42 U.S.C. § 1981a(a)(1); Pub. L. No. 102-166 (1991). Yet most of the cases cited above\\ndiscussing equitable Title VII remedies arose after the 1991 amendments allowed damages.\\n 2 MTD cited two examples at oral argument, Giles v. Gen. Elec. Co., 245 F.3d 474 (5th\\n\\nCir. 2001) and Hansard, 865 F.2d 1461. In Giles, the plaintiff was denied back pay, but\\nreceived front pay. We indicated that it may have been appropriate to deny front pay, but it\\nwas not an abuse of discretion to allow it. 245 F.3d at 489. In Hansard, we reduced a\\nplaintiff’s back pay for failure to mitigate and remanded the issue of front pay to the district\\ncourt to consider mitigation. 865 F.2d at 1468. Neither of these cases foreclose the possibility\\nthat a plaintiff may be denied a prospective remedy. But neither considered or affirmed a\\njudgment in which a plaintiff was denied any prospective remedy.\\n 3 There are also examples from other circuits. The Eighth Circuit held that evidence\\n\\nof post-termination misconduct (as opposed to McKennon’s after-acquired evidence of pre-\\ntermination misconduct) that would render the plaintiff ineligible for reinstatement may also\\njustify denying both equitable remedies. Sellers v. Mineta, 358 F.3d 1058, 1064 (8th Cir.\\n2004). The Seventh Circuit upheld denial of both reinstatement and front pay when the jury\\nfound the plaintiff’s earning capacity was not harmed as he had changed careers and started\\nreceiving a higher salary. Although he later alleged he had trouble holding that job, the court\\nsaid his employer was not required to “insure his future employment success.” McKnight v.\\nGen. Motors Corp., 973 F.2d 1366, 1372 (7th Cir. 1992).\\n 5\\n\\f Case: 17-60697 Document: 00514888165 Page: 6 Date Filed: 03/26/2019\\n\\n\\n\\n 17-60697\\nthe “purpose of Title VII to make persons whole for injuries suffered on account\\nof unlawful employment discrimination.” Albemarle Paper Co. v. Moody, 422\\nU.S. 405, 418 (1975); Brunnemann, 975 F.2d at 180.\\n Before we can assess whether the district court abused its discretion in\\nnot reinstating Bogan, we review each factor it cited in support of that ruling.\\nThe first two are ones that do counsel against reinstatement. Because Bogan’s\\nposition no longer “exists as it did during her employment,” the district court\\nproperly considered that reinstatement would require training on new\\nmachines and that the company did not have a present opening in the Tool and\\nDie department. See Palasota, 499 F.3d at 489. It was also permissible for the\\ncourt to rely on its finding that Bogan had intended to change careers to social\\nwork. Id.\\n The third reason the district court cited is MTD’s argument that it\\n“would have terminated Plaintiff in the absence of any purported\\ndiscrimination” because of “her inability to follow the rules and her attitude.”\\nSee 42 U.S.C. § 2000e-5(g)(2)(B). Yet the district court did not find that MTD\\nproved this statutory defense, it only noted it as MTD’s position. More\\nfundamentally, the district court could not find in favor of MTD on this issue\\nbecause the jury had rejected it. It was instructed that “[i]f you find by a\\npreponderance of the evidence that MTD Consumer Group Inc has proved it\\nwould have terminated Ms. Bogan’s employment even if it had not considered\\nher race and/or gender, you must find for the Defendant, MTD Consumer\\nGroup Inc, and go no further in your deliberations.” See also FIFTH CIRCUIT\\nPATTERN JURY INSTRUCTIONS (Civil Cases) 11.13 (2014); Price Waterhouse v.\\nHopkins, 490 U.S. 228, 253 (1989). The jury thus must have rejected this\\ndefense in finding that MTD was liable for discrimination. It would be\\nimproper for the court to override the jury’s factfinding on this question when\\ndeciding equitable relief. Smith v. Diffee Ford-Lincoln-Mercury, Inc., 298 F.3d\\n 6\\n\\f Case: 17-60697 Document: 00514888165 Page: 7 Date Filed: 03/26/2019\\n\\n\\n\\n 17-60697\\n955, 965 (10th Cir. 2002) (“[W]hen legal and equitable issues to be decided in\\nthe same case depend on common determinations of fact . . . the court in\\nresolving the equitable issues is then bound by the jury's findings on them.”);\\nIn re Lewis, 845 F.2d 624, 630 (6th Cir. 1988) (“In the context of employment\\ndiscrimination cases, it is well-settled that a jury's findings of discrimination\\nare binding on a court considering reinstatement.”); Hussein v. Oshkosh Motor\\nTruck Co., 816 F.2d 348, 355 (7th Cir. 1987) (“[I]n deciding whether to grant\\nequitable relief under Title VII, the district court [is] prohibited from\\nreconsidering any issues necessarily and actually decided by the jury.”);\\nLindsey v. Am. Cast Iron Pipe Co., 810 F.2d 1094, 1097–98 (11th Cir. 1987)\\n(holding that a district court’s rejection of liquidated damages in an age\\ndiscrimination case was improper because it relied on factual findings “that\\nconflicted with the jury’s findings”); Gibson v. Mohawk Rubber Co., 695 F.2d\\n1093, 1101 (8th Cir. 1982) (stating that the district court “cannot base its\\ndecision on its own factual findings that conflict with those expressly made by\\nthe jury”). Allowing MTD to relitigate the verdict during the remedial phase\\nwas error.\\n The final reason the district court cited in denying reinstatement—\\n“discord between the parties”—is also problematic because of the apparent\\nsource of that acrimony. For understandable reasons, hostility between the\\nparties that is likely to disrupt the workplace if the employee returns can be a\\nreason for denying reinstatement. See, e.g., Deloach, 897 F.2d at 822. Such\\nacrimony is often cited by courts that award front pay rather than requiring\\nthe plaintiff to return to a discriminatory employer. Id. (addressing employer’s\\nappeal of front pay award in which it argued that reinstatement was preferable\\neven though the district court had found there was too much discord between\\nthe parties for that remedy); see also Walther v. Lone Star Gas Co., 952 F.2d\\n\\n\\n 7\\n\\f Case: 17-60697 Document: 00514888165 Page: 8 Date Filed: 03/26/2019\\n\\n\\n\\n 17-60697\\n119, 127 (5th Cir. 1992) (addressing employer’s argument that reinstatement\\nshould have been imposed rather than front pay award).\\n What makes this a challenging area is that the post-lawsuit context in\\nwhich this question arises usually sees some friction between the parties.\\nAntagonism is a natural by-product of lawsuits, often even more so for ones\\nalleging discrimination. If the hostility common to litigation were sufficient\\nfor “denial of reinstatement, reinstatement would cease to be a remedy except\\nin cases where the defendant felt like reinstating the plaintiff.” EEOC v.\\nCentury Broad. Corp., 957 F.2d 1446, 1462 (7th Cir. 1992); see also Weaver v.\\nAmoco Prod. Co., 95 F.3d 52, 1996 WL 459345 at *2 (5th Cir. 1996)\\n(unpublished) (noting that the hostility must “exceed the animosity level that\\ncommonly arises between opposing parties throughout the litigation process”).\\nAnd for reasons we have just explained, the finding of discord cannot rely on\\nreasons rejected by the jury, such as hostility stemming from the employee’s\\nalleged misconduct that the jury found to be pretextual. Cf. Ray v. Iuka Special\\nMun. Separate Sch. Dist., 51 F.3d 1246, 1254 (5th Cir. 1995) (recognizing that\\nfinding of discord could not be based “upon reasons rejected by the jury,”\\nthough concluding that is not what the district court’s ruling relied on). So\\nmore than the friction that typically results from litigation or the employee’s\\ntermination is required for the discord to be a reason not to order\\nreinstatement.\\n The acrimony must rise to the level at which the parties’ relationship is\\n“irreparably damaged.” Walther, 952 F.2d at 127; see also Allen, 685 F.2d at\\n1306 (“Unless we are willing to withhold full relief from all or most successful\\nplaintiffs in discharge cases, and we are not, we cannot allow actual or expected\\nill-feeling alone to justify nonreinstatement.”). That “lingering hostility”\\nexisted when a plaintiff had alleged that his employer “attempted to black-ball\\nhim in the industry” and the employer alleged the plaintiff filed falsified\\n 8\\n\\f Case: 17-60697 Document: 00514888165 Page: 9 Date Filed: 03/26/2019\\n\\n\\n\\n 17-60697\\nexpense reports, something that it did not allege was a justification for the\\nplaintiff’s actual termination but could have been. Palasota, 499 F.3d at 490. 4\\n The district court did not find that the relationship between Bogan and\\nMTD rose to the level at which it was irreparably damaged and exceeded the\\nantagonism that normally results from trials. Walther, 952 F.2d at 127\\n(stating that a court should cite “specific instances of discord” for the acrimony\\nto justify denying reinstatement). It did describe MTD’s hostility towards\\nBogan as “palpable,” but the only example cited was the remedial-phase\\ntestimony of the human resources manager when he “discussed the human\\nresources issues he would face if the employee review process were to be\\nnegated by reinstating Plaintiff.” It is not clear that this problem is one of\\nhostility rather than inconvenience. And the concern that a court order of\\nreinstatement would be inconsistent with, and thus undermine, the employer’s\\nown dispute resolution procedures that resulted in termination would\\nseemingly always exist. More than that common situation is needed to find\\nthat the relationship between the parties is so broken that it has reached the\\npoint of no return. Id. Finally, it is the jury’s finding of discrimination that\\ncontradicted the employee review process, so allowing that disagreement to\\ndefeat reinstatement runs the risk we have already discussed of not honoring\\nthe jury’s verdict. Without evidence that the relationship between Bogan and\\nMTD exceeded that which normally accompanies trials, this factor does not\\nmilitate against the preferred remedy of reinstatement.\\n\\n\\n\\n 4 Examples from other circuits highlight how severe the hostility usually is when\\ncourts use it to deny reinstatement. See Hunter v. Town of Mocksville, N.C., 897 F.3d 538,\\n562 (4th Cir. 2018) (denying reinstatement when the plaintiff made social media posts\\nfollowing his termination calling the city for which he worked a “crooked [expletive] hole of a\\ntown” and questioning the judgement of law enforcement decisions); Hammond v. Northland\\nCounseling Ctr., Inc., 218 F.3d 886, 892 (8th Cir. 2000) (finding sufficient acrimony to\\npreclude reinstatement in a False Claims Act case when there was evidence of attempts by\\nthe plaintiff’s coworkers to “intimidate and harass” her after she filed her suit).\\n 9\\n\\f Case: 17-60697 Document: 00514888165 Page: 10 Date Filed: 03/26/2019\\n\\n\\n\\n 17-60697\\n Because the district court should not have considered two of the four\\nfactors it relied on in denying reinstatement, we cannot review its conclusion\\nthat Bogan’s reinstatement would not further the remedial goals of Title VII.\\nThe remedial discretion is vested in the district court, and we do not know how\\nit would exercise that authority with two fewer factors on the “no\\nreinstatement” side of the scale. We thus remand for further proceedings\\nwithout suggesting how the district court should exercise its discretion based\\non the two factors that remain or other permissible considerations that the\\ndistrict court may find relevant.\\n ***\\n AFFIRMED in part, VACATED and REMANDED in part.\\n\\n\\n\\n\\n 10\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4381102/\", \"author_raw\": \"GREGG COSTA, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"WIENER"},"judge2":{"kind":"string","value":"SOUTHWICK"},"judge3":{"kind":"string","value":"COSTA"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4603849/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":3,"string":"3"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Sheaneter J. BOGAN, Plaintiff-Appellant v. MTD CONSUMER GROUP, INCORPORATED, Defendant-Appellee\nCourt: U.S. Court of Appeals for the Fifth Circuit\nDate decided: 2019-03-26\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 17-60697 Document: 00514888165 Page: 1 Date Filed: 03/26/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\n United States Court of Appeals\n Fifth Circuit\n\n\n No. 17-60697 FILED\n March 26, 2019\n Lyle W. Cayce\nSHEANETER J. BOGAN., Clerk\n\n Plaintiff - Appellant\n\nv.\n\nMTD CONSUMER GROUP, INCORPORATED,\n\n Defendant - Appellee\n\n\n\n\n Appeal from the United States District Court\n for the Northern District of Mississippi\n\n\nBefore WIENER, SOUTHWICK, and COSTA, Circuit Judges.\nGREGG COSTA, Circuit Judge:\n Sheaneter Bogan filed suit alleging that she was fired because of her race\nand sex. A jury found in her favor but awarded her just $1. The district court\nthen denied Bogan both reinstatement and front pay, leaving her with no\nremedy. We review the district court’s decision not to award prospective relief.\nBecause two of the reasons the district court relied on in denying reinstatement\ndo not support that result, we remand for reconsideration.\n I.\n A.\n Bogan worked at MTD Consumer Group, a manufacturer of outdoor\npower equipment, for about 20 years. She started with the company in\n\f Case: 17-60697 Document: 00514888165 Page: 2 Date Filed: 03/26/2019\n\n\n\n 17-60697\nunskilled positions, but while working took full-time classes at a community\ncollege so she could obtain a skilled position. After she completed that\ncoursework, MTD eventually promoted Bogan to be a machinist in the Tool and\nDie department. She remained in that job for about two years until her\ntermination in April 2013.\n While pursuing the Tool and Die position, Bogan also began going to\nschool for a degree in social work. Her supervisors initially accommodated her\nclass schedule with flexible work hours. But in fall 2012, human resources\nnotified Bogan that, based on company policy only allowing flexible hours for\nwork-related schooling, she had to work a normal shift.\n Despite this decision, Bogan still worked some irregular hours. So\nBogan’s supervisors reminded her that she had to work the regular 5:00 a.m.\nto 3:30 p.m shift and could not attend classes during work hours. But on\noccasion Bogan would squeeze class time into her lunch break. When a\nsupervisor learned about this, he suspended Bogan. MTD then terminated\nher, ostensibly because she came back from lunch late. Bogan unsuccessfully\nappealed her termination to an employee review board.\n B.\n After receiving a right-to-sue letter from the EEOC, Bogan filed this suit\nalleging race and sex discrimination. MTD sought summary judgment. The\ndistrict court denied that motion, concluding that the evidence could support a\nfinding that MTD’s reason for the termination was pretextual. For example,\nother employees “routinely” took lunch breaks that lasted longer than thirty\nminutes, but Bogan was the only one punished for doing so. The court also\npointed to doubts about the accuracy of information in Bogan’s personnel file.\n A four-day trial followed that resulted in the jury finding that MTD\n“discriminated against [Bogan] on the basis of her race and/or gender.” The\n\n\n 2\n\f Case: 17-60697 Document: 00514888165 Page: 3 Date Filed: 03/26/2019\n\n\n\n 17-60697\njury awarded her $1, perhaps because of a jury instruction on the consequences\nof a failure to mitigate, an argument that MTD pushed.\n Bogan then asked the court for reinstatement or front pay. The district\ncourt held a hearing after which it denied both requests. It cited four factors\nthat it believed counseled against reinstatement and refused to order that\nremedy. For front pay, the court held that MTD established that Bogan did\nnot mitigate her damages.\n II.\n Reinstatement and front pay are equitable remedies. The ultimate\nexercise of a court’s equitable power is reviewed for abuse of discretion.\nDeloach v. Delchamps, Inc., 897 F.2d 815, 822 (5th Cir. 1990). An error of law\nor application of an incorrect legal standard rises to that level. Klier v. Elf\nAtochem N. Am., Inc., 658 F.3d 468, 474 (5th Cir. 2011). But the factual\nfindings that underlie the decision to grant or deny relief are reviewed only for\nclear error. Sellers v. Delgado Cmty. Coll., 839 F.2d 1132, 1138 (5th Cir. 1988).\n A.\n That deferential standard for review of factual determinations disposes\nof Bogan’s appeal of the front pay ruling. Bogan argues she did make\nreasonable efforts to obtain work and tried to keep up with her training. She\nmakes some good points, but there was also evidence to support the district\ncourt’s contrary conclusions. We thus see no clear error in the court’s finding\nthat Bogan did not use reasonable diligence to obtain “substantially equivalent\nemployment.” Id.\n B.\n That leaves her challenge to the ruling on reinstatement. Reinstatement\nis the preferred equitable remedy under Title VII. Hansard v. Pepsi-Cola\nMetro. Bottling Co., 865 F.2d 1461, 1469 (5th Cir. 1989). Reinstatement more\ntightly fits the termination injury. It does not require answering the front pay\n 3\n\f Case: 17-60697 Document: 00514888165 Page: 4 Date Filed: 03/26/2019\n\n\n\n 17-60697\nquestion of “whether and for how long a plaintiff will work in the future,” for\nwhich a bad guess means either that plaintiff is “left without a remedy” or\n“end[s] up with a windfall.” Duke v. Uniroyal Inc., 928 F.2d 1413, 1423 (4th\nCir. 1991); see also Reneau v. Wayne Griffin & Sons, Inc., 945 F.2d 869, 870\n(5th Cir. 1991) (noting that front pay is “necessarily speculative in nature” and\nrequires the court to engage in “intelligent guesswork”). And reinstatement\nrestores not just the financial benefits of a job but also the “psychological\nbenefits” of work. Allen v. Autauga Cty. Bd. of Educ., 685 F.2d 1302, 1306\n(11th Cir. 1982). Ergo, reinstatement is most consistent with Title VII’s\n“‘make-whole’ philosophy.” Hansard, 865 F.2d at 1469.\n This case presents an unusual situation in which no prospective (or\nmeaningful retrospective) relief was awarded after a finding of discrimination.\nOur caselaw contemplates that one form of prospective relief will ordinarily be\nappropriate when it is requested. We have often said that the trial court’s\nremedial discretion in this area involves the “selection between reinstatement\nand front pay.” Brunnemann v. Terra Int'l, Inc., 975 F.2d 175, 180 (5th Cir.\n1992) (emphasis added); see also Palasota v. Haggar Clothing Co., 499 F.3d\n474, 489 (5th Cir. 2007) (quoting Brunnemann); Weaver v. Amoco Prod. Co., 66\nF.3d 85, 88 (5th Cir. 1995) (same). The typical “either/or” nature of this\nremedial choice is also seen in our statement that “if reinstatement is not\nfeasible, front pay is the appropriate award.” Weaver, 66 F.3d at 88;\nBrunnemann, 975 F.2d at 180 (“Generally, if reinstatement is not feasible,\nfront pay will be awarded.”); see also Weaver v. Casa Gallardo, Inc., 922 F.2d\n1515, 1528 (11th Cir. 1991) (“[P]revailing Title VII plaintiffs are presumptively\nentitled to either reinstatement or front pay.”). In discussing another federal\nemployment statute (the retaliation provision of the Fair Labor Standards\nAct), Judge Wisdom went so far as to say that “it is impossible for us to imagine\n\n\n 4\n\f Case: 17-60697 Document: 00514888165 Page: 5 Date Filed: 03/26/2019\n\n\n\n 17-60697\ncases when a denial of both reinstatement and reimbursement would be\njustified.” 1 Goldberg v. Bama Mfg. Corp., 302 F.2d 152, 156 (5th Cir. 1962).\n Yet given the equitable nature of these remedies and the limits of our\nimagining the full variety of situations that arise in the workplace, there may\nbe outlier situations in which no prospective relief is appropriate for a victim\nof discrimination. Indeed, although the parties could point to no case from our\ncourt in which a plaintiff sought either form of prospective relief but received\nneither, 2 we found one such case involving an award of punitive damages that\nthe district court concluded was enough to make the victim whole. Hadley v.\nVAM P T S, 44 F.3d 372, 376 (5th Cir. 1995). The Supreme Court has also\nidentified one scenario: when after termination the employer obtains evidence\nof serious employee misconduct. McKennon v. Nashville Banner Publ’g Co.,\n513 U.S. 352, 361–62 (1995). 3 But our consistent signaling is that the usual\ncase involves a district court’s choosing which of the two options better serves\n\n\n\n 1 When Judge Wisdom made that observation, the FLSA did not allow damages for\nretaliation. 29 U.S.C. § 216(b); Pub. L. 95-151 (1977) (adding provision that allows for both\nlegal and equitable remedies). It now does, as does Title VII since the Civil Rights Act of\n1991. 42 U.S.C. § 1981a(a)(1); Pub. L. No. 102-166 (1991). Yet most of the cases cited above\ndiscussing equitable Title VII remedies arose after the 1991 amendments allowed damages.\n 2 MTD cited two examples at oral argument, Giles v. Gen. Elec. Co., 245 F.3d 474 (5th\n\nCir. 2001) and Hansard, 865 F.2d 1461. In Giles, the plaintiff was denied back pay, but\nreceived front pay. We indicated that it may have been appropriate to deny front pay, but it\nwas not an abuse of discretion to allow it. 245 F.3d at 489. In Hansard, we reduced a\nplaintiff’s back pay for failure to mitigate and remanded the issue of front pay to the district\ncourt to consider mitigation. 865 F.2d at 1468. Neither of these cases foreclose the possibility\nthat a plaintiff may be denied a prospective remedy. But neither considered or affirmed a\njudgment in which a plaintiff was denied any prospective remedy.\n 3 There are also examples from other circuits. The Eighth Circuit held that evidence\n\nof post-termination misconduct (as opposed to McKennon’s after-acquired evidence of pre-\ntermination misconduct) that would render the plaintiff ineligible for reinstatement may also\njustify denying both equitable remedies. Sellers v. Mineta, 358 F.3d 1058, 1064 (8th Cir.\n2004). The Seventh Circuit upheld denial of both reinstatement and front pay when the jury\nfound the plaintiff’s earning capacity was not harmed as he had changed careers and started\nreceiving a higher salary. Although he later alleged he had trouble holding that job, the court\nsaid his employer was not required to “insure his future employment success.” McKnight v.\nGen. Motors Corp., 973 F.2d 1366, 1372 (7th Cir. 1992).\n 5\n\f Case: 17-60697 Document: 00514888165 Page: 6 Date Filed: 03/26/2019\n\n\n\n 17-60697\nthe “purpose of Title VII to make persons whole for injuries suffered on account\nof unlawful employment discrimination.” Albemarle Paper Co. v. Moody, 422\nU.S. 405, 418 (1975); Brunnemann, 975 F.2d at 180.\n Before we can assess whether the district court abused its discretion in\nnot reinstating Bogan, we review each factor it cited in support of that ruling.\nThe first two are ones that do counsel against reinstatement. Because Bogan’s\nposition no longer “exists as it did during her employment,” the district court\nproperly considered that reinstatement would require training on new\nmachines and that the company did not have a present opening in the Tool and\nDie department. See Palasota, 499 F.3d at 489. It was also permissible for the\ncourt to rely on its finding that Bogan had intended to change careers to social\nwork. Id.\n The third reason the district court cited is MTD’s argument that it\n“would have terminated Plaintiff in the absence of any purported\ndiscrimination” because of “her inability to follow the rules and her attitude.”\nSee 42 U.S.C. § 2000e-5(g)(2)(B). Yet the district court did not find that MTD\nproved this statutory defense, it only noted it as MTD’s position. More\nfundamentally, the district court could not find in favor of MTD on this issue\nbecause the jury had rejected it. It was instructed that “[i]f you find by a\npreponderance of the evidence that MTD Consumer Group Inc has proved it\nwould have terminated Ms. Bogan’s employment even if it had not considered\nher race and/or gender, you must find for the Defendant, MTD Consumer\nGroup Inc, and go no further in your deliberations.” See also FIFTH CIRCUIT\nPATTERN JURY INSTRUCTIONS (Civil Cases) 11.13 (2014); Price Waterhouse v.\nHopkins, 490 U.S. 228, 253 (1989). The jury thus must have rejected this\ndefense in finding that MTD was liable for discrimination. It would be\nimproper for the court to override the jury’s factfinding on this question when\ndeciding equitable relief. Smith v. Diffee Ford-Lincoln-Mercury, Inc., 298 F.3d\n 6\n\f Case: 17-60697 Document: 00514888165 Page: 7 Date Filed: 03/26/2019\n\n\n\n 17-60697\n955, 965 (10th Cir. 2002) (“[W]hen legal and equitable issues to be decided in\nthe same case depend on common determinations of fact . . . the court in\nresolving the equitable issues is then bound by the jury's findings on them.”);\nIn re Lewis, 845 F.2d 624, 630 (6th Cir. 1988) (“In the context of employment\ndiscrimination cases, it is well-settled that a jury's findings of discrimination\nare binding on a court considering reinstatement.”); Hussein v. Oshkosh Motor\nTruck Co., 816 F.2d 348, 355 (7th Cir. 1987) (“[I]n deciding whether to grant\nequitable relief under Title VII, the district court [is] prohibited from\nreconsidering any issues necessarily and actually decided by the jury.”);\nLindsey v. Am. Cast Iron Pipe Co., 810 F.2d 1094, 1097–98 (11th Cir. 1987)\n(holding that a district court’s rejection of liquidated damages in an age\ndiscrimination case was improper because it relied on factual findings “that\nconflicted with the jury’s findings”); Gibson v. Mohawk Rubber Co., 695 F.2d\n1093, 1101 (8th Cir. 1982) (stating that the district court “cannot base its\ndecision on its own factual findings that conflict with those expressly made by\nthe jury”). Allowing MTD to relitigate the verdict during the remedial phase\nwas error.\n The final reason the district court cited in denying reinstatement—\n“discord between the parties”—is also problematic because of the apparent\nsource of that acrimony. For understandable reasons, hostility between the\nparties that is likely to disrupt the workplace if the employee returns can be a\nreason for denying reinstatement. See, e.g., Deloach, 897 F.2d at 822. Such\nacrimony is often cited by courts that award front pay rather than requiring\nthe plaintiff to return to a discriminatory employer. Id. (addressing employer’s\nappeal of front pay award in which it argued that reinstatement was preferable\neven though the district court had found there was too much discord between\nthe parties for that remedy); see also Walther v. Lone Star Gas Co., 952 F.2d\n\n\n 7\n\f Case: 17-60697 Document: 00514888165 Page: 8 Date Filed: 03/26/2019\n\n\n\n 17-60697\n119, 127 (5th Cir. 1992) (addressing employer’s argument that reinstatement\nshould have been imposed rather than front pay award).\n What makes this a challenging area is that the post-lawsuit context in\nwhich this question arises usually sees some friction between the parties.\nAntagonism is a natural by-product of lawsuits, often even more so for ones\nalleging discrimination. If the hostility common to litigation were sufficient\nfor “denial of reinstatement, reinstatement would cease to be a remedy except\nin cases where the defendant felt like reinstating the plaintiff.” EEOC v.\nCentury Broad. Corp., 957 F.2d 1446, 1462 (7th Cir. 1992); see also Weaver v.\nAmoco Prod. Co., 95 F.3d 52, 1996 WL 459345 at *2 (5th Cir. 1996)\n(unpublished) (noting that the hostility must “exceed the animosity level that\ncommonly arises between opposing parties throughout the litigation process”).\nAnd for reasons we have just explained, the finding of discord cannot rely on\nreasons rejected by the jury, such as hostility stemming from the employee’s\nalleged misconduct that the jury found to be pretextual. Cf. Ray v. Iuka Special\nMun. Separate Sch. Dist., 51 F.3d 1246, 1254 (5th Cir. 1995) (recognizing that\nfinding of discord could not be based “upon reasons rejected by the jury,”\nthough concluding that is not what the district court’s ruling relied on). So\nmore than the friction that typically results from litigation or the employee’s\ntermination is required for the discord to be a reason not to order\nreinstatement.\n The acrimony must rise to the level at which the parties’ relationship is\n“irreparably damaged.” Walther, 952 F.2d at 127; see also Allen, 685 F.2d at\n1306 (“Unless we are willing to withhold full relief from all or most successful\nplaintiffs in discharge cases, and we are not, we cannot allow actual or expected\nill-feeling alone to justify nonreinstatement.”). That “lingering hostility”\nexisted when a plaintiff had alleged that his employer “attempted to black-ball\nhim in the industry” and the employer alleged the plaintiff filed falsified\n 8\n\f Case: 17-60697 Document: 00514888165 Page: 9 Date Filed: 03/26/2019\n\n\n\n 17-60697\nexpense reports, something that it did not allege was a justification for the\nplaintiff’s actual termination but could have been. Palasota, 499 F.3d at 490. 4\n The district court did not find that the relationship between Bogan and\nMTD rose to the level at which it was irreparably damaged and exceeded the\nantagonism that normally results from trials. Walther, 952 F.2d at 127\n(stating that a court should cite “specific instances of discord” for the acrimony\nto justify denying reinstatement). It did describe MTD’s hostility towards\nBogan as “palpable,” but the only example cited was the remedial-phase\ntestimony of the human resources manager when he “discussed the human\nresources issues he would face if the employee review process were to be\nnegated by reinstating Plaintiff.” It is not clear that this problem is one of\nhostility rather than inconvenience. And the concern that a court order of\nreinstatement would be inconsistent with, and thus undermine, the employer’s\nown dispute resolution procedures that resulted in termination would\nseemingly always exist. More than that common situation is needed to find\nthat the relationship between the parties is so broken that it has reached the\npoint of no return. Id. Finally, it is the jury’s finding of discrimination that\ncontradicted the employee review process, so allowing that disagreement to\ndefeat reinstatement runs the risk we have already discussed of not honoring\nthe jury’s verdict. Without evidence that the relationship between Bogan and\nMTD exceeded that which normally accompanies trials, this factor does not\nmilitate against the preferred remedy of reinstatement.\n\n\n\n 4 Examples from other circuits highlight how severe the hostility usually is when\ncourts use it to deny reinstatement. See Hunter v. Town of Mocksville, N.C., 897 F.3d 538,\n562 (4th Cir. 2018) (denying reinstatement when the plaintiff made social media posts\nfollowing his termination calling the city for which he worked a “crooked [expletive] hole of a\ntown” and questioning the judgement of law enforcement decisions); Hammond v. Northland\nCounseling Ctr., Inc., 218 F.3d 886, 892 (8th Cir. 2000) (finding sufficient acrimony to\npreclude reinstatement in a False Claims Act case when there was evidence of attempts by\nthe plaintiff’s coworkers to “intimidate and harass” her after she filed her suit).\n 9\n\f Case: 17-60697 Document: 00514888165 Page: 10 Date Filed: 03/26/2019\n\n\n\n 17-60697\n Because the district court should not have considered two of the four\nfactors it relied on in denying reinstatement, we cannot review its conclusion\nthat Bogan’s reinstatement would not further the remedial goals of Title VII.\nThe remedial discretion is vested in the district court, and we do not know how\nit would exercise that authority with two fewer factors on the “no\nreinstatement” side of the scale. We thus remand for further proceedings\nwithout suggesting how the district court should exercise its discretion based\non the two factors that remain or other permissible considerations that the\ndistrict court may find relevant.\n ***\n AFFIRMED in part, VACATED and REMANDED in part.\n\n\n\n\n 10\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Sheaneter J. BOGAN, Plaintiff-Appellant v. MTD CONSUMER GROUP, INCORPORATED, Defendant-Appellee\\nCourt: U.S. Court of Appeals for the Fifth Circuit\\nDate decided: 2019-03-26\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 17-60697 Document: 00514888165 Page: 1 Date Filed: 03/26/2019\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n FOR THE FIFTH CIRCUIT\\n United States Court of Appeals\\n Fifth Circuit\\n\\n\\n No. 17-60697 FILED\\n March 26, 2019\\n Lyle W. Cayce\\nSHEANETER J. BOGAN., Clerk\\n\\n Plaintiff - Appellant\\n\\nv.\\n\\nMTD CONSUMER GROUP, INCORPORATED,\\n\\n Defendant - Appellee\\n\\n\\n\\n\\n Appeal from the United States District Court\\n for the Northern District of Mississippi\\n\\n\\nBefore WIENER, SOUTHWICK, and COSTA, Circuit Judges.\\nGREGG COSTA, Circuit Judge:\\n Sheaneter Bogan filed suit alleging that she was fired because of her race\\nand sex. A jury found in her favor but awarded her just $1. The district court\\nthen denied Bogan both reinstatement and front pay, leaving her with no\\nremedy. We review the district court’s decision not to award prospective relief.\\nBecause two of the reasons the district court relied on in denying reinstatement\\ndo not support that result, we remand for reconsideration.\\n I.\\n A.\\n Bogan worked at MTD Consumer Group, a manufacturer of outdoor\\npower equipment, for about 20 years. She started with the company in\\n\\f Case: 17-60697 Document: 00514888165 Page: 2 Date Filed: 03/26/2019\\n\\n\\n\\n 17-60697\\nunskilled positions, but while working took full-time classes at a community\\ncollege so she could obtain a skilled position. After she completed that\\ncoursework, MTD eventually promoted Bogan to be a machinist in the Tool and\\nDie department. She remained in that job for about two years until her\\ntermination in April 2013.\\n While pursuing the Tool and Die position, Bogan also began going to\\nschool for a degree in social work. Her supervisors initially accommodated her\\nclass schedule with flexible work hours. But in fall 2012, human resources\\nnotified Bogan that, based on company policy only allowing flexible hours for\\nwork-related schooling, she had to work a normal shift.\\n Despite this decision, Bogan still worked some irregular hours. So\\nBogan’s supervisors reminded her that she had to work the regular 5:00 a.m.\\nto 3:30 p.m shift and could not attend classes during work hours. But on\\noccasion Bogan would squeeze class time into her lunch break. When a\\nsupervisor learned about this, he suspended Bogan. MTD then terminated\\nher, ostensibly because she came back from lunch late. Bogan unsuccessfully\\nappealed her termination to an employee review board.\\n B.\\n After receiving a right-to-sue letter from the EEOC, Bogan filed this suit\\nalleging race and sex discrimination. MTD sought summary judgment. The\\ndistrict court denied that motion, concluding that the evidence could support a\\nfinding that MTD’s reason for the termination was pretextual. For example,\\nother employees “routinely” took lunch breaks that lasted longer than thirty\\nminutes, but Bogan was the only one punished for doing so. The court also\\npointed to doubts about the accuracy of information in Bogan’s personnel file.\\n A four-day trial followed that resulted in the jury finding that MTD\\n“discriminated against [Bogan] on the basis of her race and/or gender.” The\\n\\n\\n 2\\n\\f Case: 17-60697 Document: 00514888165 Page: 3 Date Filed: 03/26/2019\\n\\n\\n\\n 17-60697\\njury awarded her $1, perhaps because of a jury instruction on the consequences\\nof a failure to mitigate, an argument that MTD pushed.\\n Bogan then asked the court for reinstatement or front pay. The district\\ncourt held a hearing after which it denied both requests. It cited four factors\\nthat it believed counseled against reinstatement and refused to order that\\nremedy. For front pay, the court held that MTD established that Bogan did\\nnot mitigate her damages.\\n II.\\n Reinstatement and front pay are equitable remedies. The ultimate\\nexercise of a court’s equitable power is reviewed for abuse of discretion.\\nDeloach v. Delchamps, Inc., 897 F.2d 815, 822 (5th Cir. 1990). An error of law\\nor application of an incorrect legal standard rises to that level. Klier v. Elf\\nAtochem N. Am., Inc., 658 F.3d 468, 474 (5th Cir. 2011). But the factual\\nfindings that underlie the decision to grant or deny relief are reviewed only for\\nclear error. Sellers v. Delgado Cmty. Coll., 839 F.2d 1132, 1138 (5th Cir. 1988).\\n A.\\n That deferential standard for review of factual determinations disposes\\nof Bogan’s appeal of the front pay ruling. Bogan argues she did make\\nreasonable efforts to obtain work and tried to keep up with her training. She\\nmakes some good points, but there was also evidence to support the district\\ncourt’s contrary conclusions. We thus see no clear error in the court’s finding\\nthat Bogan did not use reasonable diligence to obtain “substantially equivalent\\nemployment.” Id.\\n B.\\n That leaves her challenge to the ruling on reinstatement. Reinstatement\\nis the preferred equitable remedy under Title VII. Hansard v. Pepsi-Cola\\nMetro. Bottling Co., 865 F.2d 1461, 1469 (5th Cir. 1989). Reinstatement more\\ntightly fits the termination injury. It does not require answering the front pay\\n 3\\n\\f Case: 17-60697 Document: 00514888165 Page: 4 Date Filed: 03/26/2019\\n\\n\\n\\n 17-60697\\nquestion of “whether and for how long a plaintiff will work in the future,” for\\nwhich a bad guess means either that plaintiff is “left without a remedy” or\\n“end[s] up with a windfall.” Duke v. Uniroyal Inc., 928 F.2d 1413, 1423 (4th\\nCir. 1991); see also Reneau v. Wayne Griffin & Sons, Inc., 945 F.2d 869, 870\\n(5th Cir. 1991) (noting that front pay is “necessarily speculative in nature” and\\nrequires the court to engage in “intelligent guesswork”). And reinstatement\\nrestores not just the financial benefits of a job but also the “psychological\\nbenefits” of work. Allen v. Autauga Cty. Bd. of Educ., 685 F.2d 1302, 1306\\n(11th Cir. 1982). Ergo, reinstatement is most consistent with Title VII’s\\n“‘make-whole’ philosophy.” Hansard, 865 F.2d at 1469.\\n This case presents an unusual situation in which no prospective (or\\nmeaningful retrospective) relief was awarded after a finding of discrimination.\\nOur caselaw contemplates that one form of prospective relief will ordinarily be\\nappropriate when it is requested. We have often said that the trial court’s\\nremedial discretion in this area involves the “selection between reinstatement\\nand front pay.” Brunnemann v. Terra Int'l, Inc., 975 F.2d 175, 180 (5th Cir.\\n1992) (emphasis added); see also Palasota v. Haggar Clothing Co., 499 F.3d\\n474, 489 (5th Cir. 2007) (quoting Brunnemann); Weaver v. Amoco Prod. Co., 66\\nF.3d 85, 88 (5th Cir. 1995) (same). The typical “either/or” nature of this\\nremedial choice is also seen in our statement that “if reinstatement is not\\nfeasible, front pay is the appropriate award.” Weaver, 66 F.3d at 88;\\nBrunnemann, 975 F.2d at 180 (“Generally, if reinstatement is not feasible,\\nfront pay will be awarded.”); see also Weaver v. Casa Gallardo, Inc., 922 F.2d\\n1515, 1528 (11th Cir. 1991) (“[P]revailing Title VII plaintiffs are presumptively\\nentitled to either reinstatement or front pay.”). In discussing another federal\\nemployment statute (the retaliation provision of the Fair Labor Standards\\nAct), Judge Wisdom went so far as to say that “it is impossible for us to imagine\\n\\n\\n 4\\n\\f Case: 17-60697 Document: 00514888165 Page: 5 Date Filed: 03/26/2019\\n\\n\\n\\n 17-60697\\ncases when a denial of both reinstatement and reimbursement would be\\njustified.” 1 Goldberg v. Bama Mfg. Corp., 302 F.2d 152, 156 (5th Cir. 1962).\\n Yet given the equitable nature of these remedies and the limits of our\\nimagining the full variety of situations that arise in the workplace, there may\\nbe outlier situations in which no prospective relief is appropriate for a victim\\nof discrimination. Indeed, although the parties could point to no case from our\\ncourt in which a plaintiff sought either form of prospective relief but received\\nneither, 2 we found one such case involving an award of punitive damages that\\nthe district court concluded was enough to make the victim whole. Hadley v.\\nVAM P T S, 44 F.3d 372, 376 (5th Cir. 1995). The Supreme Court has also\\nidentified one scenario: when after termination the employer obtains evidence\\nof serious employee misconduct. McKennon v. Nashville Banner Publ’g Co.,\\n513 U.S. 352, 361–62 (1995). 3 But our consistent signaling is that the usual\\ncase involves a district court’s choosing which of the two options better serves\\n\\n\\n\\n 1 When Judge Wisdom made that observation, the FLSA did not allow damages for\\nretaliation. 29 U.S.C. § 216(b); Pub. L. 95-151 (1977) (adding provision that allows for both\\nlegal and equitable remedies). It now does, as does Title VII since the Civil Rights Act of\\n1991. 42 U.S.C. § 1981a(a)(1); Pub. L. No. 102-166 (1991). Yet most of the cases cited above\\ndiscussing equitable Title VII remedies arose after the 1991 amendments allowed damages.\\n 2 MTD cited two examples at oral argument, Giles v. Gen. Elec. Co., 245 F.3d 474 (5th\\n\\nCir. 2001) and Hansard, 865 F.2d 1461. In Giles, the plaintiff was denied back pay, but\\nreceived front pay. We indicated that it may have been appropriate to deny front pay, but it\\nwas not an abuse of discretion to allow it. 245 F.3d at 489. In Hansard, we reduced a\\nplaintiff’s back pay for failure to mitigate and remanded the issue of front pay to the district\\ncourt to consider mitigation. 865 F.2d at 1468. Neither of these cases foreclose the possibility\\nthat a plaintiff may be denied a prospective remedy. But neither considered or affirmed a\\njudgment in which a plaintiff was denied any prospective remedy.\\n 3 There are also examples from other circuits. The Eighth Circuit held that evidence\\n\\nof post-termination misconduct (as opposed to McKennon’s after-acquired evidence of pre-\\ntermination misconduct) that would render the plaintiff ineligible for reinstatement may also\\njustify denying both equitable remedies. Sellers v. Mineta, 358 F.3d 1058, 1064 (8th Cir.\\n2004). The Seventh Circuit upheld denial of both reinstatement and front pay when the jury\\nfound the plaintiff’s earning capacity was not harmed as he had changed careers and started\\nreceiving a higher salary. Although he later alleged he had trouble holding that job, the court\\nsaid his employer was not required to “insure his future employment success.” McKnight v.\\nGen. Motors Corp., 973 F.2d 1366, 1372 (7th Cir. 1992).\\n 5\\n\\f Case: 17-60697 Document: 00514888165 Page: 6 Date Filed: 03/26/2019\\n\\n\\n\\n 17-60697\\nthe “purpose of Title VII to make persons whole for injuries suffered on account\\nof unlawful employment discrimination.” Albemarle Paper Co. v. Moody, 422\\nU.S. 405, 418 (1975); Brunnemann, 975 F.2d at 180.\\n Before we can assess whether the district court abused its discretion in\\nnot reinstating Bogan, we review each factor it cited in support of that ruling.\\nThe first two are ones that do counsel against reinstatement. Because Bogan’s\\nposition no longer “exists as it did during her employment,” the district court\\nproperly considered that reinstatement would require training on new\\nmachines and that the company did not have a present opening in the Tool and\\nDie department. See Palasota, 499 F.3d at 489. It was also permissible for the\\ncourt to rely on its finding that Bogan had intended to change careers to social\\nwork. Id.\\n The third reason the district court cited is MTD’s argument that it\\n“would have terminated Plaintiff in the absence of any purported\\ndiscrimination” because of “her inability to follow the rules and her attitude.”\\nSee 42 U.S.C. § 2000e-5(g)(2)(B). Yet the district court did not find that MTD\\nproved this statutory defense, it only noted it as MTD’s position. More\\nfundamentally, the district court could not find in favor of MTD on this issue\\nbecause the jury had rejected it. It was instructed that “[i]f you find by a\\npreponderance of the evidence that MTD Consumer Group Inc has proved it\\nwould have terminated Ms. Bogan’s employment even if it had not considered\\nher race and/or gender, you must find for the Defendant, MTD Consumer\\nGroup Inc, and go no further in your deliberations.” See also FIFTH CIRCUIT\\nPATTERN JURY INSTRUCTIONS (Civil Cases) 11.13 (2014); Price Waterhouse v.\\nHopkins, 490 U.S. 228, 253 (1989). The jury thus must have rejected this\\ndefense in finding that MTD was liable for discrimination. It would be\\nimproper for the court to override the jury’s factfinding on this question when\\ndeciding equitable relief. Smith v. Diffee Ford-Lincoln-Mercury, Inc., 298 F.3d\\n 6\\n\\f Case: 17-60697 Document: 00514888165 Page: 7 Date Filed: 03/26/2019\\n\\n\\n\\n 17-60697\\n955, 965 (10th Cir. 2002) (“[W]hen legal and equitable issues to be decided in\\nthe same case depend on common determinations of fact . . . the court in\\nresolving the equitable issues is then bound by the jury's findings on them.”);\\nIn re Lewis, 845 F.2d 624, 630 (6th Cir. 1988) (“In the context of employment\\ndiscrimination cases, it is well-settled that a jury's findings of discrimination\\nare binding on a court considering reinstatement.”); Hussein v. Oshkosh Motor\\nTruck Co., 816 F.2d 348, 355 (7th Cir. 1987) (“[I]n deciding whether to grant\\nequitable relief under Title VII, the district court [is] prohibited from\\nreconsidering any issues necessarily and actually decided by the jury.”);\\nLindsey v. Am. Cast Iron Pipe Co., 810 F.2d 1094, 1097–98 (11th Cir. 1987)\\n(holding that a district court’s rejection of liquidated damages in an age\\ndiscrimination case was improper because it relied on factual findings “that\\nconflicted with the jury’s findings”); Gibson v. Mohawk Rubber Co., 695 F.2d\\n1093, 1101 (8th Cir. 1982) (stating that the district court “cannot base its\\ndecision on its own factual findings that conflict with those expressly made by\\nthe jury”). Allowing MTD to relitigate the verdict during the remedial phase\\nwas error.\\n The final reason the district court cited in denying reinstatement—\\n“discord between the parties”—is also problematic because of the apparent\\nsource of that acrimony. For understandable reasons, hostility between the\\nparties that is likely to disrupt the workplace if the employee returns can be a\\nreason for denying reinstatement. See, e.g., Deloach, 897 F.2d at 822. Such\\nacrimony is often cited by courts that award front pay rather than requiring\\nthe plaintiff to return to a discriminatory employer. Id. (addressing employer’s\\nappeal of front pay award in which it argued that reinstatement was preferable\\neven though the district court had found there was too much discord between\\nthe parties for that remedy); see also Walther v. Lone Star Gas Co., 952 F.2d\\n\\n\\n 7\\n\\f Case: 17-60697 Document: 00514888165 Page: 8 Date Filed: 03/26/2019\\n\\n\\n\\n 17-60697\\n119, 127 (5th Cir. 1992) (addressing employer’s argument that reinstatement\\nshould have been imposed rather than front pay award).\\n What makes this a challenging area is that the post-lawsuit context in\\nwhich this question arises usually sees some friction between the parties.\\nAntagonism is a natural by-product of lawsuits, often even more so for ones\\nalleging discrimination. If the hostility common to litigation were sufficient\\nfor “denial of reinstatement, reinstatement would cease to be a remedy except\\nin cases where the defendant felt like reinstating the plaintiff.” EEOC v.\\nCentury Broad. Corp., 957 F.2d 1446, 1462 (7th Cir. 1992); see also Weaver v.\\nAmoco Prod. Co., 95 F.3d 52, 1996 WL 459345 at *2 (5th Cir. 1996)\\n(unpublished) (noting that the hostility must “exceed the animosity level that\\ncommonly arises between opposing parties throughout the litigation process”).\\nAnd for reasons we have just explained, the finding of discord cannot rely on\\nreasons rejected by the jury, such as hostility stemming from the employee’s\\nalleged misconduct that the jury found to be pretextual. Cf. Ray v. Iuka Special\\nMun. Separate Sch. Dist., 51 F.3d 1246, 1254 (5th Cir. 1995) (recognizing that\\nfinding of discord could not be based “upon reasons rejected by the jury,”\\nthough concluding that is not what the district court’s ruling relied on). So\\nmore than the friction that typically results from litigation or the employee’s\\ntermination is required for the discord to be a reason not to order\\nreinstatement.\\n The acrimony must rise to the level at which the parties’ relationship is\\n“irreparably damaged.” Walther, 952 F.2d at 127; see also Allen, 685 F.2d at\\n1306 (“Unless we are willing to withhold full relief from all or most successful\\nplaintiffs in discharge cases, and we are not, we cannot allow actual or expected\\nill-feeling alone to justify nonreinstatement.”). That “lingering hostility”\\nexisted when a plaintiff had alleged that his employer “attempted to black-ball\\nhim in the industry” and the employer alleged the plaintiff filed falsified\\n 8\\n\\f Case: 17-60697 Document: 00514888165 Page: 9 Date Filed: 03/26/2019\\n\\n\\n\\n 17-60697\\nexpense reports, something that it did not allege was a justification for the\\nplaintiff’s actual termination but could have been. Palasota, 499 F.3d at 490. 4\\n The district court did not find that the relationship between Bogan and\\nMTD rose to the level at which it was irreparably damaged and exceeded the\\nantagonism that normally results from trials. Walther, 952 F.2d at 127\\n(stating that a court should cite “specific instances of discord” for the acrimony\\nto justify denying reinstatement). It did describe MTD’s hostility towards\\nBogan as “palpable,” but the only example cited was the remedial-phase\\ntestimony of the human resources manager when he “discussed the human\\nresources issues he would face if the employee review process were to be\\nnegated by reinstating Plaintiff.” It is not clear that this problem is one of\\nhostility rather than inconvenience. And the concern that a court order of\\nreinstatement would be inconsistent with, and thus undermine, the employer’s\\nown dispute resolution procedures that resulted in termination would\\nseemingly always exist. More than that common situation is needed to find\\nthat the relationship between the parties is so broken that it has reached the\\npoint of no return. Id. Finally, it is the jury’s finding of discrimination that\\ncontradicted the employee review process, so allowing that disagreement to\\ndefeat reinstatement runs the risk we have already discussed of not honoring\\nthe jury’s verdict. Without evidence that the relationship between Bogan and\\nMTD exceeded that which normally accompanies trials, this factor does not\\nmilitate against the preferred remedy of reinstatement.\\n\\n\\n\\n 4 Examples from other circuits highlight how severe the hostility usually is when\\ncourts use it to deny reinstatement. See Hunter v. Town of Mocksville, N.C., 897 F.3d 538,\\n562 (4th Cir. 2018) (denying reinstatement when the plaintiff made social media posts\\nfollowing his termination calling the city for which he worked a “crooked [expletive] hole of a\\ntown” and questioning the judgement of law enforcement decisions); Hammond v. Northland\\nCounseling Ctr., Inc., 218 F.3d 886, 892 (8th Cir. 2000) (finding sufficient acrimony to\\npreclude reinstatement in a False Claims Act case when there was evidence of attempts by\\nthe plaintiff’s coworkers to “intimidate and harass” her after she filed her suit).\\n 9\\n\\f Case: 17-60697 Document: 00514888165 Page: 10 Date Filed: 03/26/2019\\n\\n\\n\\n 17-60697\\n Because the district court should not have considered two of the four\\nfactors it relied on in denying reinstatement, we cannot review its conclusion\\nthat Bogan’s reinstatement would not further the remedial goals of Title VII.\\nThe remedial discretion is vested in the district court, and we do not know how\\nit would exercise that authority with two fewer factors on the “no\\nreinstatement” side of the scale. We thus remand for further proceedings\\nwithout suggesting how the district court should exercise its discretion based\\non the two factors that remain or other permissible considerations that the\\ndistrict court may find relevant.\\n ***\\n AFFIRMED in part, VACATED and REMANDED in part.\\n\\n\\n\\n\\n 10\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}}],"truncated":false,"partial":false},"paginationData":{"pageIndex":10,"numItemsPerPage":100,"numTotalItems":31175,"offset":1000,"length":100}},"jwt":"eyJhbGciOiJFZERTQSJ9.eyJyZWFkIjp0cnVlLCJwZXJtaXNzaW9ucyI6eyJyZXBvLmNvbnRlbnQucmVhZCI6dHJ1ZX0sImlhdCI6MTc3ODc3MjA0NCwic3ViIjoiL2RhdGFzZXRzL2VpdGFucy1wdS9jbC1jb2RpbmctaW5wdXQiLCJleHAiOjE3Nzg3NzU2NDQsImlzcyI6Imh0dHBzOi8vaHVnZ2luZ2ZhY2UuY28ifQ.OPTgLA3s6CX6ksjj_tse9FgAOT5QTszvBrt33AmEx9Uc-a0EVy3Bw2jGlvM13aYziur9KouhL9wjyWUwgSPAAA","displayUrls":true,"splitSizeSummaries":[{"config":"default","split":"train","numRows":31175,"numBytesParquet":1629387251}]},"discussionsStats":{"closed":0,"open":1,"total":1},"fullWidth":true,"hasGatedAccess":true,"hasFullAccess":true,"isEmbedded":false,"savedQueries":{"community":[],"user":[]}}">
id int64 | name string | name_abbreviation string | decision_date string | docket_number string | court string | casebody string | judge1 string | judge2 string | judge3 string | exactly_three_caps int64 | extra_judges string | judge_designations string | opinions_count int64 | majority_count int64 | dissent_count int64 | concurrence_count int64 | other_count int64 | primary_citation string | reporter string | volume null | resource_url string | precedential_status string | 010combined_count int64 | 020lead_count int64 | 030concurrence_count int64 | 035concurrenceinpart_count int64 | 040dissent_count int64 | year int64 | month int64 | messages list |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
4,596,439 | Singh v. Cigna Corp. | 2019-03-05 | 17-3484-cv | U.S. Court of Appeals for the Second Circuit | {"judges": "Before: CABRANES and SACK, Circuit Judges, and KOELTL, District Judge.", "parties": "", "opinions": [{"author": "District of Connecticut (Vanessa L. Bryant, Judge) dismissing this class", "type": "010combined", "text": "17‐3484‐cv \nSi... | CABRANES | SACK | KOELTL | 1 | {"CABRANES": ", Circuit", "SACK": ", Circuit", "KOELTL": ", District"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4596439/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,596,440 | SECURITIES AND EXCHANGE COMMISSION, Plaintiff-Appellee, v. Raj RAJARATNAM, Defendant-Appellant, Galleon Management, LP, Ali Hariri, Rajiv Goel, Anil Kumar, Danielle Cheisi, Mark Kurland, Robert Moffat, New Castle Funds LLC, Roomy Khan, Deep Shah, Ali T. Far, Choo-Beng Lee, Far & Lee LLC, Spherix Capital LLC, Zvi Goffer... | S.E.C. v. Rajaratnam | 2019-03-05 | Docket 11-5124-cv; August Term, 2018 | U.S. Court of Appeals for the Second Circuit | {"judges": "Raggi, Lynch, Droney", "parties": "", "opinions": [{"author": "GERARD E. LYNCH, Circuit Judge:", "type": "010combined", "text": "11-5124-cv\nSEC v. Rajaratnam\n\n\n\n UNITED STATES COURT OF APPEALS\n FOR THE SECOND CIRCUIT\n\n\n\n ... | RAGGI | LYNCH | DRONEY | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4596440/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
8,443,917 | United States v. Jay KROLL | United States v. Kroll | 2019-03-05 | No. 16-4310; August Term, 2017 | U.S. Court of Appeals for the Second Circuit | {"judges": "Droney, Leval, Lynch", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415348/", "author_raw": ""}]} | DRONEY | LEVAL | LYNCH | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443917/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
8,443,918 | Minohor SINGH, Individually and On Behalf of All Others Similarly Situated, Lead v. CIGNA CORPORATION, David Cordani, Thomas A. McCarthy, Herbert A. Fritch, Richard Appel | Singh v. Cigna Corp. | 2019-03-05 | No. 17-3484-cv; August Term 2018 | U.S. Court of Appeals for the Second Circuit | {"judges": "Cabranes, Koeltl, Sack", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415349/", "author_raw": ""}]} | CABRANES | KOELTL | SACK | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443918/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,596,929 | Fox v. Costco Wholesale Corporation | 2019-03-06 | 17-0936-cv | U.S. Court of Appeals for the Second Circuit | {"judges": "Before: JACOBS, HALL, and DRONEY, Circuit Judges.", "parties": "", "opinions": [{"author": "HALL, Circuit Judge:", "type": "010combined", "text": "17‐0936‐cv \nFox v. Costco Wholesale Corporation \n\n\n In the\n United States Court of Appeals\n ... | JACOBS | HALL | DRONEY | 1 | {"JACOBS": ", Circuit", "HALL": ", Circuit", "DRONEY": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4596929/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
8,443,919 | Christopher FOX v. COSTCO WHOLESALE CORPORATION | Fox v. Costco Wholesale Corp. | 2019-03-06 | Docket No. 17-0936-cv; August Term, 2017 | U.S. Court of Appeals for the Second Circuit | {"judges": "Droney, Hall, Jacobs", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415350/", "author_raw": ""}]} | DRONEY | HALL | JACOBS | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443919/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,597,484 | VERMONT RAILWAY, INC., Plaintiff-Counter-Defendant - Appellee, v. TOWN OF SHELBURNE, Defendant-Counter-Claimant - Appellant, Joe Colangelo, in His Capacity as Town Manager and Zoning Enforcement Officer, Defendant. | Vt. Ry., Inc. v. Town of Shelburne | 2019-03-07 | Docket 18-188-cv; August Term, 2018 | U.S. Court of Appeals for the Second Circuit | {"judges": "Hall, Raggi, Sullivan", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/9888112/", "author_raw": ""}, {"author": "", "type": "035concurrenceinpart", "text": "", "resource_uri": "https://www.courtlistener.com/api/re... | HALL | RAGGI | SULLIVAN | 1 | {} | 4 | 0 | 0 | 2 | 2 | null | https://www.courtlistener.com/api/rest/v4/clusters/4597484/ | Published | 1 | 1 | 0 | 1 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,597,485 | 3911-Cv | 2019-03-07 | U.S. Court of Appeals for the Second Circuit | {"judges": "Before: LIVINGSTON and CHIN, Circuit Judges, and CROTTY, District Judge.", "parties": "", "opinions": [{"author": "CHIN, Circuit Judge:", "type": "010combined", "text": "17‐3911‐cv \nCooke v. United States \n UNITED STATES COURT OF APPEALS \n FOR... | LIVINGSTON | CHIN | CROTTY | 1 | {"LIVINGSTON": ", Circuit", "CHIN": ", Circuit", "CROTTY": ", District"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4597485/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||||
4,597,534 | Vt. Ry. v. Town of Shelburne | 2019-03-07 | 18-188-cv | U.S. Court of Appeals for the Second Circuit | {"judges": "Before: RAGGI, HALL, and SULLIVAN, Circuit Judges.", "parties": "", "opinions": [{"author": "HALL, Circuit Judge:", "type": "010combined", "text": "18-188-cv\nVt. Ry. v. Town of Shelburne\n\n\n In the\n United States Court of Appeals\n ... | RAGGI | HALL | SULLIVAN | 1 | {"RAGGI": ", Circuit", "HALL": ", Circuit", "SULLIVAN": ", Circuit"} | 2 | 0 | 0 | 1 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4597534/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,597,535 | Cooke v. United States | 2019-03-07 | 17-3911-cv | U.S. Court of Appeals for the Second Circuit | {"judges": "Before: LIVINGSTON and CHIN, Circuit Judges, and CROTTY, District Judge.", "parties": "", "opinions": [{"author": "CHIN, Circuit Judge:", "type": "010combined", "text": "17‐3911‐cv \nCooke v. United States \n UNITED STATES COURT OF APPEALS \n FOR... | LIVINGSTON | CHIN | CROTTY | 1 | {"LIVINGSTON": ", Circuit", "CHIN": ", Circuit", "CROTTY": ", District"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4597535/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
8,443,920 | Jessica COOKE v. United States | Cooke v. United States | 2019-03-07 | Docket No. 17-3911-cv; August Term 2018 | U.S. Court of Appeals for the Second Circuit | {"judges": "Chin, Crotty, Livingston", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415351/", "author_raw": ""}]} | CHIN | CROTTY | LIVINGSTON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443920/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,598,690 | Kolbasyuk v. Capital Mgmt. Servs., LP | 2019-03-12 | 18-1260-cv | U.S. Court of Appeals for the Second Circuit | {"judges": "Before: SACK, LIVINGSTON, and CHIN, Circuit Judges.", "parties": "", "opinions": [{"author": "DEBRA ANN LIVINGSTON, Circuit Judge:", "type": "010combined", "text": "18‐1260‐cv \nKolbasyuk v. Capital Mgmt. Servs., LP \n \n UNITED STATES COURT OF APPEALS \n ... | SACK | LIVINGSTON | CHIN | 1 | {"SACK": ", Circuit", "LIVINGSTON": ", Circuit", "CHIN": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4598690/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,598,691 | GEOMC CO., LTD., Plaintiff-Counter-Defendant-Appellee, v. CALMARE THERAPEUTICS INCORPORATED, Defendant-Counter-Claimant-Appellant. | GEOMC Co., Ltd. v. Calmare Therapeutics Inc. | 2019-03-12 | Docket 17-3502-cv; August Term 2018 | U.S. Court of Appeals for the Second Circuit | {"judges": "Newman, Jacobs, Pooler", "parties": "", "opinions": [{"author": "JON O. NEWMAN, Circuit Judge:", "type": "010combined", "text": "17-3502-cv\nGEOMC Co., Ltd. v. Calmare Therapeutics Inc.\n\n \n UNITED ... | NEWMAN | JACOBS | POOLER | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4598691/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
8,443,924 | Yuri KOLBASYUK, on Behalf of Himself and All Others Similarly Situated v. CAPITAL MANAGEMENT SERVICES, LP | Kolbasyuk ex rel. Situated v. Capital Mgmt. Servs., LP | 2019-03-12 | No. 18-1260-cv; August Term 2018 | U.S. Court of Appeals for the Second Circuit | {"judges": "Chin, Livingston, Sack", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415355/", "author_raw": ""}]} | CHIN | LIVINGSTON | SACK | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443924/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,599,044 | Haar v. Nationwide Mutual Fire Ins. Co. | 2019-03-13 | 18-128 | U.S. Court of Appeals for the Second Circuit | {"judges": "B e f o r e: KATZMANN, Chief Judge, HALL and LYNCH, Circuit Judges.", "parties": "", "opinions": [{"author": "PER CURIAM", "type": "010combined", "text": "18‐128 \nHaar v. Nationwide Mutual Fire Ins. Co. \n \n UNITED STATES COURT OF APPEALS \n FOR THE SECOND CIR... | KATZMANN | HALL | LYNCH | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4599044/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,600,776 | United States v. Black | 2019-03-18 | 18-496-cr (L) | U.S. Court of Appeals for the Second Circuit | {"judges": "Before: NEWMAN and POOLER, Circuit Judges, and COTE, District Judge.", "parties": "", "opinions": [{"author": "POOLER, Circuit Judge:", "type": "010combined", "text": "18‐496‐cr (L) \nUnited States v. Black \n UNITED STATES COURT OF APPEALS \n FOR THE SECOND CI... | NEWMAN | POOLER | COTE | 1 | {"NEWMAN": ", Circuit", "POOLER": ", Circuit", "COTE": ", District"} | 2 | 0 | 0 | 1 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4600776/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
8,443,925 | UNITED STATES of America, Appellant-Cross-Appellee v. Rodshaun BLACK, aka Rashaun Black, aka Shaun, Daniel Rodriguez, aka Danny, Ernest Green, aka Ern, Defendants-Appellees-Cross-Appellants. | United States v. Black | 2019-03-18 | Docket Nos. 18-496-cr(L); 18-548-cr(XAP); 18-574-cr(XAP); August Term, 2018 | U.S. Court of Appeals for the Second Circuit | {"judges": "Cote, Newman, Pooler", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415356/", "author_raw": ""}]} | COTE | NEWMAN | POOLER | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443925/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,601,054 | Kaplan v. Reed Smith LLP | 2019-03-19 | 17-4067-cv(L) | U.S. Court of Appeals for the Second Circuit | {"judges": "Before: LEVAL, POOLER, and LIVINGSTON, Circuit Judges.", "parties": "", "opinions": [{"author": "PER CURIAM", "type": "010combined", "text": "17‐4067‐cv(L) \nKaplan v. Reed Smith LLP \n \n UNITED STATES COURT OF APPEALS \n FOR THE SECOND CIRCUIT \n ... | LEVAL | POOLER | LIVINGSTON | 1 | {"LEVAL": ", Circuit", "POOLER": ", Circuit", "LIVINGSTON": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4601054/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
8,443,936 | David E. KAPLAN, individually and on behalf of all others similarly situated, Michael S. Allen, individually and on behalf of all others similarly situated, Chi-Pin Hsu, individually and on behalf of all others similarly situated, Fred M. Ross, Gary W. Muensterman, individually and on behalf of all others similarly sit... | Kaplan v. Reed Smith LLP | 2019-03-19 | Docket Nos. 17-4067-cv(L); 17-4144(XAP); August Term, 2018 | U.S. Court of Appeals for the Second Circuit | {"judges": "Leval, Livingston, Pooler", "parties": "", "opinions": [{"author": "PER CURIAM", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415367/", "author_raw": "PER CURIAM"}]} | LEVAL | LIVINGSTON | POOLER | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443936/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,601,359 | Tooly v. Schwaller | 2019-03-20 | 17-3564-cv | U.S. Court of Appeals for the Second Circuit | {"judges": "Before: WALKER, CALABRESI, and LIVINGSTON, Circuit Judges.", "parties": "", "opinions": [{"author": "GUIDO CALABRESI, Circuit Judge:", "type": "010combined", "text": "17‐3564‐cv \n Tooly v. Schwaller \n \n 1 UNITED STATES COURT OF APPEALS \n 2 ... | WALKER | CALABRESI | LIVINGSTON | 1 | {"WALKER": ", Circuit", "CALABRESI": ", Circuit", "LIVINGSTON": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4601359/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,601,360 | John DETTELIS Plaintiff-Appellant, v. Michael R. SHARBAUGH, Cattaraugus County Department of Probation Supervisor, Denise Longarvsky, Cattaraugus County Department of Probation Officer, Gerald Zimmerman, Cattaraugus County Department of Probation Director, Defendants-Appellees. | Dettelis v. Sharbaugh | 2019-03-20 | Docket 17-4150-cv; August Term, 2018 | U.S. Court of Appeals for the Second Circuit | {"judges": "Hall, Per Curiam, Raggi, Sullivan", "parties": "", "opinions": [{"author": "PER CURIAM", "type": "010combined", "text": "17-4150\nDettelis v. Sharbaugh\n\n\n In the\n United States Court of Appeals\n For the Second Circuit\n... | HALL | RAGGI | SULLIVAN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4601360/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
8,443,937 | Paul TOOLY v. John F. SCHWALLER, State University of New York At Potsdam, Mary Dolan | Tooly v. Schwaller | 2019-03-20 | Docket No. 17-3564-cv; August Term 2018 | U.S. Court of Appeals for the Second Circuit | {"judges": "Calabresi, Livingston, Walker", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415368/", "author_raw": ""}]} | CALABRESI | LIVINGSTON | WALKER | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443937/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,602,165 | UNITED STATES of America, Appellee, v. Gaurav MEHTA, Defendant-Appellant, Mary Opoka, Defendant-Appellant, Isha Mehta, Defendant-Appellant. | United States v. Mehta | 2019-03-21 | 16-2585 (L) | U.S. Court of Appeals for the Second Circuit | {"judges": "Parker, Livingston, Chin", "parties": "", "opinions": [{"author": "Thomas J. McAvoy, District Judge.", "type": "010combined", "text": "16-2585 (L)\n United States v. Mehta\n\n\n 1 In the\n 2 United States Court of Appeals\n 3 ... | PARKER | LIVINGSTON | CHIN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4602165/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,602,780 | Metropolitan Life Ins. Co. v. Bucsek | 2019-03-22 | 17-881 | U.S. Court of Appeals for the Second Circuit | {"judges": "Before: 25 26 KATZMANN, Chief Judge, LEVAL, Circuit Judge, and CARTER, District 27 Judge.", "parties": "", "opinions": [{"author": "LEVAL, Circuit Judge:", "type": "010combined", "text": "17-881\n Metropolitan Life Ins. Co. v. Bucsek\n\n 1 UNITED STATES COURT OF APPEALS \n 2 ... | KATZMANN | LEVAL | CARTER | 1 | {"KATZMANN": ", Chief", "LEVAL": ", Circuit", "CARTER": ", District"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4602780/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
8,443,938 | METROPOLITAN LIFE INSURANCE CO. v. John BUCSEK | Metro. Life Ins. Co. v. Bucsek | 2019-03-22 | Docket No. 17-881; August Term, 2017 | U.S. Court of Appeals for the Second Circuit | {"judges": "Carter, Katzmann, Leval", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415369/", "author_raw": ""}]} | CARTER | KATZMANN | LEVAL | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443938/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,603,230 | Manhattan Review, LLC v. Tracy Yun | 2019-03-25 | 17-4046-cv | U.S. Court of Appeals for the Second Circuit | {"judges": "Before: LIVINGSTON and LOHIER, Circuit Judges, and CROTTY, District Judge.", "parties": "", "opinions": [{"author": "Judge Paul A. Crotty, of the United States District Court for the Southern District", "type": "010combined", "text": "17‐4046‐cv \nManhattan Review, LLC, et al. v. Tracy Yun, et al. \n \n ... | LIVINGSTON | LOHIER | CROTTY | 1 | {"LIVINGSTON": ", Circuit", "LOHIER": ", Circuit", "CROTTY": ", District"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4603230/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
8,443,935 | MANHATTAN REVIEW LLC and Joern Meissner, derivatively on behalf of Manhattan Review LLC v. Tracy YUN, Manhattan Enterprise Group LLC, d/b/a Manhattan Elite Prep, and Christopher Kelly | Manhattan Review LLC v. YUN | 2019-03-25 | No. 17-4046-cv; August Term 2018 | U.S. Court of Appeals for the Second Circuit | {"judges": "Crotty, Livingston, Lohier", "parties": "", "opinions": [{"author": "PER CURIAM", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415366/", "author_raw": "PER CURIAM"}]} | CROTTY | LIVINGSTON | LOHIER | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443935/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,603,612 | Gibbons v. Bristol-Myers Squibb Co. | 2019-03-26 | 17-2638 | U.S. Court of Appeals for the Second Circuit | {"judges": "Before: LIVINGSTON, CARNEY, SULLIVAN, CIRCUIT JUDGES.", "parties": "", "opinions": [{"author": "RICHARD J. SULLIVAN, Circuit Judge:", "type": "010combined", "text": "17‐2638, et al. \nGibbons v. Bristol‐Myers Squibb Co.\n\n\n United States Court of Appeals\n f... | LIVINGSTON | CARNEY | SULLIVAN | 1 | {"LIVINGSTON": ", CIRCUIT", "CARNEY": ", CIRCUIT", "SULLIVAN": ", CIRCUIT"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4603612/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
8,443,941 | Catherine GIBBONS v. BRISTOL-MYERS SQUIBB COMPANY and Pfizer Inc. | Gibbons v. Bristol-Myers Squibb Co. | 2019-03-26 | Nos. 17-2638; 17-2642; 17-2643; 17-2648; 17-2661; 17-2667; 17-2677; 17-2687; 17-3765; 17-3867; August Term 2018 | U.S. Court of Appeals for the Second Circuit | {"judges": "Carney, Livingston, Sullivan", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415372/", "author_raw": ""}]} | CARNEY | LIVINGSTON | SULLIVAN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443941/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,604,043 | Newman v. Jewish Agency for Israel | 2019-03-27 | 18-244-cv (L) | U.S. Court of Appeals for the Second Circuit | {"judges": "Before PARKER, CHIN, and SULLIVAN, Circuit Judges.", "parties": "", "opinions": [{"author": "PER CURIAM", "type": "010combined", "text": "18-244-cv (L)\nNewman v. Jewish Agency for Israel \n \n UNITED STATES COURT O... | PARKER | CHIN | SULLIVAN | 1 | {"PARKER": ", Circuit", "CHIN": ", Circuit", "SULLIVAN": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4604043/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
8,443,942 | Eitan ELIAHU, Dotan Newman, R. David Weisskopf, Eldad Gidon, Michael Zamansky, Yakov Bossira, Dan Silberman v. JEWISH AGENCY FOR ISRAEL, New Israel Fund, Jewish Federations of North America, Na'amat, Women's International Zionist Organization, P.E.F. Israel Endowment Funds, Inc., Tzipi Livni, Shmuel Chamdani, Na'ama Bo... | Eliahu v. Jewish Agency for Isr. | 2019-03-27 | Docket No. 18-244-cv (L); 18-246-cv (Con); August Term 2018 | U.S. Court of Appeals for the Second Circuit | {"judges": "Chin, Parker, Sullivan", "parties": "", "opinions": [{"author": "PER CURIAM", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415373/", "author_raw": "PER CURIAM"}]} | CHIN | PARKER | SULLIVAN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443942/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,596,445 | UNITED STATES of America v. Vernel Aubrey WILLIAMS, Appellant | United States v. Vernel Williams | 2019-03-05 | 17-3422 | U.S. Court of Appeals for the Third Circuit | {"judges": "Chagares, Hardiman, Restrepo", "parties": "", "opinions": [{"author": "RESTREPO, Circuit Judge.", "type": "010combined", "text": "PRECEDENTIAL\n\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _____________\n\n No. 17-3422\n ... | CHAGARES | HARDIMAN | RESTREPO | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4596445/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,596,446 | UNITED STATES of America v. Kevin L. REESE, Appellant | United States v. Kevin Reese | 2019-03-05 | 17-2484 | U.S. Court of Appeals for the Third Circuit | {"judges": "Before: AMBRO, CHAGARES, and GREENAWAY, JR., Circuit Judges (Opinion", "parties": "", "opinions": [{"author": "AMBRO, Circuit Judge", "type": "010combined", "text": "PRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n ________________\n\n No. 17-2484\n ... | AMBRO | CHAGARES | GREENAWAY JR | 1 | {"AMBRO": ", GREENAWAY, JR , Circuit", "CHAGARES": ", GREENAWAY, JR , Circuit", "GREENAWAY JR": ", GREENAWAY, JR , Circuit"} | 2 | 0 | 0 | 1 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4596446/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,597,146 | UNITED STATES of America v. Aracelis N. AYALA A/K/A Gordita A/K/A Fluff Aracelis N. Ayala, Appellant | United States v. Aracelis Ayala | 2019-03-06 | 17-2422 | U.S. Court of Appeals for the Third Circuit | {"judges": "Chagares, Hardiman, Restrepo", "parties": "", "opinions": [{"author": "CHAGARES, Circuit Judge.", "type": "010combined", "text": "PRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _____________\n\n No. 17-2422\n _____... | CHAGARES | HARDIMAN | RESTREPO | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4597146/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,597,697 | Jozef R. MADAR, Appellant v. UNITED STATES CITIZENSHIP AND IMMIGRATION SERVICES | Madar v. U.S. Citizenship & Immigration Servs. | 2019-03-07 | 18-1741 | U.S. Court of Appeals for the Third Circuit | {"judges": "Greenaway, Shwartz, Porter", "parties": "", "opinions": [{"author": "PORTER, Circuit Judge.", "type": "010combined", "text": "PRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _______________\n\n No. 18-1741\n ... | GREENAWAY | SHWARTZ | PORTER | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4597697/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,598,126 | Jozef Madar v. USCIS | 2019-03-07 | 18-1741 | U.S. Court of Appeals for the Third Circuit | {"judges": "Before: GREENAWAY, JR., SHWARTZ, and PORTER, Circuit Judges.", "parties": "", "opinions": [{"author": "PORTER, Circuit Judge.", "type": "010combined", "text": "PRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _______________\n\n No. 18-174... | GREENAWAY JR | SHWARTZ | PORTER | 1 | {"GREENAWAY JR": ", Circuit", "SHWARTZ": ", Circuit", "PORTER": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4598126/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,598,125 | Ahmed KAMAL, on Behalf of Himself and the Putative Class, Appellant in No. 17-2345 v. J. CREW GROUP, INC.; J Crew Inc.; J. Crew Intermediate LLC ; J Crew International, Inc.; J. Crew Operating Corp; J. Crew Services, Inc.; Chinos Acquisition Corp ; Chinos Holdings, Inc., Appellants in No. 17-2453 | Ahmed Kamal v. J. Crew Group, Inc. | 2019-03-08 | 17-2345; 17-2453 | U.S. Court of Appeals for the Third Circuit | {"judges": "Chagares, Rendell, Scirica", "parties": "", "opinions": [{"author": "SCIRICA, Circuit Judge", "type": "010combined", "text": "PRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n\n ___________\n\n Nos. 17-2345 and 17-2453\n ... | CHAGARES | RENDELL | SCIRICA | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4598125/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,598,811 | Chrysoula Komis v. Secretary United States Depart | 2019-03-12 | 14-3813 | U.S. Court of Appeals for the Third Circuit | {"judges": "Before: GREENAWAY, JR., SCIRICA, and ROTH, Circuit Judges.", "parties": "", "opinions": [{"author": "SCIRICA, Circuit Judge", "type": "010combined", "text": "PRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _______________\n\n No. 1... | GREENAWAY JR | SCIRICA | ROTH | 1 | {"GREENAWAY JR": ", Circuit", "SCIRICA": ", Circuit", "ROTH": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4598811/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
8,443,926 | Chrysoula J. KOMIS v. SECRETARY OF the UNITED STATES DEPARTMENT OF LABOR | Komis v. Sec'y of the U.S. Dep't of Labor | 2019-03-12 | No. 14-3813 | U.S. Court of Appeals for the Third Circuit | {"judges": "Greenaway, Roth, Scirica", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415357/", "author_raw": ""}]} | GREENAWAY | ROTH | SCIRICA | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443926/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,599,846 | UNITED STATES of America EX REL. Jane DOE v. HEART SOLUTION, PC; Biosound Medical Services ; Kirtish N. Patel; Nimesh Patel; Nita K. Patel Heart Solution PC and Nita K. Patel, Appellants | U.S. Ex Rel. Jane Doe v. Heart Solution, PC | 2019-03-14 | 17-2019 | U.S. Court of Appeals for the Third Circuit | {"judges": "Before: JORDAN, ROTH, Circuit Judges and STEARNS, District Judge (Opinion", "parties": "", "opinions": [{"author": "Judge for the District of Massachusetts, sitting by", "type": "010combined", "text": "PRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _________... | JORDAN | ROTH | STEARNS | 1 | {"JORDAN": ", Circuit", "ROTH": ", Circuit", "STEARNS": ", District"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4599846/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,601,580 | James RANDALL, Appellant v. CITY OF PHILADELPHIA LAW DEPARTMENT; John Mouzon, Philadelphia Police Officer Badge #5293; Leon McKnight, Philadelphia Police Officer Badge #6630 | James Randall v. Philadelphia Law Department | 2019-03-20 | 18-2303 | U.S. Court of Appeals for the Third Circuit | {"judges": "Smith, Chagares, Bibas", "parties": "", "opinions": [{"author": "BIBAS, Circuit Judge.", "type": "010combined", "text": "PRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _______________\n\n No. 18-2303\n _______________\n... | SMITH | CHAGARES | BIBAS | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4601580/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,596,712 | UNITED STATES of America, Plaintiff - Appellee, v. Tomonta SIMMONS, Defendant - Appellant. | United States v. Tomonta Simmons | 2019-03-04 | 17-4618 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Gregory, Duncan, Diaz", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/9888102/", "author_raw": ""}, {"author": "", "type": "030concurrence", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/... | GREGORY | DUNCAN | DIAZ | 1 | {} | 4 | 0 | 0 | 2 | 2 | null | https://www.courtlistener.com/api/rest/v4/clusters/4596712/ | Published | 1 | 1 | 1 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,596,714 | UNITED STATES of America, Plaintiff - Appellee, v. Darryl Eugene MILLS, Defendant - Appellant. | United States v. Darryl Mills | 2019-03-05 | 16-4777 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Wilkinson, Niemeyer, King", "parties": "", "opinions": [{"author": "NIEMEYER, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 16-4777\n\n\nUNITE... | WILKINSON | NIEMEYER | KING | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4596714/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,596,717 | Johnnie WILLIAMS, Plaintiff-Appellee, and Son Odarious Williams, Plaintiff v. Lance Corporal Kyle STRICKLAND, Defendant-Appellant and Cpl Heroux; Sgt Walter Criddle; Beaufort County Sheriff Office; Raymond S. Heroux, Defendants. Johnnie Williams, Plaintiff-Appellee, and Son Odarious Williams, Plaintiff, v. Raymond S. H... | Johnnie Williams v. Lance Corporal Kyle Strickland | 2019-03-05 | 18-6219; 18-6220 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Keenan, Floyd, Thacker", "parties": "", "opinions": [{"author": "FLOYD, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-6219\n\n\nJOHNNIE WILLIAMS,\n\n ... | KEENAN | FLOYD | THACKER | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4596717/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,597,162 | United States v. Tomonta Simmons | 2019-03-06 | 17-4618 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Before GREGORY, Chief Judge, DUNCAN, and DIAZ, Circuit Judges.", "parties": "", "opinions": [{"author": "Vacated and remanded by published opinion. Chief Judge Gregory authored the opinion", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n ... | GREGORY | DUNCAN | DIAZ | 1 | {"GREGORY": ", Chief", "DUNCAN": ", Circuit", "DIAZ": ", Circuit"} | 2 | 0 | 0 | 1 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4597162/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,597,166 | Patrick HATELY, an Individual, Plaintiff - Appellant, v. Dr. David WATTS, an Individual, Defendant - Appellee. the Center for Democracy & Technology; The Electronic Frontier Foundation; New America's Open Technology Institute, Amici Supporting Appellant, Digital Justice Foundation, Amicus Supporting Appellee. | Patrick Hately v. Dr. David Watts | 2019-03-06 | 18-1306 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Gregory, Motz, Wynn", "parties": "", "opinions": [{"author": "WYNN, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-1306\n\n\nPAT... | GREGORY | MOTZ | WYNN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4597166/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,597,173 | EQUINOR USA ONSHORE PROPERTIES INC., F/K/A Statoil USA Onshore Properties, Inc., Plaintiff - Appellee, v. PINE RESOURCES, LLC, Defendant - Appellant. | Equinor USA Onshore Properties v. Pine Resources, LLC | 2019-03-06 | 18-1291 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Gregory, Motz, Floyd", "parties": "", "opinions": [{"author": "Affirmed by published opinion. Chief Judge Gregory authored the opinion, in which", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n ... | GREGORY | MOTZ | FLOYD | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4597173/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,597,176 | Anthony ROBINSON, Plaintiff - Appellant, v. UNITED STATES DEPARTMENT OF EDUCATION, Defendant - Appellee, and Pennsylvania Higher Education Assistance Agency, D/B/A Fed Loan Servicing; Equifax Information Services, LLC; Experian Information Solutions, Inc.; Trans Union, LLC, Defendants. | Anthony Robinson v. US Department of Education | 2019-03-06 | 18-1822 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Wilkinson, Diaz, Floyd", "parties": "", "opinions": [{"author": "WILKINSON, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-1822\n\n\nANTHONY ... | WILKINSON | DIAZ | FLOYD | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4597176/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,598,146 | UNITED STATES of America, Plaintiff - Appellee, v. Steven Lavonne MORRIS, A/K/A Worm, Defendant - Appellant. | United States v. Steven Morris | 2019-03-08 | 17-6709 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Agee, Diaz, Harris", "parties": "", "opinions": [{"author": "PAMELA HARRIS, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 17-6709\n\n\nUNITED STA... | AGEE | DIAZ | HARRIS | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4598146/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,598,532 | PARADISE WIRE & CABLE DEFINED BENEFIT PENSION PLAN; Hollingsworth, Mendenhall and McFadden, LLC; IG Holdings, Incorporated ; IG Revocable Trust; Dr. Stuart Wollman; Sheila Rosenberg; Rene Demeule, Individually on Behalf of Themselves and All Others Similarly Situated, Plaintiffs-Appellants, v. Edward M. WEIL, Jr.; Amer... | Paradise Wire & Cable Defined Benefit Pension Plan v. Weil | 2019-03-11 | 18-1483 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Niemeyer, Duncan, Quattlebaum", "parties": "", "opinions": [{"author": "QUATTLEBAUM, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-1483\n... | NIEMEYER | DUNCAN | QUATTLEBAUM | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4598532/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,598,857 | UNITED STATES of America, Plaintiff - Appellee v. William R. WHYTE, Defendant - Appellant, and Armet Armored Vehicles, Inc., Defendant. | United States v. William Whyte | 2019-03-12 | 18-4123 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Agee, Diaz, Harris", "parties": "", "opinions": [{"author": "AGEE, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-4123\n\n\n\nUNITED STATES O... | AGEE | DIAZ | HARRIS | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4598857/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,598,860 | SANITARY BOARD OF the CITY OF CHARLESTON, WEST VIRGINIA, Plaintiff - Appellant, v. Andrew WHEELER, Acting Administrator of the United States Environmental Protection Agency; United States Environmental Protection Agency, Defendants - Appellees. | Sanitary Brd of Charleston v. Andrew Wheeler | 2019-03-12 | 18-1592 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Wilkinson, Diaz, Floyd", "parties": "", "opinions": [{"author": "WILKINSON, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-1592\n\n\nSANITAR... | WILKINSON | DIAZ | FLOYD | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4598860/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,599,176 | Mountain Valley Pipeline, LLC v. Western Pocahontas Properties | 2019-03-13 | 18-1329 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Before GREGORY, Chief Judge, WYNN and THACKER, Circuit Judges.", "parties": "", "opinions": [{"author": "Charleston. John T. Copenhaver, Jr., Senior District Judge", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRC... | GREGORY | WYNN | THACKER | 1 | {"GREGORY": ", Chief", "WYNN": ", Circuit", "THACKER": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4599176/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
8,443,927 | MOUNTAIN VALLEY PIPELINE, LLC v. WESTERN POCAHONTAS PROPERTIES LIMITED PARTNERSHIP, Parcel ID No. 6-5F-1 (Terminated: 1/11/2018), 1-31-10, 1-30-8, 5-26-2, - and D. Lane McMillion, Parcel ID No. 1-13-49, 1-13-68 Dale L. McMillion, Parcel ID No. 1-13-49, 1-13-68 Alicia D. McMillion, Parcel ID No. 1-13-49, 1-13-68 Paco La... | Mountain Valley Pipeline, LLC v. Western Pocahontas Props. Ltd. | 2019-03-13 | No. 18-1329 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Gregory, Thacker, Wynn", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415358/", "author_raw": ""}]} | GREGORY | THACKER | WYNN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443927/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,599,872 | UNITED STATES of America, Plaintiff - Appellant, v. Travis Antwone MOORE, A/K/A Trav, Trap, Defendant - Appellee. | United States v. Travis Moore | 2019-03-14 | 18-4481 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Agee, Floyd, Traxler", "parties": "", "opinions": [{"author": "FLOYD, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-4481\n\n\nUNITED STATES OF... | AGEE | FLOYD | TRAXLER | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4599872/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,599,875 | Kristiana Tweed BURRELL, Individually and as Administratrix of the Estate of Ariel Grace Burrell; Travis Burrell, Plaintiffs - Appellants, v. BAYER CORPORATION, an Indiana Corporation; Bayer Healthcare LLC, a Delaware Corporation; Christopher Ford Williams; Stacy D. Travis, Dr.; Biltmore Ob-Gyn, P.A. ; Bayer Essure Inc... | Kristiana Burrell v. Bayer Corporation | 2019-03-14 | 17-1715 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Floyd, Harris, Coggins", "parties": "", "opinions": [{"author": "PAMELA HARRIS, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 17-1715\n\n\nKRI... | FLOYD | HARRIS | COGGINS | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4599875/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,600,526 | NCO FINANCIAL SYSTEMS, INCORPORATED, Now Known as EGS Financial Care, Inc., Plaintiff - Appellee, v. MONTGOMERY PARK, LLC, Defendant - Appellant. | NCO Financial Systems, Inc. v. Montgomery Park, LLC | 2019-03-15 | 17-2226 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Gregory, Niemeyer, Harris", "parties": "", "opinions": [{"author": "NIEMEYER, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 17-2226\n\n\nNCO F... | GREGORY | NIEMEYER | HARRIS | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4600526/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,600,900 | Zoe SPENCER, Plaintiff - Appellant, v. VIRGINIA STATE UNIVERSITY; Keith T. Miller, Defendants - Appellees. | Zoe Spencer v. Virginia State University | 2019-03-18 | 17-2453 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Wilkinson, Floyd, Richardson", "parties": "", "opinions": [{"author": "RICHARDSON, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 17-2453\n\n\nZOE... | WILKINSON | FLOYD | RICHARDSON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4600900/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,601,209 | UNITED STATES of America, Plaintiff - Appellee, v. Joseph Howard DAVIS, Defendant - Appellant. | United States v. Joseph Davis | 2019-03-19 | 18-4095 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Wilkinson, Niemeyer, King", "parties": "", "opinions": [{"author": "NIEMEYER, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-4095\n\n\nUNITE... | WILKINSON | NIEMEYER | KING | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4601209/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,601,224 | Howard Egba DUNCAN, Jr., A/K/A Duncan Egbaf, A/K/A Howard Duncan, Petitioner, v. William P. BARR, Attorney General, Respondent. | Howard Duncan v. William Barr | 2019-03-19 | 17-2423 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Motz, Duncan, Quattlebaum", "parties": "", "opinions": [{"author": "DUNCAN, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 17-2423\n\n\nHOWARD E... | MOTZ | DUNCAN | QUATTLEBAUM | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4601224/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,601,605 | Rosa CABRERA VASQUEZ, A/K/A Ruth Calderon Rocha, Petitioner, v. William P. BARR, Attorney General, Respondent. | Rosa Cabrera Vasquez v. William Barr | 2019-03-20 | 18-1226 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Gregory, Wynn, Thacker", "parties": "", "opinions": [{"author": "Petition for review granted; vacated and remanded by published opinion. Chief Judge Gregory", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT... | GREGORY | WYNN | THACKER | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4601605/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,601,609 | Howard Duncan v. William Barr | 2019-03-20 | 17-2423 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Before MOTZ, DUNCAN and QUATTLEBAUM, Circuit Judges.", "parties": "", "opinions": [{"author": "DUNCAN, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n ... | MOTZ | DUNCAN | QUATTLEBAUM | 1 | {"MOTZ": ", Circuit", "DUNCAN": ", Circuit", "QUATTLEBAUM": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4601609/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,602,365 | Tim P. BRUNDLE, ON BEHALF OF the CONSTELLIS EMPLOYEE STOCK OWNERSHIP PLAN, Plaintiff - Appellee, and Andrew Halldorson, on Behalf of the Constellis Employee Stock Ownership Plan, and on Behalf of a Class of All Other Persons Similarly Situated, Plaintiff, v. WILMINGTON TRUST, N.A., as Successor to Wilmington Trust Reti... | Tim Brundle v. Wilmington Trust, N.A. | 2019-03-21 | 17-1873; 17-2224; 17-2323; 17-2324; 18-1029 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Gregory, Motz, Floyd", "parties": "", "opinions": [{"author": "DIANA GRIBBON MOTZ, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n ... | GREGORY | MOTZ | FLOYD | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4602365/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,602,366 | Sharyl Thompson ATTKISSON; James Howard Attkisson; Sarah Judith Starr Attkisson, Plaintiffs - Appellants, v. Eric Himpton HOLDER, Jr., Individually; Patrick R. Donahoe, Individually; Unknown Named Agents of the Department of Justice, in Their Individual Capacities; Unknown Named Agents of the United States Postal Servi... | Sharyl Attkisson v. Eric Holder, Jr. | 2019-03-21 | 18-1677 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Wynn", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/9888176/", "author_raw": ""}, {"author": "", "type": "035concurrenceinpart", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/98... | WYNN | WYNN | 0 | {} | 5 | 0 | 0 | 3 | 2 | null | https://www.courtlistener.com/api/rest/v4/clusters/4602366/ | Published | 1 | 1 | 0 | 1 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,602,938 | Tim Brundle v. Wilmington Trust, N.A. | 2019-03-22 | 17-1873 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Before GREGORY, Chief Judge, and MOTZ and FLOYD, Circuit Judges.", "parties": "", "opinions": [{"author": "DIANA GRIBBON MOTZ, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n ... | GREGORY | MOTZ | FLOYD | 1 | {"GREGORY": ", Chief", "MOTZ": ", Circuit", "FLOYD": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4602938/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,602,939 | Howard Duncan v. William Barr | 2019-03-22 | 17-2423 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Before MOTZ, DUNCAN and QUATTLEBAUM, Circuit Judges.", "parties": "", "opinions": [{"author": "DUNCAN, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n ... | MOTZ | DUNCAN | QUATTLEBAUM | 1 | {"MOTZ": ", Circuit", "DUNCAN": ", Circuit", "QUATTLEBAUM": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4602939/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,603,306 | R.F., a Minor Child, BY AND THROUGH Her Parents and Next Friends, E.F. and H.F.; E.F.; H.F., on Their Own Behalves, Plaintiffs - Appellants, v. CECIL COUNTY PUBLIC SCHOOLS, Defendant - Appellee, and D'Ette W. Devine, Superintendent (Officially); Sarah Farr, Director of Special Education (Officially), Defendants. Counci... | R.F. v. Cecil County Public Schools | 2019-03-25 | 18-1780 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Agee, Harris, Duncan", "parties": "", "opinions": [{"author": "NETWORK; THE JUDGE DAVID L. BAZELON CENTER FOR MENTAL", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n ... | AGEE | HARRIS | DUNCAN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4603306/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,603,307 | Lance R. BELVILLE; Donald C. Carr; Mindi Stewart; Stanley Stewart; Charles Johnson; Jill Durant; Michael Antramgarza; Quintin Williams; ACA Legal Investigations, Inc. ; John McGee; David H. Patton; Inez A. Patton; Pamela D. Smith; Betty J. Trinque; Sharon Shaffer ; Robert Brandon; Daniel Gallegos ; Timothy Matthews; Sa... | Lance Belville v. Ford Motor Company | 2019-03-25 | 18-1470 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Agee, Harris, Duncan", "parties": "", "opinions": [{"author": "AGEE, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-1470\n\n\nLANCE... | AGEE | HARRIS | DUNCAN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4603307/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,603,788 | Zoe Spencer v. Virginia State University | 2019-03-26 | 17-2453 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Before WILKINSON, FLOYD, and RICHARDSON, Circuit Judges.", "parties": "", "opinions": [{"author": "RICHARDSON, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n ... | WILKINSON | FLOYD | RICHARDSON | 1 | {"WILKINSON": ", Circuit", "FLOYD": ", Circuit", "RICHARDSON": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4603788/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,603,789 | UNITED STATES of America, Plaintiff - Appellee, v. Justin Tyme HAWLEY, Defendant - Appellant. | United States v. Justin Hawley | 2019-03-26 | 18-4167 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Wynn, Diaz, Richardson", "parties": "", "opinions": [{"author": "WYNN, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-4167\n\n\nUNITED ST... | WYNN | DIAZ | RICHARDSON | 1 | {} | 3 | 0 | 0 | 2 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4603789/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,604,190 | UNITED STATES of America, Plaintiff - Appellee, v. Michael SMITH, Jr., A/K/A Mikey, A/K/A Lil Mike, A/K/A Mik, Defendant - Appellant. United States of America, Plaintiff - Appellee, v. Mark Bazemore, A/K/A Uncle Mark, Defendant - Appellant. United States of America, Plaintiff - Appellee, v. Timothy Hurtt, A/K/A Uncle T... | United States v. Michael Smith | 2019-03-27 | 16-4746; 16-4764; 16-4765 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Niemeyer, Thacker, Richardson", "parties": "", "opinions": [{"author": "RICHARDSON, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 16-4746\n\n\nUNI... | NIEMEYER | THACKER | RICHARDSON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4604190/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,604,710 | UNITED STATES of America, Plaintiff - Appellee, v. Jose Benjamin GUZMAN-VELASQUEZ, Defendant - Appellant. | United States v. Jose Guzman-Velasquez | 2019-03-28 | 18-4133 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Motz, Quattlebaum, Duncan", "parties": "", "opinions": [{"author": "DIANA GRIBBON MOTZ, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-4133\n\n... | MOTZ | QUATTLEBAUM | DUNCAN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4604710/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,595,685 | UNITED STATES of America, Plaintiff-Appellee v. Alan Victor GOMEZ GOMEZ, Defendant-Appellant | United States v. Alan Gomez Gomez | 2019-03-01 | 17-20526 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "James, Clement, Higginson", "parties": "", "opinions": [{"author": "JAMES C. HO, Circuit Judge:", "type": "010combined", "text": "Case: 17-20526 Document: 00514857955 Page: 1 Date Filed: 03/01/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH... | JAMES | CLEMENT | HIGGINSON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4595685/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,595,935 | UNITED STATES of America, Plaintiff-Appellee, v. Oladimeji Seun AYELOTAN; Femi Alexander Mewase; Rasaq Aderoju Raheem, Defendants-Appellants. | United States v. Oladimeji Ayelotan | 2019-03-04 | 17-60397 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "Stewart, Dennis, Willett", "parties": "", "opinions": [{"author": "DON R. WILLETT, Circuit Judge:", "type": "010combined", "text": "Case: 17-60397 Document: 00514858253 Page: 1 Date Filed: 03/04/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\n ... | STEWART | DENNIS | WILLETT | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4595935/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,596,349 | United States v. Oladimeji Ayelotan | 2019-03-04 | 17-60397 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "Before STEWART, Chief Judge, and DENNIS and WILLETT, Circuit Judges.", "parties": "", "opinions": [{"author": "DON R. WILLETT, Circuit Judge:", "type": "010combined", "text": "Case: 17-60397 Document: 00514859557 Page: 1 Date Filed: 03/04/2019\n\n\n\n\n REVISED March 4, 2019\... | STEWART | DENNIS | WILLETT | 1 | {"STEWART": ", Chief", "DENNIS": ", Circuit", "WILLETT": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4596349/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,597,537 | Norma Yanet FUENTES-PENA; Erik Aristedes Vijil-Fuentes; Judith Daniela Vijil-Fuentes, Petitioners v. William P. BARR, U. S. Attorney General, Respondent | Norma Fuentes-Pena v. William Barr, U. S. A | 2019-03-06 | 17-60637 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "Jolly, Dennis, Higginson", "parties": "", "opinions": [{"author": "E. GRADY JOLLY, Circuit Judge:", "type": "010combined", "text": "Case: 17-60637 Document: 00514860849 Page: 1 Date Filed: 03/06/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\n ... | JOLLY | DENNIS | HIGGINSON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4597537/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,597,542 | JATERA CORPORATION; Esther Randle Moore, Plaintiffs-Appellants v. US BANK NATIONAL ASSOCIATION, AS TRUSTEE, in Trust FOR the REGISTERED HOLDERS OF CITIGROUP MORTGAGE LOAN TRUST, Asset-Backed Pass-Through Certificates, Series 2005-HE3; Select Portfolio Servicing, Incorporated, Defendants-Appellees | Jatera Corporation v. US Bank National Asso | 2019-03-06 | 18-10248 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "Before SMITH, BARKSDALE, and HO, Circuit Judges.", "parties": "", "opinions": [{"author": "RHESA HAWKINS BARKSDALE, Circuit Judge:", "type": "010combined", "text": "Case: 18-10248 Document: 00514861432 Page: 1 Date Filed: 03/06/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n ... | SMITH | BARKSDALE | HO | 1 | {"SMITH": ", Circuit", "BARKSDALE": ", Circuit", "HO": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4597542/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,597,955 | TEXAS TECH PHYSICIANS ASSOCIATES, Plaintiff-Appellant v. UNITED STATES DEPARTMENT OF HEALTH AND HUMAN SERVICES; Alex M. Azar, II, Secretary, U.S. Department of Health and Human Services, Defendants-Appellees | Tex. Tech Physicians Assocs. v. U.S. Dep't of Health & Human Servs. | 2019-03-07 | 18-10620 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "King, Higginson, Costa", "parties": "", "opinions": [{"author": "GREGG COSTA, Circuit Judge:", "type": "010combined", "text": "Case: 18-10620 Document: 00514863670 Page: 1 Date Filed: 03/07/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\n ... | KING | HIGGINSON | COSTA | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4597955/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,597,960 | Alejandro JORGE-CHAVELAS; Alfredo Moreno-Abarca, Plaintiffs - Appellees v. LOUISIANA FARM BUREAU CASUALTY INSURANCE COMPANY; Louisiana Farm Bureau Mutual Insurance Company, Defendants - Appellants v. American Interstate Insurance Company, Intervenor Plaintiff - Appellee | Jorge-Chavelas v. La. Farm Bureau Cas. Ins. Co. | 2019-03-07 | 18-30388 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "King, Higginson, Costa", "parties": "", "opinions": [{"author": "GREGG COSTA, Circuit Judge:", "type": "010combined", "text": "Case: 18-30388 Document: 00514863514 Page: 1 Date Filed: 03/07/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\n ... | KING | HIGGINSON | COSTA | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4597960/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,598,194 | In RE: Julius Omar ROBINSON, Movant. United States of America, Plaintiff-Appellee, v. Julius Omar Robinson, Also Known as Face, Also Known as Scar, Also Known as Scarface, Defendant-Appellant. | United States v. Robinson (In Re Robinson) | 2019-03-08 | 18-10732; 18-70022 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "Higginbotham, Smith, Engelhardt", "parties": "", "opinions": [{"author": "JERRY E. SMITH, Circuit Judge:", "type": "010combined", "text": "Case: 18-70022 Document: 00514865791 Page: 1 Date Filed: 03/08/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRC... | HIGGINBOTHAM | SMITH | ENGELHARDT | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4598194/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
8,443,910 | Nancy MORROW Alvin Russell Moon, on Behalf of Estate of Austin Russell Moon, on Behalf of C.D., a Minor Christa Donahue, on Behalf of A.D., a Minor v. Jonathan MEACHUM | Morrow v. Meachum | 2019-03-08 | No. 17-11243 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "Costa, Davis, Oldham", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415341/", "author_raw": ""}]} | COSTA | DAVIS | OLDHAM | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443910/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,598,522 | James A. LATIOLAIS, Plaintiff-Appellee v. HUNTINGTON INGALLS, INCORPORATED, Formerly Known as Northrop Grumman Shipbuilding, Incorporated, Formerly Known as Northrop Grumman Ship Systems, Incorporated, Formerly Known as Avondale Industries, Incorporated, Defendant-Appellant | James Latiolais v. Eagle, Incorporated | 2019-03-11 | 18-30652 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "Jones, Haynes, Oldham", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/9888136/", "author_raw": ""}, {"author": "", "type": "040dissent", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opin... | JONES | HAYNES | OLDHAM | 1 | {} | 4 | 0 | 2 | 0 | 2 | null | https://www.courtlistener.com/api/rest/v4/clusters/4598522/ | Published | 1 | 1 | 0 | 0 | 1 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,598,649 | Kyle Shaw v. Karnes County, Texas | 2019-03-11 | 17-50937 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "Before JONES, BARKSDALE, and WILLETT, Circuit Judges.", "parties": "", "opinions": [{"author": "DON R. WILLETT, Circuit Judge:", "type": "010combined", "text": "Case: 17-50937 Document: 00514867808 Page: 1 Date Filed: 03/11/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n ... | JONES | BARKSDALE | WILLETT | 1 | {"JONES": ", Circuit", "BARKSDALE": ", Circuit", "WILLETT": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4598649/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,598,650 | Glenn Ford v. District Attorney Caddo Parish, et a | 2019-03-11 | 18-30126 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "Before SMITH, DUNCAN, and ENGELHARDT, Circuit Judges.", "parties": "", "opinions": [{"author": "KURT D. ENGELHARDT, Circuit Judge:", "type": "010combined", "text": "Case: 18-30126 Document: 00514867978 Page: 1 Date Filed: 03/11/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n ... | SMITH | DUNCAN | ENGELHARDT | 1 | {"SMITH": ", Circuit", "DUNCAN": ", Circuit", "ENGELHARDT": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4598650/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
8,443,928 | Kyle Ray SHAW v. Dwayne VILLANUEVA, in his Individual and Official Capacity as County Sheriff Robert C. Ebrom, Jr., in his Individual and Official Capacity as Chief Deputy Sheriff | Shaw v. Villanueva | 2019-03-11 | No. 17-50937 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "Barksdale, Jones, Willett", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415359/", "author_raw": ""}]} | BARKSDALE | JONES | WILLETT | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443928/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
8,443,929 | Andrea ARMSTRONG, of the Estate of Glen Ford v. Don ASHLEY Gary Alderman Gary Pittman Everett T. Rushing Billy Lockwood, Wrongly Identified as Estate of Billy Lockwood Frank Datcher Glynn Mitchell Rodney Price | Armstrong v. Ashley | 2019-03-11 | No. 18-30126 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "Duncan, Engelhardt, Smith", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415360/", "author_raw": ""}]} | DUNCAN | ENGELHARDT | SMITH | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443929/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,599,859 | Gustavo MONTEON-CAMARGO, Also Known as Ulysius Montillon-Camargo, Also Known as Gustavo Monteon-Camargo, Petitioner, v. William P. BARR, U.S. Attorney General, Respondent. | Gustavo Monteon-Camargo v. William Barr, U. S. Att | 2019-03-14 | 17-60345 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "Smith, Duncan, Engelhardt", "parties": "", "opinions": [{"author": "JERRY E. SMITH, Circuit Judge:", "type": "010combined", "text": "Case: 17-60345 Document: 00514872705 Page: 1 Date Filed: 03/14/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\... | SMITH | DUNCAN | ENGELHARDT | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4599859/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,599,961 | State of TEXAS, Plaintiff-Appellee, v. ALABAMA-COUSHATTA TRIBE OF TEXAS, Defendant-Appellant. | State of Texas v. Alabama-Coushatta Tribe of TX | 2019-03-14 | 18-40116 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "Smith, Duncan, Engelhardt", "parties": "", "opinions": [{"author": "JERRY E. SMITH, Circuit Judge:", "type": "010combined", "text": "Case: 18-40116 Document: 00514873577 Page: 1 Date Filed: 03/14/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\... | SMITH | DUNCAN | ENGELHARDT | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4599961/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,599,962 | In RE: UNITED STATES BUREAU OF PRISONS, DEPARTMENT OF JUSTICE, Respondent - Appellant | In Re U.S. Bureau of Prisons, DEPT. OF JUSTICE | 2019-03-14 | 18-50512 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "Higginbotham, Smith, Higginson", "parties": "", "opinions": [{"author": "STEPHEN A. HIGGINSON, Circuit Judge:", "type": "010combined", "text": "Case: 18-50512 Document: 00514873161 Page: 1 Date Filed: 03/14/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH... | HIGGINBOTHAM | SMITH | HIGGINSON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4599962/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,600,876 | PAPALOTE CREEK II, L.L.C., Formerly Known as Papalote Creek Windfarm II, L.L.C., Plaintiff-Appellant, v. LOWER COLORADO RIVER AUTHORITY, Defendant-Appellee. | Papalote Creek II, L.L.C. v. Lower Colorado River | 2019-03-15 | 17-50852 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "Before HIGGINBOTHAM, ELROD, and HO, Circuit Judges.", "parties": "", "opinions": [{"author": "JENNIFER WALKER ELROD, Circuit Judge:", "type": "010combined", "text": "Case: 17-50852 Document: 00514875536 Page: 1 Date Filed: 03/15/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n ... | HIGGINBOTHAM | ELROD | HO | 1 | {"HIGGINBOTHAM": ", Circuit", "ELROD": ", Circuit", "HO": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4600876/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,601,588 | BP EXPLORATION & PRODUCTION, INCORPORATED; BP America Production Company; BP, P.L.C., Requesting Parties-Appellants, v. CLAIMANT ID 100217946, Objecting Party-Appellee. | BP Exploration & Prodn, Inc. v. ID | 2019-03-18 | 18-30147 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "Before WIENER, DENNIS, and OWEN, Circuit Judges.", "parties": "", "opinions": [{"author": "PER CURIAM", "type": "010combined", "text": "IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT United States Court of Appeals\n Fifth Ci... | WIENER | DENNIS | OWEN | 1 | {"WIENER": ", Circuit", "DENNIS": ", Circuit", "OWEN": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4601588/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,601,287 | ENCOMPASS OFFICE SOLUTIONS, INCORPORATED, Plaintiff-Appellee, v. LOUISIANA HEALTH SERVICE & INDEMNITY COMPANY, Doing Business as BlueCross BlueShield of Louisiana. Defendant-Appellant. | Encompass Office Solutions, Inc. v. La. Health Serv. & Indem. Co. | 2019-03-19 | 17-10736 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "Jones, Barksdale, Willett", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/9824710/", "author_raw": ""}, {"author": "", "type": "040dissent", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/... | JONES | BARKSDALE | WILLETT | 1 | {} | 4 | 0 | 2 | 0 | 2 | null | https://www.courtlistener.com/api/rest/v4/clusters/4601287/ | Published | 1 | 1 | 0 | 0 | 1 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,601,852 | UNITED STATES of America, Plaintiff-Appellee, v. Daniel SALINAS, Defendant-Appellant. United States of America, Plaintiff-Appellee, v. Mark Anthony Salinas, Defendant-Appellant. | United States v. Mark Salinas | 2019-03-20 | 18-40361; cons w/ 18-40407 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "Before HIGGINBOTHAM, ELROD, and HO, Circuit Judges.", "parties": "", "opinions": [{"author": "PER CURIAM", "type": "010combined", "text": "Case: 18-40361 Document: 00514881265 Page: 1 Date Filed: 03/20/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n ... | HIGGINBOTHAM | ELROD | HO | 1 | {"HIGGINBOTHAM": ", Circuit", "ELROD": ", Circuit", "HO": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4601852/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,601,854 | UNITED STATES of America, Plaintiff-Appellee v. Calvin ALLEN, Defendant-Appellant | United States v. Calvin Allen | 2019-03-20 | 17-60440 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "James, Higginbotham, Elrod", "parties": "", "opinions": [{"author": "JAMES C. HO, Circuit Judge:", "type": "010combined", "text": "Case: 17-60440 Document: 00514881108 Page: 1 Date Filed: 03/20/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\n ... | JAMES | HIGGINBOTHAM | ELROD | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4601854/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,601,859 | BP EXPLORATION & PRODUCTION, INCORPORATED; BP America Production Company; BP, P.L.C., Requesting Parties-Appellants, v. CLAIMANT ID 100281817, Objecting Party-Appellee. | BP Exploration & Prodn, Inc. v. ID | 2019-03-20 | 18-30394 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "Jones, Haynes, Oldham", "parties": "", "opinions": [{"author": "ANDREW S. OLDHAM, Circuit Judge:", "type": "010combined", "text": "Case: 18-30394 Document: 00514881236 Page: 1 Date Filed: 03/20/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT Unit... | JONES | HAYNES | OLDHAM | 1 | {} | 2 | 0 | 0 | 1 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4601859/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,602,317 | ALLIANCE FOR GOOD GOVERNMENT, Plaintiff - Appellee v. COALITION FOR BETTER GOVERNMENT, Defendant - Appellant | Alliance for Good Government v. Coalition for Bett | 2019-03-21 | 18-30759 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "Higginbotham, Smith, Higginson", "parties": "", "opinions": [{"author": "PATRICK E. HIGGINBOTHAM, Circuit Judge:", "type": "010combined", "text": "Case: 18-30759 Document: 00514882154 Page: 1 Date Filed: 03/21/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE F... | HIGGINBOTHAM | SMITH | HIGGINSON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4602317/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,603,084 | Teresa BUCHANAN, Plaintiff - Appellant v. F. King ALEXANDER; Damon Andrew; A. G. Monaco; Gaston Reinoso, Defendants - Appellees | Teresa Buchanan v. F. Alexander | 2019-03-22 | 18-30148 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "Wiener, Southwick, Costa", "parties": "", "opinions": [{"author": "WIENER, Circuit Judge", "type": "010combined", "text": "Case: 18-30148 Document: 00514885022 Page: 1 Date Filed: 03/22/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT United Stat... | WIENER | SOUTHWICK | COSTA | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4603084/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,603,272 | Joseph THOMAS; Vernon Ayers; Melvin Lawson, Plaintiffs - Appellees v. Phil BRYANT, Governor of the State of Mississippi; Delbert Hosemann, Secretary of State of the State of Mississippi, Both in the Official Capacities of Their Own Offices and in Their Official Capacities as Members of the State Board of Election Commi... | Joseph Thomas v. Phil Bryant | 2019-03-22 | 19-60133 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "Dennis, Clement, Costa", "parties": "", "opinions": [{"author": "GREGG COSTA, Circuit Judge:", "type": "010combined", "text": "Case: 19-60133 Document: 00514885572 Page: 1 Date Filed: 03/22/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT United S... | DENNIS | CLEMENT | COSTA | 1 | {} | 2 | 0 | 1 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4603272/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,603,529 | Joseph Thomas v. Phil Bryant | 2019-03-25 | 19-60133 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "Before DENNIS, CLEMENT, and COSTA, Circuit Judges.", "parties": "", "opinions": [{"author": "GREGG COSTA, Circuit Judge:", "type": "010combined", "text": "Case: 19-60133 Document: 00514887045 Page: 1 Date Filed: 03/25/2019\n\n\n\n\n REVISED March 25, 2019\n\n IN THE U... | DENNIS | CLEMENT | COSTA | 1 | {"DENNIS": ", Circuit", "CLEMENT": ", Circuit", "COSTA": ", Circuit"} | 2 | 0 | 1 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4603529/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,603,849 | Sheaneter J. BOGAN, Plaintiff-Appellant v. MTD CONSUMER GROUP, INCORPORATED, Defendant-Appellee | Sheaneter Bogan v. MTD Consumer Group, Inc. | 2019-03-26 | 17-60697 | U.S. Court of Appeals for the Fifth Circuit | {"judges": "Wiener, Southwick, Costa", "parties": "", "opinions": [{"author": "GREGG COSTA, Circuit Judge:", "type": "010combined", "text": "Case: 17-60697 Document: 00514888165 Page: 1 Date Filed: 03/26/2019\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n FOR THE FIFTH CIRCUIT\n ... | WIENER | SOUTHWICK | COSTA | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4603849/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 3 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.